CN116688754A - Ship flue gas desulfurization automatic control system and method thereof - Google Patents
Ship flue gas desulfurization automatic control system and method thereof Download PDFInfo
- Publication number
- CN116688754A CN116688754A CN202310818132.4A CN202310818132A CN116688754A CN 116688754 A CN116688754 A CN 116688754A CN 202310818132 A CN202310818132 A CN 202310818132A CN 116688754 A CN116688754 A CN 116688754A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- desulfurization
- flue gas
- training
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000006477 desulfuration reaction Methods 0.000 title claims abstract description 238
- 230000023556 desulfurization Effects 0.000 title claims abstract description 238
- 239000003546 flue gas Substances 0.000 title claims abstract description 213
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 title claims abstract description 212
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000000779 smoke Substances 0.000 claims abstract description 92
- 230000008859 change Effects 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 136
- 238000012549 training Methods 0.000 claims description 80
- 239000011159 matrix material Substances 0.000 claims description 61
- 238000013527 convolutional neural network Methods 0.000 claims description 43
- 238000013507 mapping Methods 0.000 claims description 35
- 230000003009 desulfurizing effect Effects 0.000 claims description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 24
- 238000005406 washing Methods 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 13
- 239000003517 fume Substances 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 6
- 238000012300 Sequence Analysis Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 2
- 239000007789 gas Substances 0.000 abstract description 23
- 239000002699 waste material Substances 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000013135 deep learning Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 13
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 12
- 238000011176 pooling Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000001276 controlling effect Effects 0.000 description 10
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 10
- 239000003795 chemical substances by application Substances 0.000 description 9
- 238000002485 combustion reaction Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 9
- 238000010219 correlation analysis Methods 0.000 description 8
- 230000004913 activation Effects 0.000 description 7
- 238000009826 distribution Methods 0.000 description 7
- 239000003344 environmental pollutant Substances 0.000 description 7
- 239000000446 fuel Substances 0.000 description 7
- 231100000719 pollutant Toxicity 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 6
- 239000007788 liquid Substances 0.000 description 6
- 239000000284 extract Substances 0.000 description 5
- 238000012806 monitoring device Methods 0.000 description 5
- 238000012098 association analyses Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000005507 spraying Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 2
- VHUUQVKOLVNVRT-UHFFFAOYSA-N Ammonium hydroxide Chemical compound [NH4+].[OH-] VHUUQVKOLVNVRT-UHFFFAOYSA-N 0.000 description 2
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 235000019738 Limestone Nutrition 0.000 description 2
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 2
- UCKMPCXJQFINFW-UHFFFAOYSA-N Sulphide Chemical compound [S-2] UCKMPCXJQFINFW-UHFFFAOYSA-N 0.000 description 2
- 235000011114 ammonium hydroxide Nutrition 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 239000000567 combustion gas Substances 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 239000008358 core component Substances 0.000 description 2
- 238000011234 economic evaluation Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000006028 limestone Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 238000012856 packing Methods 0.000 description 2
- 239000013618 particulate matter Substances 0.000 description 2
- 238000000746 purification Methods 0.000 description 2
- 239000002002 slurry Substances 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 150000004763 sulfides Chemical class 0.000 description 2
- 229910052717 sulfur Inorganic materials 0.000 description 2
- 239000011593 sulfur Substances 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- QAOWNCQODCNURD-UHFFFAOYSA-L Sulfate Chemical compound [O-]S([O-])(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-L 0.000 description 1
- XSQUKJJJFZCRTK-UHFFFAOYSA-N Urea Chemical compound NC(N)=O XSQUKJJJFZCRTK-UHFFFAOYSA-N 0.000 description 1
- 229910021529 ammonia Inorganic materials 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000005311 autocorrelation function Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004202 carbamide Substances 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 239000003054 catalyst Substances 0.000 description 1
- 238000010531 catalytic reduction reaction Methods 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000002283 diesel fuel Substances 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000002440 industrial waste Substances 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- -1 oxygen concentration Chemical compound 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- DHCDFWKWKRSZHF-UHFFFAOYSA-N sulfurothioic S-acid Chemical compound OS(O)(=O)=S DHCDFWKWKRSZHF-UHFFFAOYSA-N 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/92—Chemical or biological purification of waste gases of engine exhaust gases
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/46—Removing components of defined structure
- B01D53/48—Sulfur compounds
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2258/00—Sources of waste gases
- B01D2258/01—Engine exhaust gases
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2258/00—Sources of waste gases
- B01D2258/02—Other waste gases
- B01D2258/0283—Flue gases
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2259/00—Type of treatment
- B01D2259/45—Gas separation or purification devices adapted for specific applications
- B01D2259/4566—Gas separation or purification devices adapted for specific applications for use in transportation means
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Environmental & Geological Engineering (AREA)
- Analytical Chemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Combustion & Propulsion (AREA)
- Treating Waste Gases (AREA)
Abstract
Discloses an automatic control system and method for ship flue gas desulfurization. According to the method, a time sequence change analysis is carried out on a main engine power value, an auxiliary engine power value and a smoke index data value by adopting an artificial intelligence control technology based on deep learning, and time sequence change characteristics of the data are associated, so that the target power value of the desulfurization circulating pump is comprehensively controlled, the desulfurization efficiency and efficiency of ship tail gas are optimized, and the waste of energy sources is avoided, so that the purpose of protecting the environment is achieved.
Description
Technical Field
The application relates to the field of intelligent control, in particular to an automatic control system and method for ship flue gas desulfurization.
Background
In the highly developed era of world trade today, the modes of cargo transportation are diverse. Currently, over two thirds of international trade total traffic and 90% of the total import and export goods transportation in China depend on ocean transportation. However, as the number of transport vessels has increased dramatically, the pollution and harm of the atmospheric and marine environment caused by the pollutants discharged from the vessels has also increased. The tail gas discharged by the ship engine is directly discharged into the atmosphere through a chimney, which forms a serious threat to the atmospheric environment.
In the prior art, a ship is configured with a desulfurization system to purify the exhaust gas discharged from an engine. In the process of actually performing tail gas purification and desulfurization, a desulfurization system is usually required to be manually controlled to realize the desulfurization of tail gas. However, the manual control is prone to the problem of inaccurate operation, such as inaccurate control of the target power value of the desulfurization circulating pump, and does not pay attention to the suitability relationship between the target power value and the exhaust emission, so that the desulfurization effect is poor and the efficiency is low, and the energy waste is also easily caused.
Accordingly, an optimized marine vessel flue gas desulfurization automatic control system is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides an automatic control system and a method for ship flue gas desulfurization, which are used for analyzing time sequence changes of a main engine power value, an auxiliary engine power value and a flue gas index data value by adopting an artificial intelligent control technology based on deep learning, and correlating time sequence change characteristics of the data so as to comprehensively and accurately control a target power value of a desulfurization circulating pump, thereby optimizing desulfurization efficiency and efficiency of ship tail gas, avoiding energy waste and achieving the aim of protecting environment.
According to one aspect of the present application, there is provided an automatic control system for ship flue gas desulfurization, comprising:
the parameter data acquisition module is used for acquiring the power data of the main machine, the power data of the auxiliary machine and the flue gas index data at the exhaust port of the desulfurizing tower detected by the flue gas detection device;
the desulfurization mode preselection module is used for acquiring a desulfurization mode preselected by a user;
the valve control module is used for controlling the desulfurization valve equipment and the flue gas valve equipment to work based on the desulfurization mode;
the desulfurization circulating pump power control module is used for determining a target power value of the desulfurization circulating pump based on the main engine power data, the auxiliary engine power data and the flue gas index data;
and the desulfurization treatment module is used for controlling the desulfurization circulating pump to work based on the target power, conveying the washing water to the desulfurization tower, and carrying out desulfurization treatment on the ship flue gas by utilizing the washing water in the desulfurization tower.
According to another aspect of the present application, there is provided an automatic control method for ship flue gas desulfurization, comprising:
acquiring power data of a main machine, power data of an auxiliary machine and flue gas index data at an exhaust port of a desulfurizing tower detected by a flue gas detection device;
Obtaining a desulfurization mode selected by a user in advance;
controlling the desulfurization valve device and the flue gas valve device to work based on the desulfurization mode;
determining a target power value of the desulfurization circulating pump based on the main engine power data, the auxiliary engine power data and the flue gas index data;
and controlling the desulfurization circulating pump to work based on the target power, conveying the washing water to a desulfurization tower, and carrying out desulfurization treatment on ship flue gas by using the washing water in the desulfurization tower.
According to the embodiment of the disclosure, the time sequence change analysis is carried out on the power value of the main engine, the power value of the auxiliary engine and the data value of the flue gas index by adopting the artificial intelligence control technology based on deep learning, and the time sequence change characteristics of the data are associated, so that the target power value of the desulfurization circulating pump is comprehensively and accurately controlled, the desulfurization efficiency and efficiency of the ship tail gas are optimized, the waste of energy sources is avoided, and the purpose of protecting the environment is achieved.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a block diagram of an automatic control system for marine flue gas desulfurization in accordance with an embodiment of the present application;
FIG. 2 is a system architecture diagram of an automatic control system for marine flue gas desulfurization according to an embodiment of the present application;
FIG. 3 is a block diagram of a desulfurization circulation pump power control module in a marine flue gas desulfurization automatic control system according to an embodiment of the present application;
FIG. 4 is a block diagram of a parameter timing correlation feature extraction unit in a marine flue gas desulfurization automatic control system according to an embodiment of the present application;
FIG. 5 is a block diagram of a training module in a marine vessel flue gas desulfurization automation system in accordance with an embodiment of the present application;
FIG. 6 is a flow chart of a method for automatically controlling flue gas desulfurization of a ship according to an embodiment of the present application;
fig. 7 is an application scenario diagram of a ship flue gas desulfurization automatic control system according to an embodiment of the present application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
In the prior art, a ship is configured with a desulfurization system to purify the exhaust gas discharged from an engine. In the process of actually performing tail gas purification and desulfurization, a desulfurization system is usually required to be manually controlled to realize the desulfurization of tail gas. However, the manual control is prone to the problem of inaccurate operation, such as inaccurate control of the target power value of the desulfurization circulating pump, and does not pay attention to the suitability relationship between the target power value and the exhaust emission, so that the desulfurization effect is poor and the efficiency is low, and the energy waste is also easily caused. Accordingly, an optimized marine vessel flue gas desulfurization automatic control system is desired.
Fig. 1 is a block diagram of an automatic control system for flue gas desulfurization of a ship according to an embodiment of the present application. Fig. 2 is a system architecture diagram of an automatic control system for flue gas desulfurization of a ship according to an embodiment of the present application. As shown in fig. 1 and 2, the ship flue gas desulfurization automatic control system 300 according to an embodiment of the present application includes: the parameter data acquisition module 310 is used for acquiring the power data of the main machine, the power data of the auxiliary machine and the flue gas index data at the exhaust port of the desulfurizing tower detected by the flue gas detection device; a desulfurization mode pre-selection module 320, configured to obtain a desulfurization mode selected in advance by a user; a valve control module 330 for controlling the operation of the desulfurization valve device and the flue gas valve device based on the desulfurization mode; the desulfurization circulation pump power control module 340 is configured to determine a target power value of the desulfurization circulation pump based on the main engine power data, the auxiliary engine power data, and the flue gas index data; and the desulfurization processing module 350 is used for controlling the desulfurization circulating pump to work based on the target power, conveying the washing water to a desulfurization tower, and carrying out desulfurization processing on ship flue gas by utilizing the washing water in the desulfurization tower.
In particular, the parameter data acquisition module 310 is configured to acquire host power data, auxiliary power data, and flue gas index data at the exhaust port of the desulfurizing tower detected by the flue gas detection device. It should be understood that the main engine power data, the auxiliary engine power data and the flue gas index data at the exhaust port of the desulfurizing tower detected by the flue gas detection device play an important role in the automatic control of the desulfurization of the ship flue gas. Therefore, in the technical scheme of the application, the target power value of the desulfurization circulating pump is comprehensively controlled by analyzing the time sequence change of the power value of the main engine, the power value of the auxiliary engine and the data value of the flue gas index and correlating the time sequence change characteristics of the data, so that the desulfurization efficiency and efficiency of the ship tail gas are optimized, and the waste of energy sources is avoided, thereby achieving the purpose of protecting the environment.
Accordingly, in one possible implementation, the main engine power data, the auxiliary engine power data, and the flue gas index data at the exhaust port of the desulfurizing tower detected by the flue gas detecting apparatus may be obtained by: determining the source of the data: determining a source of the primary power data, the secondary power data, and the smoke detection device data, such as a sensor, monitoring device, or database; host power data acquisition: the power data of the host is acquired by means of a suitable sensor or monitoring device. The data may include parameters such as current, voltage and power factor of the host; auxiliary power data acquisition: likewise, power data of the auxiliary machine is acquired by means of suitable sensors or monitoring devices. The auxiliary machine can be other equipment in the power system, such as a generator, a transformer and the like; and (3) acquiring data of a smoke detection device: and detecting flue gas index data at an exhaust port of the desulfurizing tower by using a flue gas detection device. These data may include sulfur dioxide (SO 2) concentration, nitrogen oxides (NOx) concentration, particulate matter concentration, etc. in the flue gas; data recording and storage: and recording and storing the acquired main engine power data, auxiliary engine power data and flue gas index data. A database, data log, or other data management tool may be used for storage.
In particular, the desulfurization mode pre-selection module 320 is configured to obtain a desulfurization mode selected in advance by a user. It should be understood that desulfurization refers to the process of removing sulfides from combustion flue gas or industrial waste gas. The following are some common desulfurization modes: desulfurization after combustion: the method is that the flue gas is desulfurized after the combustion process; desulfurization before combustion: the method is to desulphurize the fuel before burning; biological desulfurization: this method utilizes microorganisms or biological enzymes to degrade sulfides in flue gas. Selective catalytic reduction desulfurization: this process uses a catalyst to catalyze the reaction of sulfide with a reducing agent (such as ammonia or urea), to convert sulfide to nitrogen and water, and the like. These desulfurization modes may be selected and used in combination according to specific application and emission requirements. Each desulfurization mode has the applicable scene and advantages and disadvantages, and the selection of the proper desulfurization mode needs to consider a plurality of factors such as fuel type, treatment efficiency, cost and the like.
Accordingly, in one possible implementation, the user pre-selected desulfurization mode may be obtained by, for example: first, for each desulfurization mode, related apparatuses and technologies are studied. Knowing information such as equipment, operating parameters, energy consumption and the like required by each mode; next, the fuel properties were analyzed: the nature of the fuel is critical to the choice of desulfurization mode. Analyzing the sulfur content, ash content, moisture content, combustion characteristics and other factors of the fuel to determine the most suitable desulfurization mode; consider the environmental requirement: the environmental requirements for different desulfurization modes are also different. Considering environmental regulations and emission standards of the region where the user is located, selecting a desulfurization mode meeting the requirements; then, economic evaluation: and carrying out economic evaluation, and considering factors such as investment cost, running cost, maintenance cost and the like of the desulfurization equipment. Comparing the economic benefits of different desulfurization modes, and selecting the mode with the best economical efficiency; finally, consider the operating conditions: depending on your specific operating conditions, such as combustion temperature, combustion gas composition, and combustion gas flow rate, etc., the appropriate desulfurization mode is selected.
In particular, the valve control module 330 is configured to control operation of the desulfurization valve device and the flue gas valve device based on the desulfurization mode. Notably, the desulfurization valve device and the flue gas valve device are typically operatively controlled by a control system. The following is a general control method: an automatic control system: sensors are used to monitor parameters in the desulfurization process, such as flue gas concentration, flow, temperature, etc., and feed these parameters back to the control system. The control system automatically adjusts the opening of the desulfurization valve and the flue gas valve according to the set parameter range and algorithm so as to realize the control and optimization of the desulfurization effect; manual control system: the opening of the desulfurization valve and the flue gas valve is manually adjusted by an operator through a control panel or a control console. According to actual conditions and operation experience, operators can gradually adjust the opening of the valve according to the needs so as to meet the requirement of desulfurization effect; programmable Logic Controller (PLC): PLC is a device dedicated to industrial automation control. Through programming control, the PLC can monitor and control the working states of the desulfurization valve and the flue gas valve. The PLC can automatically adjust the opening of the valve according to preset logic and algorithm to realize the control and optimization of the desulfurization process.
Accordingly, in one possible implementation, the operation of the desulfurization valve device and the flue gas valve device may be controlled based on the desulfurization mode by, for example: determining a desulfurization mode: selecting a proper desulfurization mode, such as wet desulfurization, semi-dry desulfurization or dry desulfurization, according to the working requirements and environmental conditions; setting desulfurization parameters: setting corresponding desulfurization parameters, such as addition amount of a desulfurizing agent, reaction temperature, reaction time and the like, according to the selected desulfurization mode; and (3) installing desulfurization valve equipment: according to the process requirements, the desulfurization valve equipment is arranged at a proper position and is usually positioned on a flue gas discharge port or a desulfurizing agent injection system; and (3) connecting a control system: the desulfurization valve equipment and the flue gas valve equipment are connected with a control system so as to realize the monitoring and control of the working state of the desulfurization valve equipment and the flue gas valve equipment; the automatic control mode is as follows: if an automatic control mode is adopted, a sensor can be used for monitoring parameters in the flue gas, such as oxygen concentration, flue gas temperature and the like, and the opening degrees of the desulfurization valve equipment and the flue gas valve equipment are automatically adjusted according to the set desulfurization parameters; manual control mode: if a manual control mode is adopted, operators can manually adjust the opening degrees of the desulfurization valve equipment and the flue gas valve equipment according to the flue gas parameters monitored in real time; PLC control mode: if a Programmable Logic Controller (PLC) is adopted, a corresponding control program can be written, and the opening of the desulfurization valve equipment and the opening of the flue gas valve equipment are automatically controlled by monitoring flue gas parameters and set desulfurization parameters; monitoring and adjusting: the desulfurization effect and the running state of the equipment are monitored regularly, and the desulfurization valve equipment and the flue gas valve equipment are regulated and maintained according to the needs, so that the normal operation of the desulfurization valve equipment and the flue gas valve equipment is ensured.
In particular, the desulfurization circulation pump power control module 340 is configured to determine a target power value of the desulfurization circulation pump based on the main engine power data, the auxiliary engine power data, and the flue gas index data. In particular, in one specific example of the application, as shown in fig. 3, the desulfurization recycle pump power control module 340 includes: a time sequence data acquisition unit 341, configured to acquire a host power value, an auxiliary power value, and a flue gas index data value at a plurality of predetermined time points in a predetermined time period; a parameter time sequence correlation feature extraction unit 342, configured to perform time sequence correlation analysis on the main power values, the auxiliary power values and the flue gas index data values at the plurality of predetermined time points to obtain a parameter time sequence correlation feature matrix; a smoke index time sequence change feature extraction unit 343, configured to perform time sequence analysis on the smoke index data values at the plurality of predetermined time points to obtain smoke index time sequence association feature vectors; a mapping association unit 344, configured to fuse the parameter time sequence association feature matrix and the flue gas index time sequence association feature vector to obtain a flue gas mapping association feature vector; and a target power value control unit 345, configured to determine a target power value of the desulfurization circulation pump based on the flue gas mapping association feature vector.
Correspondingly, the time-series data acquisition unit 341 is configured to acquire a host power value, an auxiliary power value, and a flue gas index data value at a plurality of predetermined time points within a predetermined time period. It should be understood that, in the actual desulfurization of the ship flue gas, the main engine power value, the auxiliary engine power value and the flue gas index data value are considered to have an important role in the automatic control of the desulfurization of the ship flue gas. Specifically, the main engine power value refers to the output power of the main engine of the ship, which reflects the power demand and the running state of the ship. Through monitoring the power value of the host, the system can adjust the working state of the desulfurization system according to the actual running condition of the ship so as to ensure the stability and high efficiency of the desulfurization effect. The auxiliary power value refers to power consumption of auxiliary equipment of the ship, and includes a power system, a cooling system, and the like of the ship. The monitoring of the auxiliary engine power value can help the system to judge the energy consumption condition of the ship, so that reasonable desulfurization work scheduling and energy management are performed, and the efficiency and energy saving performance of the system are improved. The flue gas index data value refers to the concentration of pollutants in ship flue gas and other related parameters, such as sulfur dioxide concentration, oxygen concentration and the like. Through monitoring the flue gas index data value, the system can know the pollution degree of ship flue gas in real time, so that the working parameters and the control strategy of the desulfurization system are adjusted according to actual conditions, and better desulfurization effect and environmental protection effect are achieved.
According to the embodiment of the application, the power sensor is used for acquiring the power data of the main engine and the power data of the auxiliary engine, and the smoke detection device is used for acquiring the smoke index data at the exhaust port of the desulfurizing tower. A power sensor is a device for measuring a power parameter in an electrical power system. It is commonly used to monitor and measure the power consumption or output of circuits, motors, generators, and other electrical devices. The power sensor can measure parameters such as current, voltage, power factor and the like, and power value is obtained through calculation. A smoke detection device is a device for detecting and monitoring pollutants and harmful gases in smoke emissions. It is generally used for monitoring the fume emission sources in industrial production process, coal-fired power plants, furnaces, boilers and the like. The flue gas detection device can evaluate the pollution degree of the flue gas by measuring the parameters such as the gas concentration, the temperature, the humidity and the like in the flue gas, and provides real-time monitoring and alarming functions. The application of the smoke detection device can help to monitor and control smoke emission, and ensure the safety of environment and human health. It has important functions in the fields of environmental protection, industrial safety, energy management and the like.
Accordingly, the parameter time-sequence correlation feature extraction unit 342 is configured to perform time-sequence correlation analysis on the main power values, the auxiliary power values and the flue gas index data values at the plurality of predetermined time points to obtain a parameter time-sequence correlation feature matrix. In particular, in one specific example of the present application, as shown in fig. 4, the parameter timing-related feature extraction unit 342 includes: a parameter time sequence arrangement subunit 3421, configured to arrange the host power value, the auxiliary power value, and the flue gas index data value at the plurality of predetermined time points into a host power time sequence input vector, an auxiliary power time sequence input vector, and a flue gas index time sequence input vector according to a time dimension, respectively; and the parameter time sequence association coding subunit 3422 is configured to arrange the main power time sequence input vector, the auxiliary power time sequence input vector and the smoke index time sequence input vector into a full-parameter time sequence input matrix according to a sample dimension, and then obtain the parameter time sequence association feature matrix through an association feature extractor based on a convolutional neural network model.
The parameter time sequence arrangement subunit 3421 is configured to arrange the host power values, the auxiliary power values, and the flue gas index data values at the plurality of predetermined time points into a host power time sequence input vector, an auxiliary power time sequence input vector, and a flue gas index time sequence input vector according to a time dimension, respectively. In order to effectively extract the change characteristic information of the main power value, the auxiliary power value and the flue gas index data value in the time dimension, the main power value, the auxiliary power value and the flue gas index data value at a plurality of preset time points need to be arranged into a main power time sequence input vector, an auxiliary power time sequence input vector and a flue gas index time sequence input vector according to the time dimension, so that the distribution information of the main power value, the auxiliary power value and the flue gas index data value in the time sequence is integrated.
Accordingly, in one possible implementation manner, the main power value, the auxiliary power value, and the flue gas index data value at the plurality of predetermined time points may be respectively arranged into a main power time sequence input vector, an auxiliary power time sequence input vector, and a flue gas index time sequence input vector according to a time dimension, for example: collecting main engine power values, auxiliary engine power values and flue gas index data values at a plurality of preset time points; the host power values are arranged in time sequence to form a host power time sequence input vector. Each element of the vector represents a host power value at a point in time; and arranging the auxiliary power values in time sequence to form auxiliary power time sequence input vectors. Each element of the vector represents an auxiliary power value at a point in time; and arranging the flue gas index data values in time sequence to form a flue gas index time sequence input vector. Each element of the vector represents a fume index data value at a point in time; ensuring that the lengths of the main power time sequence input vector, the auxiliary power time sequence input vector and the smoke index time sequence input vector are the same so that the main power time sequence input vector, the auxiliary power time sequence input vector and the smoke index time sequence input vector can correspond to the same time point; and taking the main engine power time sequence input vector, the auxiliary engine power time sequence input vector and the smoke index time sequence input vector as input data for further processing, analysis or modeling.
The parameter time sequence association coding subunit 3422 is configured to arrange the main power time sequence input vector, the auxiliary power time sequence input vector, and the smoke index time sequence input vector into a full parameter time sequence input matrix according to a sample dimension, and then obtain the parameter time sequence association feature matrix through an association feature extractor based on a convolutional neural network model. Considering that the main engine power value, the auxiliary engine power value and the flue gas index data value have dynamic change rules in the time dimension, and have time sequence association relations in the sample dimension. Therefore, after the host power time sequence input vector, the auxiliary power time sequence input vector and the smoke index time sequence input vector are further arranged into a full-parameter time sequence input matrix according to a sample dimension, a correlation feature extractor based on a convolutional neural network model with excellent performance in terms of implicit correlation feature extraction is used for carrying out feature mining on the full-parameter time sequence input matrix, so that time sequence collaborative correlation feature distribution information of the host power value, the auxiliary power value and the smoke index data value in a time dimension and the sample dimension is extracted, and a parameter time sequence correlation feature matrix is obtained.
According to an embodiment of the present application, after arranging the main power time sequence input vector, the auxiliary power time sequence input vector and the smoke index time sequence input vector into a full-parameter time sequence input matrix according to a sample dimension, obtaining the parameter time sequence associated feature matrix through an associated feature extractor based on a convolutional neural network model, including: each layer of the correlation feature extractor based on the convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the correlation feature extractor based on the convolutional neural network model is the parameter time sequence correlation feature matrix, and the input of the first layer of the correlation feature extractor based on the convolutional neural network model is the full parameter time sequence input matrix.
Convolutional neural network (Convolutional Neural Network, CNN for short) is a deep learning model and is widely applied to the fields of image recognition, computer vision, natural language processing and the like. The method is mainly characterized by automatically extracting features from data, and having translational invariance and local perceptibility.
The basic structure of CNN includes the following several major components: convolution layer: the convolutional layer is the core component of the CNN, which convolves the input data by applying a series of learnable filters (also called convolutional kernels). The convolution operation can extract local characteristics of input data and retain space structure information; activation function: the convolution layer is typically followed by an activation function, such as a ReLU, to introduce nonlinear transformations to enhance the expressive power of the model; pooling layer: the pooling layer serves to reduce the spatial dimensions of the feature map while retaining important features. Common pooling operations include maximum pooling and average pooling; full tie layer: the full join layer joins the outputs of the previous convolutional layer and the pooling layer and maps them to the probability distribution of the output class. The fully-connected layer is typically composed of a plurality of neurons, each connected to all neurons of the previous layer; dropout layer: to prevent overfitting, a Dropout layer is often added to the CNN that randomly sets the output of some neurons to 0 to reduce the dependency between neurons; batch normalization layer: the batch normalization layer is used for accelerating the training process and improving the stability of the model, and the model is more robust to the change of input data by normalizing the data of each batch. In general, the structure of CNNs is typically made up of a plurality of convolutions, activation functions, pooling layers, and fully-connected layers stacked alternately, with the output ultimately being converted to a probability distribution of categories by a softmax function. The structure can effectively extract the characteristics of the input data and update parameters through a back propagation algorithm in the training process, so that the input data is classified or predicted.
It should be noted that, in other specific examples of the present application, the time-series association analysis may be performed on the main power values, the auxiliary power values, and the flue gas index data values at the plurality of predetermined time points in other manners to obtain a parameter time-series association feature matrix, for example: collecting data: and collecting historical data of the power values of the main engine, the power values of the auxiliary engine and the flue gas index data values. The accuracy and the integrity of data are ensured; data preprocessing: preprocessing the collected data, including data cleaning, missing value processing and outlier processing. The quality and consistency of the data are ensured; alignment of data: aligning the power value of the main engine, the power value of the auxiliary engine and the data value of the flue gas index according to time, and ensuring that corresponding data are at the same time point; timing correlation analysis: the data is subjected to a time-series correlation analysis using an appropriate time-series correlation analysis method such as correlation analysis, time-series analysis, or multiple regression analysis. This will help you know the relationship between the main machine power value, auxiliary machine power value and flue gas index data value; constructing a feature matrix: and constructing a parameter time sequence association characteristic matrix according to the result of the time sequence association analysis. Taking the main engine power value, the auxiliary engine power value and the flue gas index data value as characteristics and taking the relevance of the main engine power value, the auxiliary engine power value and the flue gas index data value as weights among the characteristics; feature selection: and carrying out feature selection according to the result of the feature matrix. Selecting a feature having the highest correlation to the desired parameter timing relationship; model training and prediction: the model is trained and predicted using the selected features and an appropriate machine learning algorithm. Predicting future parameter time sequence association according to time sequence association characteristics of the main engine power value, the auxiliary engine power value and the flue gas index data value; model evaluation and optimization: the performance of the model was evaluated and the necessary optimizations were performed. And according to the evaluation result, adjusting parameters and algorithms of the model to improve the accuracy and stability of prediction.
Correspondingly, the smoke index time sequence variation feature extraction unit 343 is configured to perform time sequence analysis on the smoke index data values at the plurality of predetermined time points to obtain smoke index time sequence correlation feature vectors. In particular, in one specific example of the present application, the smoke index time sequence input vector is passed through a smoke index time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain the smoke index time sequence associated feature vector. It should be understood that, for the flue gas index data, the flue gas index data includes characteristic information such as pollutant concentration and emission trend of flue gas emission, which has an important influence on control of desulfurization treatment, so in order to capture and characterize time sequence change characteristics of the flue gas index data values, in the technical scheme of the application, the flue gas index time sequence input vector needs to be encoded in a flue gas index time sequence characteristic extractor based on a one-dimensional convolutional neural network model so as to extract time sequence related characteristic information of the flue gas index data values in a time dimension, thereby obtaining a flue gas index time sequence related characteristic vector.
According to an embodiment of the present application, the smoke index time sequence input vector is passed through a smoke index time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain the smoke index time sequence correlation feature vector, including: each layer of the smoke index time sequence feature extractor based on the one-dimensional convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature images based on a feature matrix to obtain pooled feature images; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the smoke index time sequence feature extractor based on the one-dimensional convolutional neural network model is the smoke index time sequence associated feature vector, and the input of the first layer of the smoke index time sequence feature extractor based on the one-dimensional convolutional neural network model is the smoke index time sequence input vector.
A one-dimensional convolutional neural network (1D CNN) is a neural network structure for processing sequence data. Unlike a conventional two-dimensional convolutional neural network (2D CNN), 1D CNN is mainly used to process one-dimensional data, such as time-series data, audio signals, text data, and the like. The basic structure of a 1D CNN is similar to a 2D CNN, including a convolutional layer, an activation function, a pooling layer, and a fully-connected layer. The convolution layer extracts local features in the input data by means of a sliding window and then maps these features into a new representation space by a convolution operation. The activation function introduces nonlinear transformation to increase the expressive power of the network. The pooling layer is used to reduce the size of the feature map and extract the most important features. The fully connected layer maps the characteristics of the pooling layer output to final output categories or values.
It should be noted that, in other specific examples of the present application, the time sequence analysis may be performed on the flue gas index data values at the plurality of predetermined time points in other manners to obtain a flue gas index time sequence correlation feature vector, for example, data collection: flue gas index data values, such as flue gas temperature, flue gas flow rate, concentration of pollutants in flue gas, etc., are collected at a plurality of predetermined time points. The accuracy and the integrity of data are ensured; data preprocessing: preprocessing the collected data, including data cleaning, missing value processing, outlier processing and the like. The quality and consistency of the data are ensured; alignment of data: aligning the collected data according to time points to ensure that the data of different indexes corresponds to the same time point; feature extraction: and extracting corresponding characteristics according to the time sequence characteristics of the flue gas index data. Common feature extraction methods include statistical features (such as mean, variance, maximum, minimum, etc.), frequency domain features (such as power spectral density, frequency peak, etc.), time domain features (such as autocorrelation function, cross correlation function, etc.), etc.; feature vector construction: the extracted features are combined into feature vectors. Different feature combination modes can be selected according to the needs, for example, all the features are arranged in time sequence, or a sliding window mode is used for extracting local features; timing correlation analysis: and performing time sequence association analysis by using the constructed feature vector. Various statistical methods and machine learning algorithms, such as correlation analysis, autoregressive models, support vector machines, etc., can be used to explore the time sequence association between different indexes; visualization of results: and visually displaying the results of the time sequence association analysis, such as drawing a time sequence association curve, a heat map or a scatter diagram, so as to more intuitively observe and understand the association relation between the flue gas indexes.
Accordingly, the mapping association unit 344 is configured to fuse the parameter time sequence association feature matrix and the flue gas index time sequence association feature vector to obtain a flue gas mapping association feature vector. The parameter time sequence correlation characteristic matrix contains characteristic information about the running state of the ship, and the smoke index time sequence correlation characteristic vector contains characteristic information about key characteristics of ship smoke index data, such as pollutant concentration, emission trend and the like. Therefore, in the technical scheme of the application, the parameter time sequence correlation characteristic matrix and the smoke index time sequence correlation characteristic vector are further fused, so that the smoke index time sequence correlation characteristic vector is mapped into a high-dimensional space of the parameter time sequence correlation characteristic matrix, and thus, the smoke mapping correlation characteristic vector fused with the ship running state characteristic information and the ship tail gas index characteristic information is obtained, and the self-adaptive control of the target power value of the desulfurization circulating pump is performed.
Accordingly, in one possible implementation, the parameter time-series correlation feature matrix and the flue gas index time-series correlation feature vector may be fused to obtain a flue gas mapping correlation feature vector, for example: creating a parameter time sequence association feature matrix: taking parameters such as desulfurization mode selection, desulfurization valve equipment, a control method and the like as columns, taking time as rows, and recording the value of the parameter corresponding to each time point; creating a smoke index time sequence associated feature vector: taking flue gas indexes (such as flue gas temperature, flue gas flow rate, flue gas components and the like) as elements, and recording the index value of each time point according to time sequence; fusing the parameter time sequence association characteristic matrix and the smoke index time sequence association characteristic vector: a matrix operation or other methods can be used for fusing the parameter time sequence association characteristic matrix and the smoke index time sequence association characteristic vector to obtain a smoke mapping association characteristic vector; meaning of flue gas mapping associated feature vector: the flue gas mapping association feature vector is a vector obtained by fusing the parameter time sequence association feature matrix and the flue gas index time sequence association feature vector, and reflects the association relation between the parameters and the flue gas index.
Accordingly, the target power value control unit 345 is configured to determine a target power value of the desulfurization circulation pump based on the flue gas mapping association feature vector. In particular, in one specific example of the present application, the flue gas mapping-related feature vector is subjected to decoding regression by a decoder to obtain a decoded value, and the decoded value is used to represent a target power value of the desulfurization circulation pump. That is, the flue gas mapping association feature vector is subjected to decoding regression through a decoder to obtain a decoding value, wherein the decoding value is used for representing the target power value of the desulfurization circulating pump. Therefore, the method can help to analyze and predict the condition of the smoke emission more accurately, thereby improving the performance and effect of the ship smoke desulfurization automatic control system and enabling the ship smoke desulfurization automatic control system to be more intelligent and accurate.
According to an embodiment of the present application, the flue gas mapping correlation feature vector is decoded and regressed by a decoder to obtain a decoded value, where the decoded value is used to represent a target power value of the desulfurization circulation pump, and the method includes: performing decoding regression on the flue gas mapping association feature vector by using the decoder in the following formula to obtain a decoding value for representing a target power value of the desulfurization circulating pump; wherein, the formula is: Wherein->Representing the smoke mapping association feature vector, +.>Is the decoded value,/->Is a weight matrix, < >>Representing matrix multiplication.
It should be noted that, in other specific examples of the present application, the target power value of the desulfurization circulation pump may also be determined based on the flue gas mapping association feature vector in other manners, for example: and (3) collecting flue gas mapping association feature vectors: first, feature vector data related to the flue gas is collected. These feature vectors may include flue gas flow, temperature, pressure, sulfur-containing gas concentration, etc. Sensors or other monitoring devices may be used to acquire such data; constructing a feature vector model: and processing and analyzing the collected feature vector data to construct a feature vector model. The model may be a mathematical model or a machine learning model for predicting a target power value of the desulfurization circulation pump; training a model: and training the feature vector model by using the existing feature vector data and the corresponding target power value. In the training process, the model learns the association rule between the feature vector and the target power value; and (3) verifying a model: and verifying the trained model by using a part of feature vector data which does not participate in training. The accuracy and reliability of the model are evaluated by comparing the difference between the target power value predicted by the model and the actual value; predicting a target power value: once the model is validated and deemed reliable, it can be used to predict a target power value for the desulfurization recycle pump. According to the current smoke characteristic vector input, the model outputs a predicted value as a target power value.
It should be noted that, in other specific examples of the present application, the target power value of the desulfurization circulation pump may be determined by other manners based on the main engine power data, the auxiliary engine power data, and the flue gas index data, for example; collecting host power data: and acquiring power data of the host, wherein the power data comprise rated power and actual running power of the host. This may be obtained by checking specifications of the host device or using a device such as a power meter; collecting auxiliary power data: and acquiring power data of auxiliary equipment, including rated power and actual operating power of the desulfurization circulating pump. This can be obtained by checking the specifications of auxiliary equipment or using a power meter or the like; collecting flue gas index data: flue gas index data, such as flue gas flow, flue gas temperature, flue gas composition, etc., associated with the desulfurization process are obtained. These data may be obtained by a flue gas monitoring device or other measurement method; analysis data: and analyzing according to the collected data, and calculating the target power value of the desulfurization circulating pump. This may be accomplished by using mathematical models or empirical based methods. For example, a power balance equation may be used to calculate the required desulfurization recycle pump power, taking into account the main machine power, auxiliary machine power, and flue gas index data; determining a target power value: and determining a target power value of the desulfurization circulating pump according to the analysis result. This will be the power level that will allow the desulfurization system to function properly and meet the desulfurization efficiency requirements.
In particular, the desulfurization treatment module 350 is configured to control the desulfurization circulation pump to operate based on the target power, to deliver the wash water to a desulfurization tower, and to perform desulfurization treatment on the ship flue gas using the wash water in the desulfurization tower. Wherein, the ship flue gas refers to exhaust gas generated when the ship burns fuel. Ships typically use fuel oil or diesel oil as fuel, and the ship is driven to operate by generating heat energy through combustion. However, a large amount of exhaust gas including carbon dioxide (CO 2), nitrogen oxides (NOx), sulfur dioxide (SO 2), particulate matter, etc. is generated during combustion.
The desulfurization circulating pump is a pump type device used in a desulfurization system. Desulfurization systems are commonly used to remove harmful gases such as sulfur dioxide (SO 2) from flue gases produced during combustion. The main function of the desulfurization circulating pump is to draw the desulfurizing agent (such as limestone slurry or ammonia water solution) from a storage tank or a reactor and convey the desulfurizing agent into desulfurization equipment through a pipeline so as to realize the desulfurization process. The desulfurization circulating pump generally has corrosion resistance and higher wear resistance so as to adapt to the special requirements of the desulfurizing agent. They may be centrifugal pumps, gear pumps, screw pumps or other types of pumps, the specific choice depending on the requirements and design of the desulfurization system.
The desulfurizing tower is one kind of equipment for eliminating sulfur dioxide (SO 2) and other harmful gas from fume. It is a core component in the desulfurization system. The desulfurizing tower generally adopts a wet desulfurization process, and the flue gas is contacted and reacted with a desulfurizing agent (such as limestone slurry or ammonia water solution) to convert SO2 into water-soluble sulfate or thiosulfate, SO that the desulfurizing effect is achieved. The desulfurizing tower is usually a large tower-shaped device, and internally comprises a packing layer or a spraying system for increasing the contact area of flue gas and desulfurizing agent and promoting the reaction. In the desulfurization process, the flue gas enters the desulfurization tower from the bottom, passes through a packing layer or a spraying system, contacts and reacts with the desulfurizing agent, and is discharged from the top.
Accordingly, in one possible implementation, the desulfurization circulation pump may be controlled to operate based on the target power by delivering wash water to a desulfurization tower, and desulfurizing ship fumes in the desulfurization tower using the wash water, for example: determining a target power: determining required target power according to the requirements of desulfurization treatment on ship flue gas; detecting the flow rate of flue gas: detecting the flow of the flue gas using a flow sensor or other suitable device and using it as input data; detecting the liquid level of washing water in the desulfurizing tower: detecting the liquid level of the washing water in the desulfurizing tower by using a liquid level sensor or other proper equipment, and taking the liquid level as input data; according to the target power and the flue gas flow, the operation of the desulfurization circulating pump is adjusted: according to the target power and the detected flue gas flow, calculating the required washing water flow by using a control algorithm, and correspondingly adjusting the operation of the desulfurization circulating pump; and controlling a desulfurization circulating pump: using an automatic control system, a manual control system, a Programmable Logic Controller (PLC) and other devices to control the start and stop of a desulfurization circulating pump and the flow regulation so as to ensure that the washing water is conveyed to a desulfurization tower as required; monitoring the liquid level of washing water in the desulfurizing tower: continuously monitoring the liquid level of the washing water in the desulfurizing tower, ensuring sufficient supply of the washing water, and replenishing or discharging according to the requirement; desulfurizing: the desulfurization treatment is realized by spraying or showering the washing water into the ship flue gas and utilizing the chemical reaction of the desulfurizing agent in the washing water and the pollutants in the flue gas.
It should be appreciated that training of the convolutional neural network model-based correlation feature extractor, the one-dimensional convolutional neural network model-based smoke index timing feature extractor, and the decoder is required prior to the inference using the neural network model described above. That is, the ship flue gas desulfurization automatic control system of the present application further comprises a training module, configured to train the correlation feature extractor based on the convolutional neural network model, the flue gas index time sequence feature extractor based on the one-dimensional convolutional neural network model, and the decoder.
Fig. 5 is a block diagram of a training module in the marine vessel flue gas desulfurization automatic control system according to an embodiment of the present application. As shown in fig. 5, the ship flue gas desulfurization automatic control system 300 according to an embodiment of the present application further includes: training module 400, comprising: a training data parameter acquisition unit 410, configured to acquire training data, where the training data includes training host power values, training auxiliary power values, and training flue gas index data values at a plurality of predetermined time points in a predetermined period, and a true value of a target power value of the desulfurization circulation pump; the training data time sequence arrangement unit 420 is configured to arrange the training host power values, the training auxiliary power values, and the training smoke index data values at the plurality of predetermined time points into a training host power time sequence input vector, a training auxiliary power time sequence input vector, and a training smoke index time sequence input vector according to a time dimension, respectively; the training parameter data time sequence association unit 430 is configured to arrange the training host power time sequence input vector, the training auxiliary power time sequence input vector and the training smoke index time sequence input vector into a training full-parameter time sequence input matrix according to sample dimensions, and then obtain a training parameter time sequence association feature matrix through the association feature extractor based on the convolutional neural network model; a training smoke index time sequence changing unit 440, configured to pass the training smoke index time sequence input vector through the smoke index time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain a training smoke index time sequence associated feature vector; the training feature fusion unit 450 is configured to fuse the training parameter time sequence correlation feature matrix and the training smoke index time sequence correlation feature vector to obtain a training smoke mapping correlation feature vector; and a decoding loss unit 460, configured to pass the training flue gas mapping association feature vector through the decoder to obtain a decoding loss function value; a model training unit 470, configured to train the correlation feature extractor based on the convolutional neural network model, the smoke index timing feature extractor based on the one-dimensional convolutional neural network model, and the decoder based on the decoding loss function value and propagating in a gradient descent direction, where in each iteration of the training, a weight matrix of the classifier is iterated through a half-space structural constraint of weight eigen support.
In particular, in the technical scheme of the application, considering that the parameter time sequence correlation feature matrix expresses local correlation features in time sequence-sample intersecting dimensions of a host power value, an auxiliary power value and a smoke index data value, and the smoke index time sequence input vector expresses time sequence local correlation features of the smoke index data value, the source data and the corresponding feature correlation dimensions are different, so that when the parameter time sequence correlation feature matrix and the smoke index time sequence correlation feature vector are fused, the smoke mapping correlation feature vector simultaneously comprises partial feature distribution of the local correlation features in the time sequence-sample intersecting dimensions and the local correlation features in the single sample time sequence dimensions. In this way, when the smoke mapping correlation feature vector is decoded and regressed by the decoder, the feature distribution of each part of the smoke mapping correlation feature vector also has different weight fitting directions relative to the corresponding part of the weight matrix of the decoder, so that the overall feature distribution of the smoke mapping correlation feature vector has the problem of poor convergence relative to the weight matrix of the decoder, thereby affecting the training speed of the decoder. Based on this, the applicant of the present application maps the associated feature vector in the flue gas, for example, written as The weight matrix at each decoder, e.g. denoted +.>In the iterative process of (1), weight matrix +.>The semi-space structuring constraint of the weight intrinsic support is specifically expressed as follows:
wherein the method comprises the steps ofIs the training smoke mapping association feature vector, < >>Is a weight matrix of the decoder, +.>Is a matrix->Eigenvector of eigenvalues of (a)>And->Representing matrix multiplication and addition, respectively,/->Representing the weight matrix of the decoder after iteration. Here, the weight eigen-supported half-space structuring constraint is applied in the weight matrix of the decoder>Eigenvalue sets of the structured matrix of (c) and the flue gas mapping association eigenvector to be decoded +.>Is used as support for the correlation integration of the weight matrix +.>Represented for use with the objectDecoded said smoke mapping association feature vector +.>Is subjected to structural support constraints of hyperplane as decision boundary, such that the smoke mapping-associated feature vector to be decoded is +_>Can be in the weight matrix +.>The represented half-space open domain effectively converges with respect to the hyperplane, thereby improving the training speed of the decoder. Therefore, the target power value self-adaptive control of the desulfurization circulating pump can be comprehensively carried out based on the running state and the tail gas emission condition of the actual ship, so that the desulfurization efficiency and efficiency of the ship tail gas are optimized, the waste of energy sources is avoided, and the purpose of protecting the environment is achieved.
As described above, the ship flue gas desulfurization automatic control system 300 according to the embodiment of the present application may be implemented in various wireless terminals, for example, a server having a ship flue gas desulfurization automatic control algorithm, or the like. In one possible implementation, the intelligent scrubber control system 300 according to an embodiment of the present application may be integrated into the wireless terminal as a software module and/or hardware module. For example, the marine vessel flue gas desulfurization automatic control system 300 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the marine vessel flue gas desulfurization automatic control system 300 can also be one of a number of hardware modules of the wireless terminal.
Alternatively, in another example, the marine vessel flue gas desulfurization automatic control system 300 and the wireless terminal may be separate devices, and the marine vessel flue gas desulfurization automatic control system 300 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
Further, an automatic control method for ship flue gas desulfurization is also provided.
Fig. 6 is a flowchart of a ship flue gas desulfurization automatic control method according to an embodiment of the present application. As shown in fig. 6, in the automatic control method for ship flue gas desulfurization, the method includes: s110, acquiring power data of a main machine, power data of an auxiliary machine and flue gas index data at an exhaust port of the desulfurizing tower detected by a flue gas detection device; s120, acquiring a desulfurization mode selected by a user in advance; s130, controlling the desulfurization valve device and the flue gas valve device to work based on the desulfurization mode; s140, determining a target power value of the desulfurization circulating pump based on the main engine power data, the auxiliary engine power data and the flue gas index data; and S150, controlling the desulfurization circulating pump to work based on the target power, conveying the washing water to a desulfurization tower, and carrying out desulfurization treatment on ship flue gas by using the washing water in the desulfurization tower.
Fig. 7 is an application scenario diagram of a ship flue gas desulfurization automatic control system according to an embodiment of the present application. As shown in fig. 7, in this application scenario, first, host power values at a plurality of predetermined time points within a predetermined period are acquired by a power sensor (e.g., P1 illustrated in fig. 6); acquiring auxiliary power values at a plurality of predetermined time points within a predetermined period by a power sensor (for example, P2 illustrated in fig. 6); and, acquiring a flue gas index data value at the flue gas outlet of the desulfurizing tower by a flue gas detecting apparatus (e.g., D illustrated in fig. 6). The data is then input to a server (e.g., S illustrated in fig. 6) deployed with an automatic control algorithm for marine flue gas desulfurization, wherein the server is capable of processing the input data with the automatic control algorithm for marine flue gas desulfurization to obtain a decoded value representing a target power value of the desulfurization circulation pump.
In summary, according to the ship flue gas desulfurization automatic control method provided by the embodiment of the application, the time sequence change analysis is carried out on the main engine power value, the auxiliary engine power value and the flue gas index data value by adopting the artificial intelligent control technology based on deep learning, and the time sequence change characteristics of the data are associated, so that the accurate control of the target power value of the desulfurization circulating pump is comprehensively carried out, the desulfurization efficiency and efficiency of ship tail gas are optimized, the waste of energy sources is avoided, and the purpose of protecting the environment is achieved.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (8)
1. An automatic control system for ship flue gas desulfurization, comprising:
the parameter data acquisition module is used for acquiring the power data of the main machine, the power data of the auxiliary machine and the flue gas index data at the exhaust port of the desulfurizing tower detected by the flue gas detection device;
the desulfurization mode preselection module is used for acquiring a desulfurization mode preselected by a user;
the valve control module is used for controlling the desulfurization valve equipment and the flue gas valve equipment to work based on the desulfurization mode;
the desulfurization circulating pump power control module is used for determining a target power value of the desulfurization circulating pump based on the main engine power data, the auxiliary engine power data and the flue gas index data;
And the desulfurization treatment module is used for controlling the desulfurization circulating pump to work based on the target power, conveying the washing water to the desulfurization tower, and carrying out desulfurization treatment on the ship flue gas by utilizing the washing water in the desulfurization tower.
2. The marine vessel fume desulfurization automatic control system of claim 1, wherein the desulfurization circulation pump power control module comprises:
the time sequence data acquisition unit is used for acquiring a host power value, an auxiliary power value and a flue gas index data value at a plurality of preset time points in a preset time period;
the parameter time sequence associated feature extraction unit is used for performing time sequence associated analysis on the main engine power values, the auxiliary engine power values and the flue gas index data values at a plurality of preset time points to obtain a parameter time sequence associated feature matrix;
the smoke index time sequence change feature extraction unit is used for performing time sequence analysis on the smoke index data values of the plurality of preset time points to obtain smoke index time sequence association feature vectors;
the mapping association unit is used for fusing the parameter time sequence association feature matrix and the flue gas index time sequence association feature vector to obtain a flue gas mapping association feature vector;
and the target power value control unit is used for determining the target power value of the desulfurization circulating pump based on the flue gas mapping association feature vector.
3. The marine vessel flue gas desulfurization automatic control system according to claim 2, wherein the parameter timing-related feature extraction unit includes:
the parameter time sequence arrangement subunit is used for respectively arranging the main machine power value, the auxiliary machine power value and the smoke index data value of the plurality of preset time points into a main machine power time sequence input vector, an auxiliary machine power time sequence input vector and a smoke index time sequence input vector according to the time dimension;
and the parameter time sequence association coding subunit is used for arranging the host power time sequence input vector, the auxiliary power time sequence input vector and the smoke index time sequence input vector into a full-parameter time sequence input matrix according to sample dimensions and then obtaining the parameter time sequence association characteristic matrix through an association characteristic extractor based on a convolutional neural network model.
4. The marine vessel fume desulfurization automatic control system according to claim 3, wherein the fume index time series change feature extraction unit is configured to: and the smoke index time sequence input vector passes through a smoke index time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain the smoke index time sequence associated feature vector.
5. The marine vessel fume desulfurization automatic control system according to claim 4, wherein the target power value control unit is configured to: and carrying out decoding regression on the flue gas mapping association feature vector through a decoder to obtain a decoding value, wherein the decoding value is used for representing the target power value of the desulfurization circulating pump.
6. The marine vessel flue gas desulfurization automatic control system of claim 5, further comprising a training module for training the convolutional neural network model-based correlation feature extractor, the one-dimensional convolutional neural network model-based flue gas index timing feature extractor, and the decoder.
7. The marine vessel fume desulfurization automatic control system of claim 6, wherein the training module comprises:
the system comprises a training data parameter acquisition unit, a desulfurization circulating pump and a desulfurization circulating pump, wherein the training data parameter acquisition unit is used for acquiring training data, and the training data comprises training host power values, training auxiliary power values and training smoke index data values at a plurality of preset time points in a preset time period, and a true value of a target power value of the desulfurization circulating pump;
the training data time sequence arrangement unit is used for arranging the training host power values, the training auxiliary power values and the training smoke index data values of the plurality of preset time points into training host power time sequence input vectors, training auxiliary power time sequence input vectors and training smoke index time sequence input vectors according to time dimensions;
The training parameter data time sequence association unit is used for arranging the training host power time sequence input vector, the training auxiliary power time sequence input vector and the training smoke index time sequence input vector into a training full-parameter time sequence input matrix according to sample dimensions and then obtaining a training parameter time sequence association feature matrix through the association feature extractor based on the convolutional neural network model;
the training smoke index time sequence change unit is used for enabling the training smoke index time sequence input vector to pass through the smoke index time sequence feature extractor based on the one-dimensional convolutional neural network model so as to obtain a training smoke index time sequence associated feature vector;
the training feature fusion unit is used for fusing the training parameter time sequence association feature matrix and the training smoke index time sequence association feature vector to obtain a training smoke mapping association feature vector; and
the decoding loss unit is used for enabling the training smoke mapping association feature vector to pass through the decoder so as to obtain a decoding loss function value;
the model training unit is used for training the correlation feature extractor based on the convolutional neural network model, the smoke index time sequence feature extractor based on the one-dimensional convolutional neural network model and the decoder based on the decoding loss function value and through gradient descent direction propagation, wherein in each round of iteration of training, the weight matrix of the classifier is subjected to half-space structuring constraint iteration of weight intrinsic support.
8. The marine vessel flue gas desulfurization automatic control system of claim 7, wherein in each iteration of the training, the weight matrix of the decoder is subjected to a weighted eigen-supported half-space structured constraint iteration with the following optimization formula;
wherein, the optimization formula is:
wherein the method comprises the steps ofIs the training smoke mapping association feature vector, < >>Is a weight matrix of the decoder, +.>Is a matrixEigenvector of eigenvalues of (a)>And->Representing matrix multiplication and addition, respectively,/->Representing the weight matrix of the decoder after iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818132.4A CN116688754A (en) | 2023-07-05 | 2023-07-05 | Ship flue gas desulfurization automatic control system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818132.4A CN116688754A (en) | 2023-07-05 | 2023-07-05 | Ship flue gas desulfurization automatic control system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116688754A true CN116688754A (en) | 2023-09-05 |
Family
ID=87823948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310818132.4A Pending CN116688754A (en) | 2023-07-05 | 2023-07-05 | Ship flue gas desulfurization automatic control system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116688754A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117180952A (en) * | 2023-11-07 | 2023-12-08 | 湖南正明环保股份有限公司 | Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof |
| CN117574244A (en) * | 2024-01-15 | 2024-02-20 | 成都秦川物联网科技股份有限公司 | Ultrasonic water meter fault prediction method, device and equipment based on Internet of things |
| CN117970987A (en) * | 2024-04-01 | 2024-05-03 | 新疆凯龙清洁能源股份有限公司 | Intelligent control system and method for wet desulfurization |
| CN117983034A (en) * | 2024-04-07 | 2024-05-07 | 浙江微盾环保科技有限公司 | Tail gas treatment and monitoring system of medical waste treatment equipment |
-
2023
- 2023-07-05 CN CN202310818132.4A patent/CN116688754A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117180952A (en) * | 2023-11-07 | 2023-12-08 | 湖南正明环保股份有限公司 | Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof |
| CN117180952B (en) * | 2023-11-07 | 2024-02-02 | 湖南正明环保股份有限公司 | Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof |
| CN117574244A (en) * | 2024-01-15 | 2024-02-20 | 成都秦川物联网科技股份有限公司 | Ultrasonic water meter fault prediction method, device and equipment based on Internet of things |
| CN117574244B (en) * | 2024-01-15 | 2024-04-02 | 成都秦川物联网科技股份有限公司 | Ultrasonic water meter fault prediction method, device and equipment based on Internet of things |
| CN117970987A (en) * | 2024-04-01 | 2024-05-03 | 新疆凯龙清洁能源股份有限公司 | Intelligent control system and method for wet desulfurization |
| CN117970987B (en) * | 2024-04-01 | 2024-06-11 | 新疆凯龙清洁能源股份有限公司 | Intelligent control system and method for wet desulfurization |
| CN117983034A (en) * | 2024-04-07 | 2024-05-07 | 浙江微盾环保科技有限公司 | Tail gas treatment and monitoring system of medical waste treatment equipment |
| CN117983034B (en) * | 2024-04-07 | 2024-06-18 | 浙江微盾环保科技有限公司 | Tail gas treatment and monitoring system of medical waste treatment equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116688754A (en) | Ship flue gas desulfurization automatic control system and method thereof | |
| CN113082954B (en) | Whole-process intelligent operation regulation and control system of wet desulphurization device | |
| CN114191953B (en) | Flue gas desulfurization and denitrification control method based on convolutional neural network and XGBoost | |
| CN109978048B (en) | Fault analysis and diagnosis method for slurry circulating pump of desulfurizing tower | |
| CN108549792B (en) | Soft measurement method for dioxin emission concentration in solid waste incineration process based on latent structure mapping algorithm | |
| CN114225662B (en) | Hysteresis model-based flue gas desulfurization and denitrification optimal control method | |
| CN112613237B (en) | CFB unit NOx emission concentration prediction method based on LSTM | |
| CN111242469B (en) | Method and system for coupling ultralow emission and high-efficiency energy-saving operation of boiler or kiln | |
| CN109224815A (en) | A kind of ammonia process of desulfurization optimal control method based on Multivariable Constrained interval prediction control | |
| CN112364562A (en) | Cooperative control method and system for flue gas environmental protection island | |
| CN111222625B (en) | Apparatus for generating learning data | |
| CN116983819A (en) | Flue gas desulfurization washing tower and method thereof | |
| CN113175678A (en) | Method and device for monitoring garbage incineration | |
| CN112216351A (en) | Desulfurization optimization method and device, electronic equipment and storage medium | |
| CN111223529A (en) | Combustion optimization device and method thereof | |
| CN109766666A (en) | Boiler smoke based on low nitrogen burning and SNCR-SCR Collaborative Control discharges NOxConcentration prediction method | |
| CN111401652A (en) | Boiler optimization method and system based on CO online detection | |
| CN114218760A (en) | Method and device for constructing prediction model of secondary pollutant discharge amount of incinerator | |
| CN111219733B (en) | Apparatus for managing combustion optimization and method thereof | |
| CN113505497A (en) | Method and system for monitoring slurry quality of wet flue gas desulfurization absorption tower | |
| CN117180937A (en) | Method and system for eliminating white smoke from desulfurized flue gas | |
| Qiu et al. | An energy‐efficiency evaluation method for high‐sulfur natural gas purification system using artificial neural networks and particle swarm optimization | |
| CN117193179A (en) | Flue gas desulfurization process monitoring and management system and method thereof | |
| CN115201408A (en) | Method for predicting concentration of sulfur dioxide at desulfurization outlet under all working conditions | |
| CN117968431B (en) | Method and device for controlling flue gas waste heat recovery of coal-fired power plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |