CN118096085B - Flour production line equipment operation and maintenance management method based on Internet of things - Google Patents
Flour production line equipment operation and maintenance management method based on Internet of things Download PDFInfo
- Publication number
- CN118096085B CN118096085B CN202410494661.8A CN202410494661A CN118096085B CN 118096085 B CN118096085 B CN 118096085B CN 202410494661 A CN202410494661 A CN 202410494661A CN 118096085 B CN118096085 B CN 118096085B
- Authority
- CN
- China
- Prior art keywords
- data
- production
- energy
- optimization
- energy consumption
- 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.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 168
- 238000007726 management method Methods 0.000 title claims abstract description 29
- 235000013312 flour Nutrition 0.000 title claims abstract description 26
- 238000012423 maintenance Methods 0.000 title claims abstract description 11
- 238000005457 optimization Methods 0.000 claims abstract description 121
- 238000000034 method Methods 0.000 claims abstract description 89
- 239000002245 particle Substances 0.000 claims abstract description 81
- 230000008569 process Effects 0.000 claims abstract description 70
- 238000005265 energy consumption Methods 0.000 claims abstract description 67
- 230000002068 genetic effect Effects 0.000 claims abstract description 63
- 230000013016 learning Effects 0.000 claims abstract description 31
- 230000002787 reinforcement Effects 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 230000002452 interceptive effect Effects 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 42
- 230000035772 mutation Effects 0.000 claims description 14
- 230000009471 action Effects 0.000 claims description 13
- 230000006872 improvement Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 239000002994 raw material Substances 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000002921 genetic algorithm search Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000002028 premature Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 230000008303 genetic mechanism Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 230000007774 longterm Effects 0.000 claims description 4
- 230000011273 social behavior Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000002688 persistence Effects 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000004806 packaging method and process Methods 0.000 description 4
- 241000209140 Triticum Species 0.000 description 3
- 235000021307 Triticum Nutrition 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 108010068370 Glutens Proteins 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000010353 genetic engineering Methods 0.000 description 1
- 235000021312 gluten Nutrition 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 230000009326 social learning Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/092—Reinforcement learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
- G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of equipment operation and maintenance management, in particular to a flour production line equipment operation and maintenance management method based on the Internet of things, which comprises the following steps: the energy consumption data of each equipment and process stage are collected in real time through energy metering equipment arranged on a flour production line; the collected energy consumption data is transmitted to a central energy management unit, and the energy consumption data and the production data are integrated to form a comprehensive data set; introducing an integrated iterative multi-objective optimization algorithm, comprising a genetic algorithm and particle swarm optimization, taking a comprehensive data set as input and analyzing to balance production efficiency and energy consumption, and finding out an optimal production configuration and an energy use strategy; and introducing reinforcement learning technology, automatically identifying and implementing optimal production configuration and energy use strategies through interactive learning with a production environment. The invention can continuously find the optimal strategy of energy use and reduce invalid and excessive energy consumption.
Description
Technical Field
The invention relates to the technical field of equipment operation and maintenance management, in particular to a flour production line equipment operation and maintenance management method based on the Internet of things.
Background
In the flour production industry, management of energy consumption and production efficiency is a key economic and environmental factor, and a traditional flour production line relies on experience and regular maintenance plans to manage energy use and maintain production efficiency, so that the method is low in efficiency, and cannot respond to changes in the production process in real time, so that energy waste and production interruption are caused.
With the development of internet of things, real-time data acquisition and analysis become possible, providing new opportunities for improving energy management and efficiency of a production line, however, how to effectively integrate and utilize these large amounts of data to optimize production configuration and energy use strategies remains a challenge. Traditional data processing methods often fail to handle complex production dynamics and variable energy demands, and lack fast response capability to incidents in the production process.
Furthermore, while there are some optimization methods in the prior art, such as a single mathematical programming or machine learning model, these methods are generally focused on a particular aspect of the production process, lacking comprehensive consideration of the overall performance and energy consumption of the production line. Therefore, there is a need for a method that can fully analyze and optimize energy and production efficiency in a flour production line, which should dynamically adapt to changes in the production environment, and achieve real-time, automated optimization decisions.
Disclosure of Invention
Based on the above purpose, the invention provides an operation and maintenance management method for flour production line equipment based on the Internet of things.
A flour production line equipment operation and maintenance management method based on the Internet of things comprises the following steps:
S1, energy consumption data acquisition: the energy consumption data of each equipment and process stage are collected in real time through energy metering equipment arranged on a flour production line;
s2, data transmission and integration: the collected energy consumption data is transmitted to a central energy management unit, and the energy consumption data and the production data are integrated to form a comprehensive data set;
S3, introducing an integrated iterative multi-objective optimization algorithm, including genetic algorithm and particle swarm optimization, taking a comprehensive data set as input and analyzing to balance production efficiency and energy consumption, and finding out an optimal production configuration and an energy use strategy;
s4, introducing reinforcement learning technology, automatically identifying and implementing optimal production configuration and energy use strategy through interactive learning with the production environment, and realizing automatic adjustment of the production process to minimize energy cost.
Further, the S1 specifically includes:
s11: the method comprises the steps of installing multiple types of energy metering equipment including an electric energy meter, a gas flowmeter and a water flowmeter in key equipment and process stages of a flour production line, and monitoring and recording the consumption of electric power, gas and water in each equipment and process stage in real time;
S12: the configuration data acquisition unit is used for inputting the data of each metering device, carrying out standardization processing on the data to form a data stream in a unified format, and transmitting the standardized data stream to the central energy management unit in real time by utilizing a wireless network for subsequent data analysis and optimization processing.
Further, the production data in S2 includes raw material consumption, product yield, equipment operation state and process parameters, and S2 specifically includes:
S21: preprocessing the collected data, including data cleaning, data standardization and data synchronization;
S22: after data preprocessing, data fusion operation is carried out, energy consumption data and production data are integrated into a unified data model, and the energy consumption data are associated with corresponding production activities through data matching and association;
S23: and constructing a comprehensive data set, organizing the fused data into the comprehensive data set by using a database management system or a data analysis platform, wherein the data set reflects the relation between the production activity and the energy consumption, and each data record contains a time stamp, an energy consumption index and production parameter information in the comprehensive data set.
Further, the integrated iterative multi-objective optimization algorithm in S3 specifically includes:
S31: in the initial stage, a genetic algorithm is used for global searching, the genetic algorithm searches a solution space by simulating natural selection and genetic mechanisms (such as selection, crossing and variation), an optimized solution set is searched, the genetic algorithm widely searches the solution space, a main area of a global optimal solution is identified, and the problem that the global optimal solution falls into local optimal in early stage is avoided;
S32: evaluating and selecting, after genetic algorithm optimization after multiple iterations, evaluating the performance of the currently found optimal solution or solution set, and determining the quality of the genetic algorithm search result, if so, approaching global optimal or if there is an obvious improvement space;
S33: in the refinement and optimization stage, an optimal solution or a solution set found by a genetic algorithm is used for performing refinement and search by starting a particle swarm optimization algorithm, the particle swarm optimization is performed by simulating social behaviors of a bird swarm so as to quickly converge on the optimal solution in a solution space, and local search and optimization are performed in a main area determined by the genetic algorithm so as to refine and adjust and improve the accuracy of the solution;
S34: iterative loop, combining the results of genetic algorithm and particle swarm optimization, and continuously performing iterative optimization, wherein in each iteration, parameters (such as crossing rate, variation rate, learning factor and the like) of the genetic algorithm and the particle swarm optimization are adjusted according to the results of the last iteration so as to adapt to the dynamic change of the optimization process;
S35: through an iterative mode, genetic algorithm and particle swarm optimization are continuously recycled until a stopping criterion is met, wherein the stopping criterion comprises the preset iterative times, the improvement amount of the solution is lower than a threshold value or a preset performance target is achieved;
S36: final optimization results: after multiple iterations, the optimization process of genetic algorithm and particle swarm optimization is integrated, and finally an optimized energy management strategy is determined, wherein the strategy is subjected to local search and refinement on the basis of a global optimal solution so as to ensure the optimal efficiency of energy use and the optimal configuration of the production process.
Further, the global searching using a genetic algorithm specifically includes:
selecting: selecting high-quality individuals (solutions) from the current population, and as parents of the next generation, the selection process evaluates the performance of each individual based on a fitness function, namely, a function of energy efficiency or cost efficiency of the production line, wherein the fitness function is expressed as: fitness = × + ×Wherein, the method comprises the steps of, wherein,AndIs a weight factor for adjusting the degree of influence of yield and plant operating efficiency on the overall fitness;
crossing: after a parent individual is selected, generating offspring through crossover operation, and generating a new individual through single-point crossover combining with the characteristics of the parent individual;
Variation: in order to maintain the diversity of the population and avoid premature convergence to a locally optimal solution, mutation operation is carried out on part of individuals, and the characteristics of the individuals are changed randomly.
Further, the evaluating and selecting specifically includes:
In each generation of genetic algorithm, evaluating individuals in the population, selecting high-performance individuals to enter the next generation, quantifying the capacity of each individual to solve the problem by relying on a fitness function in the evaluating and selecting process, evaluating each individual based on the well-defined fitness function, wherein the individuals with high fitness indicate that the corresponding production configuration and energy use strategy are better;
The selection process comprises the following steps: selection is made according to fitness, and roulette selection is employed to provide highly fitness individuals with a high probability of being selected as a parent of the next generation.
Further, in the refinement and optimization stage, the particle swarm optimization algorithm is used for performing local search in a solution area determined by the genetic algorithm, and the processing procedure of the particle swarm optimization algorithm comprises the following steps:
each particle in the population represents a potential solution, namely a corresponding production configuration and energy use strategy;
each particle adjusts its search direction and speed based on individual experience (individual best position) and integrated experience (global best position), and the particle update is calculated as follows:
；
；
Wherein, Is a particleAt the time ofIs used for the speed of the (c) in the (c),Is a particleAt the time ofIs provided in the position of (a),Is the individual best position for particle i,Is the global optimum position for the device,Is an inertial weight, controls the persistence of the particle velocity,AndIs an acceleration constant, controls the speed of movement of particles to individual and global optima,AndIs a random number within interval 0.1. In this way, the PSO algorithm can effectively perform refinement search in the globally optimal vicinity to find a better solution.
Further, the iterative loop is a process of alternately executing genetic algorithm and particle swarm optimization, and in each iteration, parameters of the genetic algorithm and the particle swarm optimization are adjusted according to the results of previous iterations, wherein the parameters comprise a crossing rate, a mutation rate (genetic algorithm parameters), an acceleration constant and an inertia weight (particle swarm optimization parameters);
The final optimization result comprehensively considers the genetic algorithm and the optimal solution obtained in the particle swarm optimization process to form a final optimization strategy, and the final strategy balances the production efficiency and the energy consumption, so that the optimization of energy use is realized while the production requirement is met.
Further, the step S4 introduces reinforcement learning technology, and continuously optimizes the decision by observing the feedback of the production process, which specifically includes:
Defining a reinforcement learning environment: the method comprises the steps of representing the current state of a production line by defining a state, wherein the current state comprises energy consumption data, production speed, raw material usage amount and product quality index; defining executable operations through the action set, including adjusting device parameters, altering energy input, and modifying production cadence; by defining rewards, the reward signal gives positive rewards when reducing energy consumption and improving production efficiency based on goals of production efficiency and energy consumption, and negative rewards otherwise;
Selecting a strategy-based algorithm PPO to process continuous states and action spaces, and finding an optimal strategy in a complex production environment;
The optimal production configuration and the energy use strategy obtained by analyzing the integrated iterative multi-objective optimization algorithm are used as the training basis of reinforcement learning, and during the training process, by trying different actions and observing results (such as energy consumption and production quantity), how to adjust the production configuration to optimize the energy use is learned, and by continuously trial and error learning, the strategy is updated to maximize long-term rewards.
Further, the PPO algorithm specifically includes:
policy function: policy function Is indicated in a given stateDown selection actionWhereinParameters representing policy networks, in the present invention, statesIs the current production line state including energy consumption, production rate, etc., and actsAdjusting equipment setting or changing energy use strategies;
Dominance function: dominance function Representing execution of an actionIn stateTo a better degree than average, in a production environment, the dominance function can help identify which actions result in better energy usage efficiency or production performance than current strategies;
objective function: the goal of the PPO algorithm is to maximize a tailored objective function that is based on probability ratios WhereinIs a parameter of the old policy, and the objective function is defined as:
Wherein Is a small constant, takes a value of 0.2, is used to limit the stride of policy updates,In the form of a probability proportion,For clipping functions forThe value of (2) is limited toWithin the range.
The invention has the beneficial effects that:
According to the invention, by introducing an integrated iterative multi-objective optimization algorithm and combining a genetic algorithm and particle swarm optimization, the energy consumption and the production efficiency of the flour production line can be comprehensively analyzed and optimized, the production efficiency and the energy use can be effectively balanced, so that the remarkable reduction of the energy cost is realized, meanwhile, the production capacity is maintained or improved, the optimal strategy of the energy use can be continuously found through refined search and iterative optimization, the invalid and excessive energy consumption is reduced, and for enterprises, the cost saving and the economic benefit improvement are meant.
According to the invention, the reinforcement learning technology is introduced, so that the method can automatically identify and implement the optimal production configuration and energy use strategy through the real-time interactive learning with the production environment, the dynamic adaptation mechanism can enable the production process to be adjusted according to real-time data and environmental changes, the optimization strategy can be continuously updated and improved, the production process is ensured to always run in an optimal state, the flexibility and response speed of the production line are improved, and the decision making capability and the optimization efficiency of the system can be continuously improved through long-term learning accumulation.
According to the invention, a comprehensive data analysis and decision frame is constructed by integrating and analyzing the real-time energy consumption data and the production data of the production line, the data driving method enables the decision process to be more scientific and accurate, powerful support can be provided for production management and energy optimization based on comprehensive data analysis, each decision can be ensured to be made based on the latest and most comprehensive information through continuous data fusion, analysis and optimization, and the intelligent level of production management and the accuracy of the decision are greatly improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method according to an embodiment of the invention;
Fig. 2 is a schematic diagram of an integrated iterative multi-objective optimization algorithm according to an embodiment of the present invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in fig. 1-2, the operation and maintenance management method of the flour production line equipment based on the internet of things comprises the following steps:
S1, energy consumption data acquisition: the energy consumption data of each equipment and process stage are collected in real time through energy metering equipment arranged on a flour production line;
s2, data transmission and integration: the collected energy consumption data is transmitted to a central energy management unit, and the energy consumption data and the production data are integrated to form a comprehensive data set;
S3, introducing an integrated iterative multi-objective optimization algorithm, including genetic algorithm and particle swarm optimization, taking a comprehensive data set as input and analyzing to balance production efficiency and energy consumption, and finding out an optimal production configuration and an energy use strategy;
s4, introducing reinforcement learning technology, automatically identifying and implementing optimal production configuration and energy use strategy through interactive learning with the production environment, and realizing automatic adjustment of the production process to minimize energy cost.
S1 specifically comprises:
s11: the method comprises the steps of installing multiple types of energy metering equipment including an electric energy meter, a gas flowmeter and a water flowmeter in key equipment and process stages of a flour production line, and monitoring and recording the consumption of electric power, gas and water in each equipment and process stage in real time;
S12: the configuration data acquisition unit is used for inputting the data of each metering device, carrying out standardization processing on the data to form a data stream in a unified format, and transmitting the standardized data stream to the central energy management unit in real time by utilizing a wireless network for subsequent data analysis and optimization processing.
The key equipment and the process stages comprise:
raw material receiving and storing:
key equipment: raw material bin and conveying system;
the process comprises the following steps: receiving, cleaning, grading and storing wheat or other raw materials.
Cleaning and pretreatment:
key equipment: a cleaning machine and a stone removing machine;
The process comprises the following steps: the wheat is cleaned, impurities and stone grains are removed, and metal foreign matters are removed.
Grinding:
key equipment: a pulverizer and a screen;
the process comprises the following steps: the cleaned wheat is ground into flour, including multiple grinding and sieving processes, to obtain flour of varying accuracy.
Screening and classifying:
key equipment: plane screen, cylinder screen and pulverizer;
the process comprises the following steps: the ground flour is sieved and classified, and flour with different sizes and qualities is separated.
Powder quality adjustment:
Key equipment: a conditioner and a stirrer;
the process comprises the following steps: the quality of flour, such as humidity, particle size and gluten content, is adjusted according to different product requirements.
And (3) processing and packaging a finished product:
key equipment: a packaging machine and a weighing system;
the process comprises the following steps: quantitatively packaging, packaging and marking the processed flour, and preparing for sale or storage.
The production data in S2 include raw material consumption, product yield, equipment operation status and process parameters, and S2 specifically includes:
S21: preprocessing the collected data, including data cleaning, data standardization and data synchronization;
S22: after data preprocessing, data fusion operation is carried out, energy consumption data and production data are integrated into a unified data model, and the energy consumption data are associated with corresponding production activities through data matching and association;
S23: and constructing a comprehensive data set, organizing the fused data into the comprehensive data set by using a database management system or a data analysis platform, wherein the data set reflects the relation between the production activity and the energy consumption, and each data record contains a time stamp, an energy consumption index and production parameter information in the comprehensive data set.
The integrated iterative multi-objective optimization algorithm in S3 specifically comprises:
S31: in the initial stage, a genetic algorithm is used for global searching, the genetic algorithm searches a solution space by simulating natural selection and genetic mechanisms (such as selection, crossing and variation), an optimized solution set is searched, the genetic algorithm widely searches the solution space, a main area of a global optimal solution is identified, and the problem that the global optimal solution falls into local optimal in early stage is avoided;
S32: evaluating and selecting, after genetic algorithm optimization after multiple iterations, evaluating the performance of the currently found optimal solution or solution set, and determining the quality of the genetic algorithm search result, if so, approaching global optimal or if there is an obvious improvement space;
S33: in the refinement and optimization stage, an optimal solution or a solution set found by a genetic algorithm is used for performing refinement and search by starting a particle swarm optimization algorithm, the particle swarm optimization is performed by simulating social behaviors of a bird swarm so as to quickly converge on the optimal solution in a solution space, and local search and optimization are performed in a main area determined by the genetic algorithm so as to refine and adjust and improve the accuracy of the solution;
S34: iterative loop, combining the results of genetic algorithm and particle swarm optimization, and continuously performing iterative optimization, wherein in each iteration, parameters (such as crossing rate, variation rate, learning factor and the like) of the genetic algorithm and the particle swarm optimization are adjusted according to the results of the last iteration so as to adapt to the dynamic change of the optimization process;
S35: through an iterative mode, genetic algorithm and particle swarm optimization are continuously recycled until a stopping criterion is met, wherein the stopping criterion comprises the preset iterative times, the improvement amount of the solution is lower than a threshold value or a preset performance target is achieved;
S36: final optimization results: after multiple iterations, the optimization process of genetic algorithm and particle swarm optimization is integrated, and finally an optimized energy management strategy is determined, wherein the strategy is subjected to local search and refinement on the basis of a global optimal solution so as to ensure the optimal efficiency of energy use and the optimal configuration of the production process.
To clearly describe the detailed process of the integrated iterative multi-objective optimization algorithm, the process of the integrated iterative multi-objective optimization algorithm is decomposed and input, output and how they are used in combination with energy consumption data and production data are specified:
1. The initial stage: global search (using genetic algorithm):
input data: the integrated data set comprises energy consumption data and production data.
The treatment process comprises the following steps:
Genetic algorithms explore the solution space by modeling natural selection and genetic mechanisms (selection, crossover, mutation).
The main area for identifying the globally optimal solution is widely searched, so that the premature sinking into the locally optimal solution is avoided.
Outputting data: a set of potential optimization solutions, expressed as a combination of production configuration and energy usage strategies.
2. Evaluation and selection:
input data: the genetic algorithm produces a potentially optimal solution.
The treatment process comprises the following steps:
The performance of each solution is evaluated based on actual production and energy consumption metrics.
The quality of the solution is determined, and whether the solution is close to the global optimum or whether there is significant room for improvement is determined.
Outputting data: the filtered optimized solution is the most likely solution set near the global optimum.
3. And (3) a refinement and optimization stage: local search (using particle swarm optimization):
input data: and (5) optimizing the solution set after screening.
The treatment process comprises the following steps:
The particle swarm optimization algorithm performs a local search within a main region determined by the genetic algorithm.
By simulating the social behavior of the bird group, the particle swarm optimization is quickly converged to the optimal solution.
The adjustment solution is refined to improve its accuracy and performance.
Outputting data: finer and optimized production configurations and energy usage strategies.
4. And (3) iteration loop:
Input data: and outputting particle swarm optimization.
The treatment process comprises the following steps:
and (5) continuously iterating, and optimizing by combining a genetic algorithm and a particle swarm optimization result.
In each iteration, the algorithm parameters (e.g., crossover rate, mutation rate, learning factor) are adjusted to suit the needs of the optimization process.
The iteration continues until stopping criteria (e.g., number of iterations, improvement, performance objective) are met.
Outputting data: and (5) iteratively optimizing the production configuration and the energy use strategy.
5. Final optimization results:
Input data: and continuously optimizing results in the iteration process.
The treatment process comprises the following steps:
and integrating the genetic algorithm and the result of the particle swarm optimization process to form a final optimization strategy.
The strategy balances production efficiency and energy consumption to achieve optimal performance.
Outputting data: the final determined optimized energy management strategy, which directs actual production and energy usage to ensure maximum efficiency and cost effectiveness.
Through the steps, the optimization algorithm not only combines the advantages of genetic algorithm and particle swarm optimization, but also definitely determines the input and output data of each stage, and how to continuously optimize the production configuration and the energy use strategy through the iterative process, so that the optimal balance between the production efficiency and the energy consumption is realized.
The global search using genetic algorithm specifically includes:
selecting: selecting high-quality individuals (solutions) from the current population, and as parents of the next generation, the selection process evaluates the performance of each individual based on a fitness function, namely, a function of energy efficiency or cost efficiency of the production line, wherein the fitness function is expressed as: fitness = × + ×Wherein, the method comprises the steps of, wherein,AndIs a weight factor for adjusting the degree of influence of yield and plant operating efficiency on the overall fitness;
Crossing: after a parent individual is selected, offspring are generated through crossover operations, new individuals are generated by combining features of the parent individual through single-point crossover, and single-point crossover examples: if there are two individuals A and B, their codes (characteristic representation) may be a combination of energy consumption parameters and production parameters, the single point crossover will select an intersection point, and the data exchange of A and B before this point will generate two new individuals;
Variation: to maintain diversity of the population and avoid premature convergence to a locally optimal solution, a mutation operation is performed on a part of individuals, characteristics of the individuals are randomly changed, and mutation examples are that: for an individual, one or more of its features may be randomly selected and its value randomly increased or decreased (e.g., by adjusting the energy consumption parameter) to explore a new region of the solution space.
The evaluation and selection specifically comprises:
In each generation of genetic algorithm, evaluating individuals in the population, selecting high-performance individuals to enter the next generation, quantifying the capacity of each individual to solve the problem by relying on a fitness function in the evaluating and selecting process, evaluating each individual based on the well-defined fitness function, wherein the individuals with high fitness indicate that the corresponding production configuration and energy use strategy are better;
The selection process comprises the following steps: selection is made according to fitness, and roulette selection is employed to provide highly fitness individuals with a high probability of being selected as a parent of the next generation.
Roulette selection is to assign a selection probability in terms of the proportion of fitness of an individual to the total fitness, each individual being selected with a probability equal to the sum of its fitness divided by the total fitness. Thus, the individuals with high fitness are more likely to be selected, but the individuals with low fitness are also likely to be selected, so that the diversity of the population is maintained.
In the refinement and optimization stage, the particle swarm optimization algorithm is used for carrying out local search in a solution area determined by the genetic algorithm, and the particle swarm optimization algorithm processing process comprises the following steps:
each particle in the population represents a potential solution, namely a corresponding production configuration and energy use strategy;
each particle adjusts its search direction and speed based on individual experience (individual best position) and integrated experience (global best position), and the particle update is calculated as follows:
；
；
Wherein, Is a particleAt the time ofIs used for the speed of the (c) in the (c),Is a particleAt the time ofIs provided in the position of (a),Is the individual best position for particle i,Is the global optimum position for the device,Is an inertial weight, controls the persistence of the particle velocity,AndIs an acceleration constant, controls the speed of movement of particles to individual and global optima,AndIs a random number within interval 0.1. In this way, the PSO algorithm can effectively perform refinement search in the globally optimal vicinity to find a better solution
The iterative loop is a process of alternately executing genetic algorithm and particle swarm optimization, and in each iteration, parameters of the genetic algorithm and the particle swarm optimization are adjusted according to the result of the previous iteration, wherein the parameters comprise a crossing rate, a mutation rate (genetic algorithm parameter), an acceleration constant and an inertia weight (particle swarm optimization parameter);
The final optimization result comprehensively considers the genetic algorithm and the optimal solution obtained in the particle swarm optimization process to form a final optimization strategy, and the final strategy balances the production efficiency and the energy consumption, so that the optimization of energy use is realized while the production requirement is met. The final optimization strategy will guide the actual production and energy management decisions such as adjusting the line speed, equipment operation mode and energy allocation to achieve optimal energy and production efficiency.
Genetic Algorithm (GA) parameter adjustment strategies are as follows:
crossover rate: the crossover rate determines how many individuals in the new generation will be generated by crossover operations, and can be increased to increase the exploratory capacity and diversity of the population if insufficient diversity of the current population is found.
And (3) adjusting a strategy: if the optimal solution is not improved obviously after continuous several iterations, the crossing rate can be improved; if the diversity of the population is too high, resulting in ambiguous optimization direction, the crossover rate can be reduced appropriately.
Mutation rate: the mutation rate determines how many individuals in the population experience mutation operation, and the mutation can introduce new genetic characteristics to increase the diversity of the population.
And (3) adjusting a strategy: if the optimization process falls into local optimum, the mutation rate can be increased so as to increase the possibility of jumping out of the local optimum; conversely, if the population changes too much, resulting in unstable search process, the mutation rate is reduced.
Particle Swarm Optimization (PSO) parameter adjustment strategies are as follows:
acceleration constant: the acceleration constants include an individual learning factor (c 1) and a social learning factor (c 2) representing the tendency of the particles to follow their own experience and group experience, respectively.
And (3) adjusting a strategy: if the particles tend to aggregate rapidly, leading to premature convergence, c2 may be reduced to increase exploration; if the search process is too decentralized, c2 may be added to enhance inter-particle information sharing and collaboration.
Inertial weight (w):
the inertial weights determine the tendency of the particles to maintain the current velocity direction, which balances the ability of global exploration and local development.
And (3) adjusting a strategy: dynamic adjustment methods are typically employed, such as setting higher inertial weights early in the iteration to facilitate global exploration, and decreasing inertial weights as the iteration progresses to enhance local searches. For example, a linear decrementing strategy may be used, gradually decreasing from a higher initial value to a lower ending value.
Through the dynamic adjustment of the parameters of GA and PSO, dynamic balance between global search and local search can be realized, the solution space can be effectively explored, and the probability of finding the global optimal solution can be improved. The self-adaptive adjustment strategy is beneficial to the optimization algorithm to adapt to the search requirements of different stages, so that the efficiency and effect of the whole optimization process are improved.
Setting the flour production line to have several key operating points requires optimizing energy consumption and production efficiency. The goal is to reduce energy costs while maintaining or increasing throughput.
Step 1, data acquisition and integration:
energy metering equipment and sensors are installed on key equipment of a production line, and energy consumption data (such as electric power, water and gas consumption) and production data (such as production capacity and equipment running state) are collected in real time.
The data are integrated to form a comprehensive data set which contains information such as time stamp, energy consumption, production quantity and the like.
Step 2, in the initial stage, global searching is carried out by using a genetic algorithm:
initializing a genetic algorithm: an initial set of solutions is randomly generated, each solution representing a production configuration and energy usage scheme.
Performing global search:
the fitness of each solution is evaluated, measured by calculating the energy consumption per unit of product.
Genetic manipulation (selection, crossover, variation) is applied to generate new populations.
This process is repeated until a set of potential optimal solutions is found.
Step 3, refinement optimization-local search using particle swarm optimization
The output of GA is taken as the input of PSO: the best performing solution in the GA process is chosen as the initial particle position for the PSO.
Performing local search:
The particles update their own velocity and position based on their own optimal position and the optimal position of the population.
The new location of each particle represents an updated production and energy usage scenario.
The iteration is repeated until a better solution is found in the local solution space.
And 4, iterative optimization process:
Alternately using GA and PSO, the quality of the solution is improved by iteration:
Parameters of GA and PSO, such as crossing rate, variation rate, inertial weight, etc., are dynamically adjusted according to the result of the previous iteration.
After each iteration, the best solution found currently is evaluated, and whether stopping conditions (such as iteration times, improvement amount and the like) are met is checked.
Step 5, generating a final optimization result:
And synthesizing the optimal solution obtained in the iterative process to form a final optimization strategy, wherein the strategy minimizes energy consumption while ensuring production efficiency.
And implementing a final strategy, and adjusting actual operation parameters of the production line, such as adjusting the operation speed of a machine, replacing or adjusting equipment configuration, optimizing energy distribution and the like.
Practical application
By this integrated iterative optimization process, it is found that certain devices can be exceptionally energy efficient within a specific time period, while by adjusting the operating schedule or parameters of these devices, energy consumption can be significantly reduced without affecting throughput, or it can be identified that by slightly increasing the energy consumption of certain devices, overall production efficiency can be improved and costs reduced.
S4, introducing reinforcement learning technology, and continuously optimizing decisions by observing feedback of the production process, wherein the reinforcement learning technology specifically comprises the following steps:
Defining a reinforcement learning environment: the method comprises the steps of representing the current state of a production line by defining a state, wherein the current state comprises energy consumption data, production speed, raw material usage amount and product quality index; defining executable operations through the action set, including adjusting device parameters, altering energy input, and modifying production cadence; by defining rewards, the reward signal gives positive rewards when reducing energy consumption and improving production efficiency based on goals of production efficiency and energy consumption, and negative rewards otherwise;
selecting a strategy-based algorithm PPO (Proximal Policy Optimization) to process the continuous state and action space, finding an optimal strategy in a complex production environment;
the optimal production configuration and the energy use strategy obtained by analyzing the integrated iterative multi-objective optimization algorithm are used as the training basis of reinforcement learning, in the training process, by trying different actions and observing results (such as energy consumption and production capacity), how to adjust the production configuration to optimize the energy use is learned, and by continuously trial and error learning, the strategy is updated to maximize long-term rewards;
the trained reinforcement learning model is deployed in a production environment, state data is received in real time, the production process is regulated according to strategy output actions of the model, performance and decision-making effect of the model are monitored, and the reinforcement learning model can be ensured to stably reduce energy cost while maintaining or improving production efficiency.
The PPO algorithm specifically includes:
policy function: policy function Is indicated in a given stateDown selection actionWhereinParameters representing policy networks, in the present invention, statesIs the current production line state including energy consumption, production rate, etc., and actsAdjusting equipment setting or changing energy use strategies;
Dominance function: dominance function Representing execution of an actionIn stateTo a better degree than average, in a production environment, the dominance function can help identify which actions result in better energy usage efficiency or production performance than current strategies;
objective function: the goal of the PPO algorithm is to maximize a tailored objective function that is based on probability ratios WhereinIs a parameter of the old policy, and the objective function is defined as:
Wherein Is a small constant, takes a value of 0.2, is used to limit the stride of policy updates,In the form of a probability proportion,For clipping functions forThe value of (2) is limited toWithin the range;
The operation process of the PPO algorithm is as follows:
policy evaluation: evaluating current policies using collected production and energy data Calculating a dominance function for each state action pair。
Policy improvement: by optimizing an objective functionUpdating policy parametersI.e. to find policy parameters that can increase the expected rewards.
Cutting and updating: by passing throughLimiting the magnitude of policy updating prevents the performance from being drastically reduced due to excessive policy updating.
In the invention, the PPO algorithm is applied to effectively perform strategy optimization in the operation of the production line, and the production parameters and the energy use strategy are automatically adjusted so as to minimize the energy cost and simultaneously maintain or improve the production efficiency. By constantly interactively learning and updating the strategy, the system can adapt to the change of the production environment and continuously optimize the energy efficiency of the production process.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the invention is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (1)
1. The flour production line equipment operation and maintenance management method based on the Internet of things is characterized by comprising the following steps of:
S1, energy consumption data acquisition: the energy consumption data of each equipment and process stage are collected in real time through energy metering equipment arranged on a flour production line;
s2, data transmission and integration: the collected energy consumption data is transmitted to a central energy management unit, and the energy consumption data and the production data are integrated to form a comprehensive data set;
S3, introducing an integrated iterative multi-objective optimization algorithm, including genetic algorithm and particle swarm optimization, taking a comprehensive data set as input and analyzing to balance production efficiency and energy consumption, and finding out an optimal production configuration and an energy use strategy;
S4, introducing reinforcement learning technology, automatically identifying and implementing optimal production configuration and energy use strategy through interactive learning with the production environment, and realizing automatic adjustment of the production process to minimize energy cost;
The S1 specifically comprises the following steps:
s11: the method comprises the steps of installing multiple types of energy metering equipment including an electric energy meter, a gas flowmeter and a water flowmeter in key equipment and process stages of a flour production line, and monitoring and recording the consumption of electric power, gas and water in each equipment and process stage in real time;
S12: the configuration data acquisition unit is used for inputting the data of each metering device, carrying out standardization processing on the data to form a data stream in a unified format, and transmitting the standardized data stream to the central energy management unit in real time by utilizing a wireless network so as to be used for subsequent data analysis and optimization processing;
The production data in S2 include raw material consumption, product yield, equipment operation state and process parameters, and S2 specifically includes:
S21: preprocessing the collected data, including data cleaning, data standardization and data synchronization;
S22: after data preprocessing, data fusion operation is carried out, energy consumption data and production data are integrated into a unified data model, and the energy consumption data are associated with corresponding production activities through data matching and association;
S23: constructing a comprehensive data set, organizing the fused data into the comprehensive data set by using a database management system or a data analysis platform, wherein the data set reflects the relation between production activities and energy consumption, and each data record contains a time stamp, an energy consumption index and production parameter information in the comprehensive data set;
The integrated iterative multi-objective optimization algorithm in S3 specifically includes:
s31: in the initial stage, a genetic algorithm is used for global searching, the genetic algorithm searches a solution space by simulating natural selection and a genetic mechanism, an optimized solution set is searched, the genetic algorithm widely searches the solution space, a main area of a globally optimal solution is identified, and the situation that the globally optimal solution falls into local optimization in the early stage is avoided;
s32: evaluating and selecting, optimizing a genetic algorithm after multiple iterations, evaluating the performance of the currently found optimal solution or solution set, and determining the quality of a genetic algorithm search result;
S33: in the refinement and optimization stage, an optimal solution or a solution set found by a genetic algorithm is used for performing refinement and search by starting a particle swarm optimization algorithm, the particle swarm optimization is performed by simulating social behaviors of a bird swarm so as to quickly converge on the optimal solution in a solution space, and local search and optimization are performed in a main area determined by the genetic algorithm so as to refine and adjust and improve the accuracy of the solution;
S34: iterative loop, combining the result of genetic algorithm and particle swarm optimization, continuously iterating and optimizing, and adjusting the parameters of genetic algorithm and particle swarm optimization according to the result of the last iteration in each iteration so as to adapt to the dynamic change of the optimization process;
S35: through an iterative mode, genetic algorithm and particle swarm optimization are continuously recycled until a stopping criterion is met, wherein the stopping criterion comprises the preset iterative times, the improvement amount of the solution is lower than a threshold value or a preset performance target is achieved;
s36: final optimization results: after multiple iterations, synthesizing an optimization process of genetic algorithm and particle swarm optimization, and finally determining an optimized energy management strategy;
the global search using genetic algorithm specifically includes:
selecting: selecting high-quality individuals from the current population as parents of the next generation, wherein the selection process evaluates the performance of each individual based on a fitness function, namely, the energy efficiency or cost efficiency function of the production line, and the fitness function is expressed as: fitness = ×+×Wherein, the method comprises the steps of, wherein,AndIs a weight factor for adjusting the degree of influence of yield and plant operating efficiency on the overall fitness;
crossing: after a parent individual is selected, generating offspring through crossover operation, and generating a new individual through single-point crossover combining with the characteristics of the parent individual;
Variation: in order to maintain diversity of the population and avoid premature convergence to a local optimal solution, carrying out mutation operation on part of individuals and randomly changing characteristics of the individuals;
The evaluation and selection specifically comprises:
In each generation of genetic algorithm, evaluating individuals in the population, selecting high-performance individuals to enter the next generation, quantifying the capacity of each individual to solve the problem by relying on a fitness function in the evaluating and selecting process, evaluating each individual based on the well-defined fitness function, wherein the individuals with high fitness indicate that the corresponding production configuration and energy use strategy are better;
The selection process comprises the following steps: selecting according to fitness, and adopting roulette selection to enable individuals with high fitness to have parents with high probability of being selected as the next generation;
The particle swarm optimization algorithm is used for carrying out local search in a solution area determined by the genetic algorithm, and the particle swarm optimization algorithm processing process comprises the following steps:
each particle in the population represents a potential solution, namely a corresponding production configuration and energy use strategy;
each particle adjusts its search direction and speed according to individual experience and collective experience, and the particle update is calculated as follows:
；
；
Wherein, Is a particleAt the time ofIs used for the speed of the (c) in the (c),Is a particleAt the time ofIs provided in the position of (a),Is the individual best position for particle i,Is the global optimum position for the device,Is an inertial weight, controls the persistence of the particle velocity,AndIs an acceleration constant, controls the speed of movement of particles to individual and global optima,AndIs a random number within interval [0,1 ];
The iterative loop is a process of alternately executing genetic algorithm and particle swarm optimization, and in each iteration, parameters of the genetic algorithm and the particle swarm optimization are adjusted according to the result of the previous iteration, wherein the parameters comprise a crossing rate, a variation rate, an acceleration constant and an inertia weight;
the final optimization result comprehensively considers the genetic algorithm and the optimal solution obtained in the particle swarm optimization process to form a final optimization strategy, and the final strategy balances the production efficiency and the energy consumption, so that the optimization of energy use is realized while the production requirement is met;
and S4, introducing reinforcement learning technology, and continuously optimizing the decision by observing the feedback of the production process, wherein the method specifically comprises the following steps of:
Defining a reinforcement learning environment: the method comprises the steps of representing the current state of a production line by defining a state, wherein the current state comprises energy consumption data, production speed, raw material usage amount and product quality index; defining executable operations through the action set, including adjusting device parameters, altering energy input, and modifying production cadence; by defining rewards, the reward signal gives positive rewards when reducing energy consumption and improving production efficiency based on goals of production efficiency and energy consumption, and negative rewards otherwise;
Selecting a strategy-based algorithm PPO to process continuous states and action spaces, and finding an optimal strategy in a complex production environment;
The optimal production configuration and the energy use strategy obtained by analyzing the integrated iterative multi-objective optimization algorithm are used as the training basis of reinforcement learning, in the training process, by trying different actions and observing results, how to adjust the production configuration to optimize the energy use is learned, and by continuously trying and learning by mistake, the strategy is updated to maximize the long-term rewards;
The PPO algorithm specifically includes:
policy function: policy function Is indicated in a given stateDown selection actionWhereinParameters representing a policy network;
Dominance function: dominance function Representing execution of an actionIn stateLower to a better degree than the average case;
objective function: the goal of the PPO algorithm is to maximize a tailored objective function that is based on probability ratios WhereinIs a parameter of the old policy, and the objective function is defined as:
Wherein Is a small constant, takes a value of 0.2, is used to limit the stride of policy updates,In the form of a probability proportion,For clipping functions forThe value of (2) is limited toWithin the range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410494661.8A CN118096085B (en) | 2024-04-24 | 2024-04-24 | Flour production line equipment operation and maintenance management method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410494661.8A CN118096085B (en) | 2024-04-24 | 2024-04-24 | Flour production line equipment operation and maintenance management method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118096085A CN118096085A (en) | 2024-05-28 |
| CN118096085B true CN118096085B (en) | 2024-07-19 |
Family
ID=91158783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410494661.8A Active CN118096085B (en) | 2024-04-24 | 2024-04-24 | Flour production line equipment operation and maintenance management method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118096085B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118446652A (en) * | 2024-06-13 | 2024-08-06 | 深圳市中广电通灯业有限公司 | LED track lamp production control method and system based on Internet of things |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116862160A (en) * | 2023-06-29 | 2023-10-10 | 盐城工学院 | Multi-target balance optimization method for automobile coating production line |
| CN117789422A (en) * | 2024-02-26 | 2024-03-29 | 江西依爱弘泰消防安全技术有限公司 | Combustible gas alarm control system and method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110286588B (en) * | 2019-05-24 | 2021-11-09 | 同济大学 | Assembly line rebalance optimization method considering energy consumption |
| CN110851272B (en) * | 2019-10-30 | 2022-02-11 | 内蒙古农业大学 | Cloud task scheduling method based on phagocytic particle swarm genetic hybrid algorithm |
| CN112632860B (en) * | 2021-01-04 | 2024-06-04 | 华中科技大学 | Power transmission system model parameter identification method based on reinforcement learning |
| CN115689502B (en) * | 2022-12-30 | 2023-04-14 | 广东美的制冷设备有限公司 | Equipment scheduling method, device, production system and storage medium |
| CN116088761A (en) * | 2023-01-18 | 2023-05-09 | 华中科技大学 | Automatic parameter adjusting method and system for distributed storage system based on reinforcement learning |
| CN116451737A (en) * | 2023-04-25 | 2023-07-18 | 上海电力大学 | PG-W-PSO method for improving particle swarm based on reinforcement learning strategy gradient |
| CN117273275A (en) * | 2023-10-08 | 2023-12-22 | 飞友科技有限公司 | Flight management and control plan generation method based on genetic programming algorithm |
-
2024
- 2024-04-24 CN CN202410494661.8A patent/CN118096085B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116862160A (en) * | 2023-06-29 | 2023-10-10 | 盐城工学院 | Multi-target balance optimization method for automobile coating production line |
| CN117789422A (en) * | 2024-02-26 | 2024-03-29 | 江西依爱弘泰消防安全技术有限公司 | Combustible gas alarm control system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118096085A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Parpinelli et al. | A review of techniques for online control of parameters in swarm intelligence and evolutionary computation algorithms | |
| Zhou et al. | Multiobjective evolutionary algorithms: A survey of the state of the art | |
| CN117891606B (en) | Cloud computing driven industrial park management system | |
| Bansal et al. | Inertia weight strategies in particle swarm optimization | |
| Kuo et al. | Integration of particle swarm optimization and genetic algorithm for dynamic clustering | |
| CN116934220A (en) | Intelligent warehouse layout method based on intelligent data analysis and algorithm optimization | |
| CN118096085B (en) | Flour production line equipment operation and maintenance management method based on Internet of things | |
| Yang et al. | Constrained dynamic multi-objective evolutionary optimization for operational indices of beneficiation process | |
| CN103745273A (en) | Semiconductor fabrication process multi-performance prediction method | |
| CN117830029B (en) | Centralized control platform management system based on optimization algorithm | |
| CN108898259A (en) | Adaptive Evolutionary planning Methods of electric load forecasting and system based on multi-factor comprehensive | |
| CN113128124B (en) | Multi-grade C-Mn steel mechanical property prediction method based on improved neural network | |
| CN117952286A (en) | Intelligent road construction plan adjusting system | |
| CN108469797A (en) | A kind of grinding process modeling method based on neural network and evolutionary computation | |
| Jamous et al. | Modifications of particle swarm optimization techniques and its application on stock market: A survey | |
| CN102129242A (en) | Product quality control method during batch processing production process based on two-layer hybrid intelligent optimization | |
| Tian et al. | Dynamic operation optimization based on improved dynamic multi-objective dragonfly algorithm in continuous annealing process. | |
| CN118244729B (en) | MES-based production workshop dynamic management method and system | |
| CN110490446A (en) | A kind of modular process recombination method based on improved adaptive GA-IAGA | |
| CN117852693A (en) | Rotational molding machine remote optimization device and method integrating artificial intelligence algorithm | |
| Mutturi | Dynamic optimization of fed-batch bioprocesses using flower pollination algorithm | |
| Li et al. | An efficient hybridized genetic algorithm | |
| CN117196174A (en) | Material demand prediction method based on multidimensional feature fusion | |
| CN118536677B (en) | Intelligent decision-making method and system for technological parameters of mineral separation system | |
| CN118628097B (en) | Method and system for managing full life cycle cost of 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |