CN114278496A - Auxiliary control method and system of wind generating set and wind generating set - Google Patents
Auxiliary control method and system of wind generating set and wind generating set Download PDFInfo
- Publication number
- CN114278496A CN114278496A CN202111152513.0A CN202111152513A CN114278496A CN 114278496 A CN114278496 A CN 114278496A CN 202111152513 A CN202111152513 A CN 202111152513A CN 114278496 A CN114278496 A CN 114278496A
- Authority
- CN
- China
- Prior art keywords
- control system
- data
- generating set
- algorithm model
- auxiliary control
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 84
- 238000004891 communication Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 description 13
- 230000008447 perception Effects 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Sustainable Development (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Energy (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Wind Motors (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application discloses wind generating set's auxiliary control method, system and wind generating set, this method is applied to the auxiliary control system who sets up at the fan end, includes: acquiring data acquired by a sensor accessed to an auxiliary control system; calling an algorithm model to analyze data and generating a control instruction; and sending the control instruction to a main control system of the wind generating set, so that the main control system can complete the control of the wind generating set according to the control instruction. The auxiliary control system is arranged at the fan end, the algorithm model is integrated into the auxiliary control system, various data are collected and processed, the auxiliary control system is communicated with the main control system, the wind generating set is diagnosed on site, the data volume of network transmission is reduced, and local control over the wind generating set is achieved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an auxiliary control method and system of a wind generating set and the wind generating set.
Background
The wind power plant comprises a plurality of wind generating sets, each wind generating set comprises a wind wheel, a generator and the like, and the wind wheel comprises blades, a hub, reinforcing members and the like. At present, the wind power plant mainly controls the wind generating set through a plurality of independent subsystems with different functions, including an online monitoring system, a set health assessment system, a blade video monitoring system and the like, and a main control system is in network communication with a field level controller platform through acquiring data of the subsystems, so that the set is monitored and controlled.
However, the fan master control system manages a plurality of subsystems, so that the function coupling degree is high, the deployment is complex, the hardware computing power of the fan master control system is limited, and the application of machine learning and estimation control to the fan master control system is limited by resources such as network load.
Disclosure of Invention
The embodiment of the application provides an auxiliary control method and system of a wind generating set and the wind generating set, and realizes local control of the wind generating set.
In a first aspect, an embodiment of the present application provides an auxiliary control method for a wind turbine generator system, where the method is applied to an auxiliary control system disposed at a wind turbine end, and the method includes:
acquiring data acquired by a sensor accessed to the auxiliary control system;
calling an algorithm model to analyze the data and generate a control instruction;
and sending the control instruction to a main control system of the wind generating set, so that the main control system can control the wind generating set according to the control instruction.
In one possible embodiment, the invoking an algorithm model to analyze the data and generate control instructions includes:
judging characteristic conditions of the data acquired by the sensor, and determining whether to trigger an algorithm model corresponding to the data of the sensor;
and responding to triggering of an algorithm model corresponding to the data of the sensor, and calling the algorithm model to generate a fan operation control instruction.
In one possible embodiment, the invoking the algorithm model to generate the fan operation control instruction in response to triggering the algorithm model corresponding to the data of the sensor comprises:
responding to triggering of an algorithm model corresponding to the data of the sensor, and calling a service interface related to the algorithm model to obtain the relevant working condition data of the fan;
and calling the algorithm model to analyze the fan-related working condition data and/or the data collected by the sensor to generate a fan operation control instruction.
In a possible implementation mode, the sensors are classified and managed according to types, interfaces and communication protocols, and the protocols of the sensors are configured;
setting attributes of acquisition variables corresponding to the sensors, wherein the attributes comprise: and acquiring at least one of frequency, data type, limit value and applicable model.
In one possible embodiment, the method further comprises:
the sensor is connected with the master control system, the protocol version of the master control system is obtained, the acquisition variable of the sensor is obtained according to the protocol version, and the input channel and the output channel of the acquisition variable are automatically adapted.
In one possible embodiment, the communication protocol between the secondary control system and the primary control system includes a real-time communication protocol.
In a possible implementation manner, the algorithm model is trained in a cloud server, and the trained algorithm model is issued to the auxiliary control system by the cloud server.
In a second aspect, an embodiment of the present application provides an auxiliary control system, where the auxiliary control system is disposed at a fan end of a wind turbine generator system, and includes:
a processor; and
a memory, in which a computer program is stored, which, when executed by the processor, implements the method for assisting in controlling a wind turbine generator system according to any one of the embodiments of the first aspect.
In a third aspect, embodiments of the present application further provide a wind turbine generator system, where the wind turbine generator system includes the auxiliary control system described in the foregoing second aspect.
In a fourth aspect, the present application further provides a computer-readable storage medium for storing a computer program for executing the auxiliary control method of the wind turbine generator system according to any one of the foregoing embodiments of the first aspect.
In the above embodiment of the present application, the auxiliary control method of the wind turbine generator system is applied to an auxiliary control system arranged at a wind turbine end, and acquires data acquired by a sensor connected to the auxiliary control system; calling an algorithm model to analyze data and generating a control instruction; and sending the control instruction to a main control system of the wind generating set, so that the main control system can complete the control of the wind generating set according to the control instruction. The auxiliary control system is arranged at the fan end, the algorithm model is integrated into the auxiliary control system, various data are collected and processed, the auxiliary control system is communicated with the main control system, local diagnosis and control of the wind generating set are achieved, the calculation power of the main control system is not occupied, the data volume of network transmission is reduced, and local control of the wind generating set is achieved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments provided in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a flowchart of an auxiliary control method of a wind turbine generator system according to an embodiment of the present application;
FIG. 2 is a flow chart of another method for assisting in controlling a wind turbine generator system according to an embodiment of the present disclosure;
FIG. 3 is a structural distribution diagram of a wind turbine generator system according to an embodiment of the present disclosure;
FIG. 4 is a diagram illustrating a software architecture of an auxiliary controller according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an auxiliary control system in an embodiment of the present application.
Detailed Description
The wind power plant mainly controls the wind generating set through a plurality of independent systems with different functions, wherein the independent systems comprise an online monitoring system, a set health assessment system, a blade video monitoring system and the like, and a main control system of the wind generating set is communicated with a field level controller platform through a network to monitor and control the set. However, the fan master control system manages a plurality of subsystems, so that the function coupling degree is high, the deployment is complex, the hardware computing power of the fan master control system is limited, and the application of machine learning and estimation control to the fan master control system is limited by resources such as network load.
Based on this, the embodiment of the application provides an auxiliary control method for a wind generating set, which is applied to an auxiliary control system arranged at a wind turbine end to acquire data acquired by a sensor accessed to the auxiliary control system; calling an algorithm model to analyze data and generating a control instruction; and sending the control instruction to a main control system of the wind generating set, so that the main control system can complete the control of the wind generating set according to the control instruction. The auxiliary control system is arranged at the fan end, the algorithm model is integrated into the auxiliary control system, various data are collected and processed, the auxiliary control system is communicated with the main control system, local diagnosis and control of the wind generating set are achieved, the calculation power of the main control system is not occupied, the data volume of network transmission is reduced, and local control of the wind generating set is achieved.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and the described embodiments are only exemplary embodiments of the present application, and not all implementations. Those skilled in the art can combine the embodiments of the present application to obtain other embodiments without inventive work, and these embodiments are also within the scope of the present application.
Referring to fig. 1, the figure is a flowchart of an auxiliary control method of a wind turbine generator system according to an embodiment of the present application.
The method is applied to an auxiliary control system arranged at a fan end, and specifically comprises the following steps:
s101: acquiring data acquired by a sensor accessed to an auxiliary control system;
the auxiliary control system is provided with a plurality of external interfaces, supports a plurality of communication protocols, and can be accessed to a plurality of types of sensors to acquire required data. For example, various types of sensors such as microphones, cameras, radar, etc. may be accessed. The auxiliary control system may be externally connected with sensors that are expandable, including but not limited to the above-mentioned sensors.
S102: calling an algorithm model to analyze data and generating a control instruction;
and calling a related algorithm model according to the data acquired by the sensor, analyzing the data acquired by the sensor by the algorithm model, and generating a corresponding control instruction according to an analysis result.
S103: and sending the control instruction to a main control system of the wind generating set, so that the main control system can complete the control of the wind generating set according to the control instruction.
And after the auxiliary control system generates a control instruction according to the called algorithm model, the control instruction is sent to a main control system of the wind generating set, and the main control system controls the wind generating set according to the control instruction.
According to the auxiliary control method of the wind generating set, the auxiliary control system collects data of the external sensor, calls the related algorithm model to analyze the data, generates the control instruction and forwards the control instruction to the main control system, local diagnosis of the wind generating set is achieved, the data volume of network transmission is reduced, and local control of the wind generating set is achieved.
The auxiliary control system at the wind turbine end not only needs to collect data of a sensor connected into the auxiliary control system, but also needs to perform information interaction with the main control system to integrate all data, so that all working condition data and monitoring data of the wind generating set can be obtained, and local control of the wind generating set is realized.
The auxiliary control system provided by the embodiment of the application adopts a double-kernel system, namely a real-time kernel and a non-real-time kernel, wherein the real-time kernel is used for operating a real-time algorithm model, so that the auxiliary control system has real-time and stable communication capacity with a main control system, and the real-time control of the wind generating set is realized. The non-real-time kernel is used for running an algorithm model with low time-efficiency requirements, such as an analysis and diagnosis model, and does not participate in real-time control.
When a real-time communication protocol is adopted between the auxiliary control system and the main control system, the real-time and stable communication with the main control system is ensured.
According to the acquired data acquired by the sensor, different algorithm models can be called to generate corresponding control instructions according to different application scenes. Firstly, judging data acquired by a sensor through characteristic conditions, and determining whether an algorithm model corresponding to the data of the sensor is triggered; and when the characteristic conditions are met, determining to trigger the algorithm model corresponding to the data of the sensor, and responding to the triggering of the algorithm model corresponding to the data of the sensor to generate a fan operation control instruction.
Specifically, after the algorithm model is called, a service interface related to the algorithm model needs to be called to obtain the relevant working condition data of the fan; and analyzing the relevant working condition data of the fan and/or the data acquired by the sensor by the algorithm model to generate a fan operation control instruction.
Based on this, the embodiment of the present application provides another auxiliary control method for a wind turbine generator system, refer to fig. 2, which is a flowchart of the auxiliary control method for a wind turbine generator system provided in this embodiment.
The method specifically comprises the following steps:
s201: acquiring data acquired by a sensor accessed to an auxiliary control system;
s202: judging characteristic conditions of data acquired by a sensor, and determining whether to trigger an algorithm model corresponding to the data of the sensor;
s203: responding to triggering of an algorithm model corresponding to the data of the sensor, and calling a service interface related to the algorithm model to acquire fan related working condition data;
s204: calling an algorithm model to analyze the fan-related working condition data and/or the data collected by the sensor to generate a fan operation control instruction;
s205: and sending the control instruction to a main control system of the wind generating set, so that the main control system can complete the control of the wind generating set according to the control instruction.
In step S201, when the characteristic condition of the data collected by the sensor is determined and the corresponding algorithm model is called, the embodiment of the present application provides a perceptual scheduling algorithm, where the perceptual scheduling algorithm defines a set of scheduling rules related to the algorithm model, and the scheduling rules of the perceptual scheduling algorithm need to be followed when the algorithm model is called.
The perception scheduling algorithm is configured with judgment thresholds, judgment conditions, operation formulas and the like of different units, large-scale flow data can be analyzed in real time in the continuously changing process through a flow calculation processing mode, possible useful information is captured, and the result is sent to the next calculation node.
And automatically adapting an algorithm model list capable of meeting data requirements according to the list of the sensors accessed by the wind generating set by the perception scheduling algorithm, and setting the algorithm model of the sensor required by the non-access to a forbidden state.
The scheduling rules of the perceptual throttling algorithm will be described below in conjunction with one possible implementation.
One possible implementation is that the perceptual scheduling algorithm may configure the following characteristic conditions: (1) configuring a scheduling mode, comprising: conditional triggering, timing triggering, cyclic scheduling and delayed execution; (2) whether the operation type is real-time control or not can also set the priority of the operation; (3) resource management: defining a memory, a Central Processing Unit (CPU), running time, hard disk space and the like; (4) setting a triggering condition: taking a setting example of active power, the triggering condition is "# 3471# >45& #3471# < ═ 50", where 3471 is an Identity Document (ID) of an "active power control lower limit feedback" variable in the data dictionary, and the triggering condition is that the active power control lower limit feedback is greater than 45 and less than or equal to 50.
Because different algorithm models need to be called for data processing of the sensor, and in view of hardware cost and the like, the method is not suitable for model training in a single-machine side auxiliary control system, occupies too much data resources, and has higher requirements on the data processing capacity of the system, in the embodiment, different algorithm models are trained in advance in the cloud server, the trained algorithm models are issued to the auxiliary control system by the cloud server, and the algorithm models integrally deployed in the auxiliary control system are called based on a perception scheduling algorithm.
It should be noted that the rule form of invoking the algorithm model is not limited in the embodiment of the present application, and the above embodiment is merely an exemplary illustration, and there are other possible implementation manners according to actual requirements.
The working principle of the perceptual scheduling algorithm will be described in conjunction with a specific application scenario.
In the process of monitoring and controlling the blades of the wind generating set by the main control system, when the external environment temperature is lower than 5 ℃, the blades cannot normally work, and the blade protection needs to be started. Therefore, when the current temperature acquired by the temperature sensor is lower than 5 ℃, the sensing scheduling algorithm can judge according to the data acquired by the sensor, when the current temperature is judged to be lower than 5 ℃, the algorithm model called based on the sensing scheduling algorithm is an icing protection model, after the icing protection model is called, the icing protection model can call a data service function, more data of the wind generating set are acquired for analysis, and a corresponding control instruction is generated according to an analysis result. In the application scenario, the control instruction generated by the icing protection model is shutdown, the control instruction is sent to the main control system, and the main control system controls the blades of the wind generating set according to the control instruction.
Because this auxiliary control system can external multiple type sensor, in order to make things convenient for the multiple extensible sensor of access, the data of intelligent acquisition major control system, this embodiment can carry out classification management to the sensor, formulates the collection strategy.
In specific implementation, the sensors are classified and managed according to types (analog sensors/digital sensors), signals, interfaces, communication protocols and the like, and different protocols are configured. For example, the serial sensor uses an RS-485 communication interface, and a Programmable Logic Controller (PLC) transmits through a network interface, and uses an OPCUA protocol.
In a preferred implementation, attributes of measurement points corresponding to the sensor may be set, where the measurement points are also referred to as acquisition variables, and each measurement point corresponds to a standard entry, where the entry includes: an Identity (ID) of an entry, a name, an acquisition frequency, a data type, a limit value, an applicable model, and the like.
Different communication protocols are formulated, and different protocol versions correspond to different acquisition variables. After the auxiliary control system is connected with the main control system, the protocol version of the main control system is firstly obtained, the data of the port needing to be acquired is determined according to the protocol version and the acquisition rule, and the acquisition channel, namely the input/output channel, is automatically adapted after the sensor is accessed into the port. Through the classified management of the sensors, the sensors can be automatically verified after being accessed, so that the configuration of the sensors is more convenient.
One possible application scenario is that the sensor automatically accesses the IEPE channel, and may define a sampling policy of the sensor, including participation in calculating data length, sampling rate, raw data length, and feature value calculation interval time.
In order to realize control of wind generating sets of various models, an embodiment of the present application provides a structural distribution diagram of a wind generating set, and referring to fig. 3, a wind generating set 300 is divided into 3 regions, including: the nacelle region 301, the tower base region 302 and the hub region 303 constitute an organic whole.
The auxiliary control system provided by the embodiment of the application mainly comprises an auxiliary controller, a first auxiliary control substation and a second auxiliary control substation, wherein the first auxiliary control substation can acquire data accessed to a tower bottom area and send the data to the auxiliary controller, the second auxiliary control substation can acquire data accessed to a hub area and send the data to the auxiliary controller, the auxiliary controller can acquire data of a sensor accessed to the auxiliary control system, an algorithm model is called to analyze and calculate the data, a control instruction is generated according to a calculation result, and the control instruction is sent to the main control system.
The auxiliary controller can monitor working condition data such as videos and audios, the sensor is monitored on line, and the data are analyzed and processed by algorithms such as machine learning. A possible implementation mode can utilize a Graphics Processing Unit (GPU) to perform image Processing, for example, the motion track of a blade is monitored through a blade video, the blade is prevented from sweeping a tower, whether the blade is frozen or broken or not is judged through image recognition, simulation is performed based on real-time working condition data of a Unit, future working condition data is predicted, and the Unit is intervened and optimally controlled in advance.
The auxiliary controller acquires data of a sensor accessed to the auxiliary control system and then processes the acquired data. The auxiliary control method of the wind generating set will be described below with reference to a specific scenario.
In this embodiment, the auxiliary controller includes a Digital Signal Processor (DSP) and a graphics Processor GPU as an example.
For a monitoring video of a blade, a Digital Signal Processor (DSP) is used for image preprocessing, the DSP has strong computing capacity, and can complete Fast Fourier Transform (FFT) of a signal, namely a method for rapidly computing discrete Fourier Transform. And the DSP outputs the preprocessed characteristic value result frame, and the GPU performs target identification. When data calculation is carried out, each calculation task is refined and disassembled and is distributed to the heterogeneous calculation units for execution. According to the rules of the scheduling algorithm model, when the algorithm model is called to analyze and process the data of the sensor, the calculation unit can be scheduled in real time to complete the calculation task of the data, the algorithm model generates a control instruction based on the calculation result of the calculation unit, the auxiliary controller sends the control instruction to the main control system, and the main control system controls the wind generating set.
In order to enhance the processing capability of the auxiliary controller, a Field Programmable Gate Array (FPGA) chip may be integrated, and is mainly used for image recognition and video monitoring, such as monitoring whether a fan blade has a crack or is frozen through a fan video.
The FPGA chip is provided with cache logic, global or local quick modification is carried out on the FPGA chip logic through the cache logic, and dynamic reconfiguration of the system is accelerated and realized by controlling resource configuration of re-layout and re-wiring. By using the dynamic reconfiguration technology, the system can have the advantages of software implementation and hardware implementation under the condition of only increasing a small amount of hardware resources.
The software architecture of the auxiliary control system will be described with reference to the accompanying drawings.
Referring to fig. 4, a schematic diagram of a software architecture of an auxiliary controller according to an embodiment of the present application is shown.
The software architecture of the auxiliary control system is mainly divided into a base layer 401 and an application layer 402, and the base layer 401 mainly includes: the application layer 402 mainly includes an algorithm model issued to the auxiliary control system, and one possible implementation manner is that the algorithm model includes: the wind generating set control method comprises a machine learning model 4021, an estimation control model 4022, a single machine health assessment model 4023 and the like, and local control of the wind generating set is achieved by using an algorithm model to assist a main control system. It should be noted that the above-mentioned algorithm models of the modules and the application layer included in the base layer are only exemplary descriptions, and not all implementations are limited in any way, and other possible implementations are also within the scope of the present application.
And the data acquisition module realizes the acquisition access of data according to different acquisition strategies. As the auxiliary control system is externally connected with a plurality of sensors, the sensors can be classified and managed according to types, signals, interfaces and the like, and different protocols are configured. For example, the serial port sensor adopts an RS-485 communication interface, the programmable logic controller PLC transmits through a network interface, and an OPCUA protocol is adopted. Setting measuring point attributes corresponding to the sensors, wherein the measuring points are also called acquisition variables, each measuring point corresponds to a standard entry, and the entry comprises: entry ID, name, acquisition frequency, data type, limit value, applicable model and the like.
In this embodiment, a communication protocol with the master control system may also be established, and different protocol versions correspond to different acquisition variables. After the auxiliary control system is connected with the main control system, the protocol version of the main control system is firstly obtained, and according to the protocol version and the acquisition rule, after the sensor is connected, the data acquisition model can be automatically adapted to the input/output channel of the data to obtain the data of the sensor.
The perception scheduling module belongs to a core module of the auxiliary control system, and the module judges characteristic conditions according to data collected by the sensor, identifies the current event state of the wind generating set and determines whether to trigger an algorithm model corresponding to the data of the sensor. After the characteristic conditions are met, the perception scheduling module can trigger and call an algorithm model related to an application layer, the algorithm model calls the data service module to obtain more working condition data of the wind generating set, the working condition data are analyzed, the analysis result is output to the perception scheduling module, the perception scheduling module issues a control command to the main control system, and the main control system controls the operation of the wind generating set according to the control command.
The operation principle of the software architecture of the auxiliary control system will be described in conjunction with a specific application scenario.
Taking the vibration of the main bearing as an example, the data acquisition module is responsible for acquiring data of an acceleration sensor of the main bearing and pushing the acquired vibration data to the perception scheduling module in real time, the perception scheduling module judges a vibration limit value of the main bearing, if the vibration exceeds the upper limit value, the perception scheduling module calls a vibration algorithm model of an application layer, the vibration algorithm model calls the data service module to acquire more working condition data of the wind generating set for analysis and generate a control instruction according to an analysis result, the perception scheduling module forwards the control instruction to the main control system, the main control system controls the operation of the wind generating set, namely, the main bearing is controlled to reduce the vibration times.
The auxiliary control system provided by the embodiment adopts a double-kernel system, namely a real-time kernel and a non-real-time kernel, and the real-time kernel is used for operating a real-time algorithm model, so that the auxiliary control system has real-time and stable communication capability with the main control system, and local control of the wind generating set is realized. The non-real-time kernel is used for running an algorithm model with low time-efficiency requirements, such as an analysis and diagnosis model, and does not participate in real-time control.
In an actual application scenario, from the perspective of market requirements and cost, if the real-time control requirements on the wind generating set are low, the auxiliary control system and the main control system can adopt a non-real-time communication protocol, and the auxiliary control system utilizes the switch to perform information interaction with the main control system, so that the control on the wind generating set is realized.
In this embodiment, from the perspective of market demand and cost, the auxiliary control system and the main control system use a non-real-time communication protocol, and do not need the main control system to perform network communication with the field level controller platform, and the auxiliary control system and the main control system perform communication, so as to implement local control over the wind turbine generator system, and also reduce communication cost.
In addition, the embodiment of the present application further provides an auxiliary control system, which is disposed at the wind turbine end, and referring to fig. 5, the auxiliary control system 500 includes a processor 501 and a memory 502:
the memory 502 stores a computer program which, when executed by the processor 501, implements the method of assisting control of a wind park as described in the above-mentioned method embodiments.
Based on the auxiliary control system provided by the above embodiment, the embodiment of the application further provides a wind generating set, and the wind generating set comprises the auxiliary control system provided by the above embodiment.
In addition, the embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium is used for storing a computer program, and the computer program is used for executing the auxiliary control method of the wind turbine generator system according to the above-mentioned method embodiment.
The embodiments in the present specification are described in a progressive manner, and similar parts between the embodiments may be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, for the device embodiment, since it is substantially similar to the method embodiment, it is described relatively simply, and the relevant portions can be referred to the partial description of the method embodiment. The above-described embodiments of the apparatus are merely illustrative, where units or modules described as separate components may or may not be physically separate, and components displayed as the units or modules may or may not be physical modules, that is, may be located in one place, or may also be distributed on multiple network units, and some or all of the units or modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only exemplary of the present application and is not intended to limit the present application in any way. Equivalent changes or modifications of the above embodiments are within the scope of the present application.
Claims (10)
1. An auxiliary control method for a wind generating set, characterized in that the method is applied to an auxiliary control system arranged at a wind turbine end, and the method comprises the following steps:
acquiring data acquired by a sensor accessed to the auxiliary control system;
calling an algorithm model to analyze the data and generate a control instruction;
and sending the control instruction to a main control system of the wind generating set, so that the main control system can control the wind generating set according to the control instruction.
2. The method of claim 1, wherein the calling algorithm model analyzes the data and generating control instructions comprises:
judging characteristic conditions of the data acquired by the sensor, and determining whether to trigger an algorithm model corresponding to the data of the sensor;
and responding to triggering of an algorithm model corresponding to the data of the sensor, and calling the algorithm model to generate a fan operation control instruction.
3. The method of claim 2, wherein said invoking the algorithmic model to generate a wind turbine operational control instruction in response to triggering the algorithmic model corresponding to the sensor data comprises:
responding to triggering of an algorithm model corresponding to the data of the sensor, and calling a service interface related to the algorithm model to obtain the relevant working condition data of the fan;
and calling the algorithm model to analyze the fan-related working condition data and/or the data collected by the sensor to generate a fan operation control instruction.
4. The method according to any one of claims 1 to 3, wherein the sensors are classified and managed according to types, interfaces, communication protocols, and the protocols of the sensors are configured;
setting attributes of acquisition variables corresponding to the sensors, wherein the attributes comprise: and acquiring at least one of frequency, data type, limit value and applicable model.
5. The method of claim 4, further comprising:
and acquiring a protocol version of the master control system, acquiring an acquisition variable of the sensor according to the protocol version, and automatically adapting an input channel and an output channel of the acquisition variable.
6. The method of claim 1, wherein the communication protocol between the secondary control system and the primary control system comprises a real-time communication protocol.
7. The method of claim 1, wherein the algorithm model is trained in a cloud server, and the trained algorithm model is sent to the auxiliary control system by the cloud server.
8. An auxiliary control system, wherein the auxiliary control system is disposed at a fan end, comprising:
a processor; and
a memory storing a computer program which, when executed by the processor, implements the method of auxiliary control of a wind park according to any of claims 1 to 7.
9. A wind park according to claim 8, wherein the wind park comprises an auxiliary control system.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium is adapted to store a computer program for performing the method of auxiliary control of a wind park according to any of claims 1 to 7.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152513.0A CN114278496A (en) | 2021-09-29 | 2021-09-29 | Auxiliary control method and system of wind generating set and wind generating set |
| PCT/CN2022/101438 WO2023050930A1 (en) | 2021-09-29 | 2022-06-27 | Auxiliary control method and system for wind turbine generator set, and wind turbine generator set |
| BR112024000658A BR112024000658A2 (en) | 2021-09-29 | 2022-06-27 | AUXILIARY CONTROL METHOD AND SYSTEM FOR WIND TURBINE GENERATOR SET AND WIND TURBINE GENERATOR SET |
| AU2022356758A AU2022356758A1 (en) | 2021-09-29 | 2022-06-27 | Auxiliary control method and system for wind turbine generator set, and wind turbine generator set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152513.0A CN114278496A (en) | 2021-09-29 | 2021-09-29 | Auxiliary control method and system of wind generating set and wind generating set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114278496A true CN114278496A (en) | 2022-04-05 |
Family
ID=80868642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111152513.0A Pending CN114278496A (en) | 2021-09-29 | 2021-09-29 | Auxiliary control method and system of wind generating set and wind generating set |
Country Status (4)
| Country | Link |
|---|---|
| CN (1) | CN114278496A (en) |
| AU (1) | AU2022356758A1 (en) |
| BR (1) | BR112024000658A2 (en) |
| WO (1) | WO2023050930A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023050930A1 (en) * | 2021-09-29 | 2023-04-06 | 新疆金风科技股份有限公司 | Auxiliary control method and system for wind turbine generator set, and wind turbine generator set |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090187282A1 (en) * | 2008-01-17 | 2009-07-23 | Detlef Menke | Wind turbine arranged for independent operation of its components and related method and computer program |
| CN102984758A (en) * | 2012-12-25 | 2013-03-20 | 西安大唐电信有限公司 | Sensor data transmission method based on Internet of Things |
| WO2020099135A1 (en) * | 2018-11-12 | 2020-05-22 | Siemens Aktiengesellschaft | Method and assistance system for generating training data for a learning-based configuration of a technical system |
| CN111520282A (en) * | 2020-05-21 | 2020-08-11 | 明阳智慧能源集团股份公司 | Wind turbine measurement and control system and measurement and control method based on edge calculation and deep learning |
| US20210010458A1 (en) * | 2018-03-20 | 2021-01-14 | Hanjin Ind. Co., Ltd. | Multi-class controller for wind power generator and wind power generation system using same |
| CN112483334A (en) * | 2020-12-11 | 2021-03-12 | 重庆科凯前卫风电设备有限责任公司 | Intelligent control method of wind turbine generator based on edge calculation |
| CN112594142A (en) * | 2020-11-23 | 2021-04-02 | 东方电气集团科学技术研究院有限公司 | Terminal cloud collaborative wind power operation and maintenance diagnosis system based on 5G |
| CN113357083A (en) * | 2021-08-09 | 2021-09-07 | 东方电气风电有限公司 | Intelligent control system and method for wind generating set |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10132295B2 (en) * | 2015-05-15 | 2018-11-20 | General Electric Company | Digital system and method for managing a wind farm having plurality of wind turbines coupled to power grid |
| EP3638900B1 (en) * | 2017-06-14 | 2023-06-07 | KK Wind Solutions A/S | Independent monitoring system for a wind turbine |
| CN109973326A (en) * | 2017-12-27 | 2019-07-05 | 北京金风科创风电设备有限公司 | Data acquisition system of wind generating set |
| US11015576B2 (en) * | 2018-08-13 | 2021-05-25 | Inventus Holdings, Llc | Wind turbine control system including an artificial intelligence ensemble engine |
| US10954919B1 (en) * | 2019-10-02 | 2021-03-23 | General Electric Company | Machine-learning model-based analytic for monitoring wind farm power performance |
| CN114278496A (en) * | 2021-09-29 | 2022-04-05 | 新疆金风科技股份有限公司 | Auxiliary control method and system of wind generating set and wind generating set |
-
2021
- 2021-09-29 CN CN202111152513.0A patent/CN114278496A/en active Pending
-
2022
- 2022-06-27 WO PCT/CN2022/101438 patent/WO2023050930A1/en active Application Filing
- 2022-06-27 BR BR112024000658A patent/BR112024000658A2/en unknown
- 2022-06-27 AU AU2022356758A patent/AU2022356758A1/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090187282A1 (en) * | 2008-01-17 | 2009-07-23 | Detlef Menke | Wind turbine arranged for independent operation of its components and related method and computer program |
| CN102984758A (en) * | 2012-12-25 | 2013-03-20 | 西安大唐电信有限公司 | Sensor data transmission method based on Internet of Things |
| US20210010458A1 (en) * | 2018-03-20 | 2021-01-14 | Hanjin Ind. Co., Ltd. | Multi-class controller for wind power generator and wind power generation system using same |
| WO2020099135A1 (en) * | 2018-11-12 | 2020-05-22 | Siemens Aktiengesellschaft | Method and assistance system for generating training data for a learning-based configuration of a technical system |
| CN111520282A (en) * | 2020-05-21 | 2020-08-11 | 明阳智慧能源集团股份公司 | Wind turbine measurement and control system and measurement and control method based on edge calculation and deep learning |
| CN112594142A (en) * | 2020-11-23 | 2021-04-02 | 东方电气集团科学技术研究院有限公司 | Terminal cloud collaborative wind power operation and maintenance diagnosis system based on 5G |
| CN112483334A (en) * | 2020-12-11 | 2021-03-12 | 重庆科凯前卫风电设备有限责任公司 | Intelligent control method of wind turbine generator based on edge calculation |
| CN113357083A (en) * | 2021-08-09 | 2021-09-07 | 东方电气风电有限公司 | Intelligent control system and method for wind generating set |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023050930A1 (en) * | 2021-09-29 | 2023-04-06 | 新疆金风科技股份有限公司 | Auxiliary control method and system for wind turbine generator set, and wind turbine generator set |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023050930A1 (en) | 2023-04-06 |
| AU2022356758A1 (en) | 2024-01-18 |
| BR112024000658A2 (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3549312B1 (en) | A master node, a local node and respective methods performed thereby for predicting one or more metrics associated with a communication network | |
| US11268495B2 (en) | Wind farm noise prediction method, apparatus and system | |
| CN111108737B (en) | Providing software applications on edge devices in an internet of things environment | |
| CN108597057A (en) | A kind of unmanned plane failure predication diagnostic system and method based on noise deep learning | |
| CN112003763A (en) | Network link monitoring method, monitoring device, monitoring equipment and storage medium | |
| CN117931424A (en) | Network resource scheduling optimization system of cloud environment | |
| CN114278496A (en) | Auxiliary control method and system of wind generating set and wind generating set | |
| CN116980284B (en) | Optical cable fiber distribution box operation and maintenance information transmission method and system based on Internet of things | |
| CN111324460B (en) | Power monitoring control system and method based on cloud computing platform | |
| CN117873690B (en) | Method for managing power consumption of arithmetic unit chip, computing subsystem and intelligent computing platform | |
| CN113765216A (en) | Monitoring method, device and system of power distribution equipment and storage medium | |
| CN113357083A (en) | Intelligent control system and method for wind generating set | |
| CN116248674A (en) | Data transmission method, device and system | |
| CN117507935A (en) | Control method, system, electronic equipment and medium for battery management | |
| CN114598719A (en) | Smart city Internet of things event management method, device and readable medium | |
| CN113570476A (en) | Container service monitoring method of power grid monitoring system based on custom alarm rule | |
| CN108107791A (en) | Wind power plant control device, method and system | |
| CN112131023A (en) | Message processing system, method, device and storage medium for application container engine | |
| CN116089086A (en) | Rail transit energy saving method, device, equipment and storage medium | |
| CN109302723B (en) | Multi-node real-time radio monitoring control method based on Internet | |
| CN115129565A (en) | Log data processing method, device, system, equipment and medium | |
| CN116361703A (en) | Energy-saving control method and device for data center, electronic equipment and readable medium | |
| Zhang et al. | Intelligent fault diagnosis system based on vibration signal edge computing | |
| CN112526945B (en) | Full-process monitoring and early warning system with feedback and closed-loop control functions | |
| CN114244681A (en) | Equipment connection fault early warning method and device, storage medium and electronic equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 830026 No. 107, Shanghai Road, Urumqi economic and Technological Development Zone, the Xinjiang Uygur Autonomous Region Applicant after: Jinfeng Technology Co.,Ltd. Address before: 830026 No. 107, Shanghai Road, Urumqi economic and Technological Development Zone, the Xinjiang Uygur Autonomous Region Applicant before: XINJIANG GOLDWIND SCIENCE & TECHNOLOGY Co.,Ltd. |