Intelligent dust adjusting system

Abstract

The invention relates to the technical field of operation and maintenance of power plant equipment, and provides an intelligent dust adjusting system which realizes automatic adjustment of secondary current of an electric dust remover through a data acquisition unit, a data acquisition unit, a data processing unit, a model correction unit and a decision generation unit, so that the dust concentration is accurately controlled, and the operation efficiency is improved. The optimal electric field current setting can be predicted by using the deep learning model according to real-time data such as power plant load, dust concentration at the inlet and outlet of the electric precipitator, flue gas flow and temperature, and the model is continuously optimized through the genetic algorithm. The intelligent dust adjusting system effectively solves the problems of complexity and low efficiency of manual adjustment of electric precipitation current, improves the dust removal efficiency, reduces the energy consumption, and enhances the economic benefit and environmental protection performance of a power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of power plant equipment operation and maintenance, and in particular to an intelligent dust regulating system. Background Art

[0002] The technological development of intelligent dust control systems is remarkable. With the continuous advancement of the Internet of Things, big data and artificial intelligence technologies, intelligent dust control systems have been able to achieve efficient and accurate dust control. These systems use built-in sensors and controllers to monitor and adjust dust concentration in real time, improving the production environment to meet environmental standards. At the same time, the intelligent dust control system also incorporates cloud computing and remote monitoring functions, allowing operators to view the operating status and various parameters of the equipment in real time in the control room or remote terminal, improving the maintenance efficiency and reliability of the equipment. In addition, the intelligent dust control system also has a fault self-diagnosis function, which can automatically detect and identify equipment failures and take timely countermeasures, further improving the stability and reliability of the system.

[0003] The existing intelligent dust regulation system has the following technical pain points in the actual application process. The existing electrostatic precipitator adjustment relies on manual operation. The operating staff on duty need to click on the electrostatic precipitator electric field one by one, and then enter the corresponding window to change the current value. This one-by-one adjustment method is inefficient. At the same time, the lack of support for the automatic control system makes it impossible for the electrostatic precipitator to automatically adjust the secondary current according to load changes or dust concentration to achieve the best dust removal efficiency. The cumbersome adjustment method not only increases the difficulty of operation for operators, but also causes the electrostatic precipitator to operate inflexibly when the load changes rapidly, thereby increasing the consumption rate of factory electricity and affecting the economic benefits of the power plant.

[0004] The existing ESP adjustment methods are too cumbersome, and they can neither automatically adjust the ESP current nor adjust it manually at one time. The main reason is the limitation of technology. Traditional ESP adjustment relies on manual operation. The operator on duty needs to click on the ESP electric field one by one, and then enter the corresponding window to change the current value. This one-by-one adjustment method is inefficient. At the same time, the lack of support from the automatic control system makes it impossible for the ESP to automatically adjust the secondary current according to load changes or dust concentration to achieve the best dust removal efficiency. The cumbersome adjustment method not only increases the difficulty of operation for operators, but also causes the ESP to operate inflexibly when the load changes rapidly, thereby increasing the consumption rate of plant electricity and affecting the economic benefits of the power plant. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent dust regulation system to solve the problem that the secondary current of the electrostatic precipitator needs to be manually adjusted when the load of the power plant increases or decreases.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows:

[0007] The present invention provides an intelligent dust control system, comprising:

[0008] A data acquisition unit is used to acquire operation and maintenance data of the intelligent dust control system, the operation and maintenance data of the intelligent dust control system includes power plant load data, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, electric field current of the electrostatic precipitator and flue gas temperature, and stores the acquired operation and maintenance data of the intelligent dust control system in a database;

[0009] A data acquisition unit is used to collect dust concentration, flue gas flow, temperature, electric field current data and corresponding standard safety parameters at the inlet and outlet of the electric precipitator of the power plant, and store the collected data in a database;

[0010] a data processing unit for acquiring dust control tasks, extracting data features of dust control tasks, obtaining dust control task index data, retrieving corresponding historical data in a database according to the dust control task index data, obtaining historical data corresponding to the dust control tasks, training using a deep learning model of historical data corresponding to the dust control tasks, obtaining a dust control task simulation model, receiving real-time dust control tasks, substituting the real-time dust control tasks into the dust control task simulation model, obtaining real-time dust control task simulation results, collecting dust concentration, flue gas flow, temperature and electric field current data at the inlet and outlet of the electric precipitator of the power plant during the execution of the dust control task, obtaining the operating data of the electric precipitator of the power plant after the execution of the dust control task, comparing the operating data of the electric precipitator of the power plant after the execution of the dust control task with the simulation results of the real-time dust control task, and optimizing the dust control task simulation model if the error range between the simulation results of the real-time dust control task and the operating data of the electric precipitator of the power plant after the execution of the dust control task is greater than a preset value;

[0011] A model correction unit is used to obtain data generated in the process of constructing the dust regulation task simulation model in the data processing unit and in the process of data processing of the dust regulation task simulation model, obtain a data processing unit operation data set, and optimize the dust regulation task simulation model using a genetic algorithm based on the data processing unit operation data set to obtain an optimized dust regulation task simulation model;

[0012] The decision generation unit is used to use the optimized dust control task simulation model to process the data of the real-time dust control task, output the real-time simulation results, and generate corresponding control instructions according to the real-time simulation results. The control instructions are sent to the controller of the electrostatic precipitator. The controller of the electrostatic precipitator automatically adjusts the size of the electric field current according to the control instructions to achieve dust concentration control.

[0013] Furthermore, in the intelligent dust control system provided by the present invention, the data acquisition unit is also used for:

[0014] The data acquisition unit establishes a connection with sensors and data sources of the intelligent dust control system, wherein the sensors include dust concentration monitors for the inlet and outlet of the electrostatic precipitator, a flue gas flow meter, an electric field current monitor for the electrostatic precipitator, and a flue gas temperature sensor;

[0015] The data acquisition unit sends data requests to various data sources. The data requests include power plant load data, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, electrostatic precipitator electric field current and flue gas temperature information. After receiving the request, the data source sends the corresponding data to the data acquisition unit in a standardized format.

[0016] Furthermore, in the intelligent dust control system provided by the present invention, the data acquisition unit is also used for:

[0017] The data acquisition unit establishes a data acquisition channel with each monitoring point of the electric precipitator of the power plant. After the data acquisition channel is established, the data acquisition unit collects data such as dust concentration, flue gas flow, temperature and electric field current at the inlet and outlet of the electric precipitator of the power plant in real time;

[0018] The data collection unit performs data integrity check, outlier detection and data range verification on the collected data to obtain verified data, which will be stored in the database.

[0019] Furthermore, in the intelligent dust control system provided by the present invention, the data processing unit is also used for:

[0020] The data processing unit retrieves the corresponding historical data in the database according to the dust regulation task index data, and the dust regulation task index data includes power plant load data, dust concentration data at the inlet and outlet of the electrostatic precipitator, flue gas flow data and temperature data;

[0021] The retrieved historical data are preprocessed, and the preprocessed and integrated historical data are used as input to the deep learning model to train the deep learning model and obtain a dust regulation task simulation model;

[0022] The data processing unit verifies the dust control task simulation model, applies the dust control task simulation model to a portion of historical data that has not participated in training, and compares the difference between the predicted results of the dust control task simulation model and the actual results. If the error range is greater than the preset value, the dust control task simulation model needs to be optimized.

[0023] Furthermore, in the intelligent dust control system provided by the present invention, the data processing unit is also used for:

[0024] The data processing unit receives dust control task requests from power plants or other monitoring systems in real time, performs preliminary analysis on the received tasks, and then extracts data features of the received real-time dust control tasks. The extracted features include dust concentration target value, flue gas flow expectation, temperature requirement, and electric field current setting.

[0025] The extracted real-time dust control task feature data is used as input and substituted into the pre-trained dust control task simulation model. The simulation result of the real-time dust control task is obtained through calculation by the pre-trained dust control task simulation model.

[0026] The simulation results of the real-time dust regulation task include the predicted dust concentration, flue gas flow, temperature and electric field current data at the inlet and outlet of the electrostatic precipitator.

[0027] Furthermore, in the intelligent dust control system provided by the present invention, the model correction unit is also used for:

[0028] The data generated by the model correction unit during operation include data for constructing a dust regulation task simulation model, input and output data when the model performs data processing, forming a data processing unit operation data set, and encoding the data in the data processing unit operation data set;

[0029] Initialize a population containing multiple candidate solutions, where the candidate solutions are parameter configurations of the dust regulation task simulation model. The candidate solutions are randomly generated and encoded as chromosomes of the genetic algorithm.

[0030] After initializing the population, the model correction unit performs genetic operations including selection, crossover, and mutation to produce the next generation. The genetic operations are iterated multiple times until the stopping condition is met.

[0031] Furthermore, in the intelligent dust control system provided by the present invention, the decision generation unit is also used for:

[0032] The decision generation unit receives real-time dust regulation task data from the sensor, inputs the real-time dust regulation task data into the optimized dust regulation task simulation model, and performs real-time simulation calculation. The optimized dust regulation task simulation model predicts the best electric field current setting according to the current load condition and dust concentration parameters;

[0033] After the simulation is completed, the decision generation unit analyzes the simulation results and generates corresponding control instructions based on the simulation results. When the control instructions are generated, the decision generation unit sends the control instructions to the controller of the electrostatic precipitator.

[0034] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0035] The present invention realizes automation of the secondary current adjustment of the electric precipitator of the power plant through the intelligent dust adjustment system, without manual operation, thus improving the automation degree of the system, reducing the operating burden of the operator on duty, and improving work efficiency. The system can automatically adjust the electric field current according to the real-time power plant load, dust concentration at the inlet and outlet of the electric precipitator, flue gas flow rate, temperature and other parameters, thereby realizing precise control of dust concentration. This helps to improve the compliance of power plant emissions with environmental protection standards and improve dust removal efficiency.

[0036] The system has a built-in model correction unit that can continuously collect data during system operation and use genetic algorithms to optimize the dust regulation task simulation model. This allows the model to continuously adapt to changes in power plant load and dust concentration, improving the accuracy of predictions and the reliability of the system. By automatically adjusting the secondary current of the electrostatic precipitator, the system can effectively reduce the consumption rate of plant electricity while ensuring dust removal efficiency. This not only helps to reduce the operating costs of the power plant, but also helps to improve the economic benefits of the power plant.

[0037] The intelligent dust control system of the present invention significantly improves the economic benefits of the power plant by improving dust removal efficiency, reducing energy consumption and reducing manual operation costs. At the same time, since the system can monitor and adjust the operating status of the electrostatic precipitator in real time, it also helps to extend the service life of the equipment and further reduce maintenance costs. The intelligent dust control system has a fault self-diagnosis function, which can automatically detect and identify equipment failures and take timely countermeasures. This helps to improve the stability and reliability of the system and improve the safe and stable operation of the power plant.

[0038] The system can automatically adjust the secondary current of the electrostatic precipitator according to the real-time changes in the power plant load, and improve the dust removal efficiency to always maintain a high level. This helps the power plant to maintain a stable dust removal effect and low energy consumption when the load fluctuates greatly.

[0039] In summary, the intelligent dust control system of the present invention provides strong support for the environmentally friendly operation and economic benefit improvement of power plants through the beneficial effects of improving the degree of automation, precise dust control, continuous model optimization, reducing energy consumption, improving economic benefits, enhancing system stability, and flexibly responding to load changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0041] Figure 1 A schematic diagram of the internal modules of the intelligent dust control system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0043] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0044] The present invention provides an intelligent dust control system, comprising:

[0045] A data acquisition unit is used to acquire operation and maintenance data of the intelligent dust control system, the operation and maintenance data of the intelligent dust control system includes power plant load data, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, electric field current of the electrostatic precipitator and flue gas temperature, and stores the acquired operation and maintenance data of the intelligent dust control system in a database;

[0046] A data acquisition unit is used to collect dust concentration, flue gas flow, temperature, electric field current data and corresponding standard safety parameters at the inlet and outlet of the electric precipitator of the power plant, and store the collected data in a database;

[0047] a data processing unit for acquiring dust control tasks, extracting data features of dust control tasks, obtaining dust control task index data, retrieving corresponding historical data in a database according to the dust control task index data, obtaining historical data corresponding to the dust control tasks, training using a deep learning model of historical data corresponding to the dust control tasks, obtaining a dust control task simulation model, receiving real-time dust control tasks, substituting the real-time dust control tasks into the dust control task simulation model, obtaining real-time dust control task simulation results, collecting dust concentration, flue gas flow, temperature and electric field current data at the inlet and outlet of the electric precipitator of the power plant during the execution of the dust control task, obtaining the operating data of the electric precipitator of the power plant after the execution of the dust control task, comparing the operating data of the electric precipitator of the power plant after the execution of the dust control task with the simulation results of the real-time dust control task, and optimizing the dust control task simulation model if the error range between the simulation results of the real-time dust control task and the operating data of the electric precipitator of the power plant after the execution of the dust control task is greater than a preset value;

[0048] The data processing unit plays a core role in the intelligent dust control system. Its detailed functions and workflow are as follows:

[0049] The data processing unit receives dust regulation task requests from power plants or other monitoring systems. The dust regulation task requests include adjusting the dust concentration at the inlet and outlet of the electrostatic precipitator to a certain target value, adjusting the flue gas flow, temperature requirements or electric field current settings, etc.

[0050] After preliminary analysis of the received dust control task, the data processing unit extracts data features of the task, including key parameters such as dust concentration target value, flue gas flow rate expectation, temperature requirements, and electric field current setting. Based on the extracted dust control task index data, the data processing unit retrieves the corresponding historical data in the database, including power plant load data under similar working conditions in the past, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow rate, temperature, and electric field current.

[0051] After preprocessing and integration, the retrieved historical data is used as input data of the deep learning model to train the model. Through training, a model that can simulate the dust regulation task, namely the dust regulation task simulation model, is obtained.

[0052] When a real-time dust control task is received, the data processing unit substitutes the task characteristic data into the pre-trained dust control task simulation model, performs calculations and obtains the simulation results of the real-time dust control task. The simulation results of the real-time dust control task include the predicted dust concentration, flue gas flow, temperature and electric field current data at the inlet and outlet of the electrostatic precipitator.

[0053] During the execution of the dust control task, the data processing unit will collect the actual operating data of the power plant's electrostatic precipitator in real time, including the dust concentration at the inlet and outlet, flue gas flow, temperature, and electric field current. The actual operating data after the dust control task is executed is compared with the previous simulation results. If the error range between the two is greater than the preset value, it means that the current dust control task simulation model is not accurate enough or needs to be updated. The data processing unit will trigger the model optimization process and use the new data to retrain the model or adjust the model parameters to improve the accuracy and adaptability of the model.

[0054] Through the above process, the data processing unit can realize accurate simulation and prediction of dust control tasks, and continuously optimize the model according to the feedback of actual operation data, thereby improving the intelligent dust control system to automatically adjust the secondary current of the electrostatic precipitator according to changes in the power plant load and realize accurate control of dust concentration.

[0055] A model correction unit is used to obtain data generated in the process of constructing the dust regulation task simulation model in the data processing unit and in the process of data processing of the dust regulation task simulation model, obtain a data processing unit operation data set, and optimize the dust regulation task simulation model using a genetic algorithm based on the data processing unit operation data set to obtain an optimized dust regulation task simulation model;

[0056] The model correction unit is responsible for optimizing the dust control task simulation model in the intelligent dust control system to improve the accuracy and adaptability of the model. The following is the detailed workflow of the model correction unit:

[0057] The model correction unit first obtains all the data generated by the data processing unit in the process of building the dust control task simulation model, including model training data, model verification data, model parameters, etc. At the same time, the model correction unit also collects the data generated by the dust control task simulation model in the process of data processing, such as model prediction results, actual operation data, error analysis, etc.

[0058] All the data collected above are integrated to form a complete data processing unit operation data set. This set contains all relevant information generated during the model construction and operation process, and is the basis for subsequent optimization work. Based on the data processing unit operation data set, the model correction unit uses a genetic algorithm to optimize the dust regulation task simulation model. Genetic algorithm is a search algorithm that simulates natural selection and genetic mechanisms, which can find the optimal solution in a complex space.

[0059] During the optimization process, the model correction unit regards the parameter configuration of the dust control task simulation model as a candidate solution, and forms an initial population by randomly generating multiple candidate solutions. Then, the selection, crossover and mutation operations of the genetic algorithm are used to iteratively generate new candidate solutions, gradually approaching the optimal solution.

[0060] As the genetic algorithm iterates, the model correction unit continuously evaluates the quality of each candidate solution and updates the population based on the evaluation results. Excellent candidate solutions will be retained, and new candidate solutions will be generated through crossover and mutation operations.

[0061] After multiple iterations, when the stopping condition is met (such as reaching the preset number of iterations or error range), the genetic algorithm will converge to an optimal solution or a near-optimal solution. At this time, the model correction unit will use this optimal solution to update the parameter configuration of the dust control task simulation model to obtain an optimized model.

[0062] Finally, the model correction unit outputs the optimized dust regulation task simulation model to the decision generation unit or other related modules for use. The optimized model has higher accuracy and adaptability, and can better cope with the challenges brought by power plant load changes.

[0063] Through the above workflow, the model correction unit can continuously optimize and improve the dust control task simulation model, enhance the intelligent dust control system to always maintain the best working state, and achieve precise control of dust concentration.

[0064] The decision generation unit is used to use the optimized dust control task simulation model to process the data of the real-time dust control task, output the real-time simulation results, and generate corresponding control instructions according to the real-time simulation results. The control instructions are sent to the controller of the electrostatic precipitator. The controller of the electrostatic precipitator automatically adjusts the size of the electric field current according to the control instructions to achieve dust concentration control.

[0065] In the intelligent dust control system, the decision generation unit processes the data of the real-time dust control task according to the optimized dust control task simulation model, and generates corresponding control instructions to automatically adjust the electric field current of the electrostatic precipitator, thereby realizing precise control of dust concentration. The following is the detailed workflow of the decision generation unit:

[0066] The decision generation unit receives real-time dust adjustment tasks from power plants or other monitoring systems. The real-time dust adjustment tasks include adjusting the dust concentration at the inlet and outlet of the electrostatic precipitator to a certain target value, adjusting the flue gas flow rate, temperature requirements, etc. The decision generation unit inputs the received real-time dust adjustment task data into the optimized dust adjustment task simulation model. The dust adjustment task simulation model performs real-time simulation calculations based on the current load conditions, dust concentration parameters and other related factors.

[0067] Through simulation calculation, the dust regulation task simulation model outputs real-time simulation results, including the predicted dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, temperature, and recommended electric field current settings. Based on the real-time simulation results, the decision generation unit generates corresponding control instructions. These instructions are intended to guide the controller of the electrostatic precipitator on how to adjust the size of the electric field current to achieve the expected dust concentration control target.

[0068] The decision generation unit sends the generated control instructions to the controller of the electrostatic precipitator. After receiving the instructions, the controller will automatically adjust the size of the electric field current according to the instructions. During the execution of the control instructions, the decision generation unit will monitor the operating status of the electrostatic precipitator and the changes in dust concentration in real time. If it is found that there is a large deviation between the actual operating results and the expected target, the decision generation unit will adjust the control strategy or regenerate the control instructions in time to improve the effective control of dust concentration.

[0069] The decision-making unit will also continuously optimize the dust regulation task simulation model and control strategy based on the actual operation data and feedback information of the electrostatic precipitator. Through continuous learning and improvement, the decision-making unit can gradually improve the accuracy and efficiency of dust regulation, providing a strong guarantee for the safe and stable operation of the power plant.

[0070] In summary, the decision-making unit achieves precise control of the electric field current of the electrostatic precipitator by comprehensively using the optimized dust regulation task simulation model and real-time data processing technology, thereby effectively solving the problem of manually adjusting the secondary current of the electrostatic precipitator when the load of the power plant increases or decreases.

[0071] Specifically, in the intelligent dust control system provided by the present invention, the data acquisition unit is further used for:

[0072] The data acquisition unit establishes a connection with sensors and data sources of the intelligent dust control system, wherein the sensors include dust concentration monitors for the inlet and outlet of the electrostatic precipitator, a flue gas flow meter, an electric field current monitor for the electrostatic precipitator, and a flue gas temperature sensor;

[0073] The data acquisition unit sends data requests to various data sources. The data requests include power plant load data, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, electrostatic precipitator electric field current and flue gas temperature information. After receiving the request, the data source sends the corresponding data to the data acquisition unit in a standardized format.

[0074] Specifically, in the intelligent dust control system provided by the present invention, the data acquisition unit is also used for:

[0075] The data acquisition unit establishes a data acquisition channel with each monitoring point of the electric precipitator of the power plant. After the data acquisition channel is established, the data acquisition unit collects data such as dust concentration, flue gas flow, temperature and electric field current at the inlet and outlet of the electric precipitator of the power plant in real time;

[0076] The data collection unit performs data integrity check, outlier detection and data range verification on the collected data to obtain verified data, which will be stored in the database.

[0077] Specifically, in the intelligent dust control system provided by the present invention, the data processing unit is further used for:

[0078] The data processing unit retrieves the corresponding historical data in the database according to the dust regulation task index data, and the dust regulation task index data includes power plant load data, dust concentration data at the inlet and outlet of the electrostatic precipitator, flue gas flow data and temperature data;

[0079] The retrieved historical data are preprocessed, and the preprocessed and integrated historical data are used as input to the deep learning model to train the deep learning model and obtain a dust regulation task simulation model;

[0080] The data processing unit verifies the dust control task simulation model, applies the dust control task simulation model to a portion of historical data that has not participated in training, and compares the difference between the predicted results of the dust control task simulation model and the actual results. If the error range is greater than the preset value, the dust control task simulation model needs to be optimized.

[0081] Specifically, in the intelligent dust control system provided by the present invention, the data processing unit is further used for:

[0082] The data processing unit receives dust control task requests from power plants or other monitoring systems in real time, performs preliminary analysis on the received tasks, and then extracts data features of the received real-time dust control tasks. The extracted features include dust concentration target value, flue gas flow expectation, temperature requirement, and electric field current setting.

[0083] The extracted real-time dust control task feature data is used as input and substituted into the pre-trained dust control task simulation model. The simulation result of the real-time dust control task is obtained through calculation by the pre-trained dust control task simulation model.

[0084] The simulation results of the real-time dust regulation task include the predicted dust concentration, flue gas flow, temperature and electric field current data at the inlet and outlet of the electrostatic precipitator.

[0085] Specifically, in the intelligent dust control system provided by the present invention, the model correction unit is further used for:

[0086] The data generated by the model correction unit during operation include data for constructing a dust regulation task simulation model, input and output data when the model performs data processing, forming a data processing unit operation data set, and encoding the data in the data processing unit operation data set;

[0087] Initialize a population containing multiple candidate solutions, where the candidate solutions are parameter configurations of the dust regulation task simulation model. The candidate solutions are randomly generated and encoded as chromosomes of the genetic algorithm.

[0088] After initializing the population, the model correction unit performs genetic operations including selection, crossover, and mutation to produce the next generation. The genetic operations are iterated multiple times until the stopping condition is met.

[0089] Specifically, the model correction unit in the intelligent dust control system provided by the present invention follows the following detailed steps when performing its optimization function:

[0090] The model correction unit collects two types of data during operation. One type is the data generated when building the dust control task simulation model, including the model's structural parameters, training data, verification data, etc. The other type is the input and output data when the model processes data, such as real-time dust control task data, model prediction results, actual operation data, etc.

[0091] All the collected data will be integrated into a data processing unit to run the data set. In order to facilitate subsequent processing, these data will be encoded into a form suitable for genetic algorithm operation. For example, the parameter configuration of the model (candidate solution) will be encoded as a chromosome in the genetic algorithm.

[0092] The model correction unit initializes a population containing multiple candidate solutions. These candidate solutions represent different parameter configurations of the dust regulation task simulation model and are the starting point for the genetic algorithm to search for the optimal solution. The candidate solutions are obtained by random generation, and each candidate solution is encoded as a chromosome, which constitutes part of the population.

[0093] Genetic Operations:

[0094] Selection: In each generation, the model correction unit selects a portion of excellent candidate solutions as parents according to the fitness function (usually based on the error between the model prediction results and the actual running data) to generate the next generation.

[0095] Crossover: The selected parent candidate solutions will undergo a crossover operation, that is, exchanging part of their chromosomes to generate new candidate solutions (offspring). The crossover operation helps to combine the advantages of different parent generations and explore new parameter configuration spaces.

[0096] Mutation: In order to maintain the diversity of the population and prevent premature convergence, the model correction unit will also perform mutation operations on the newly generated candidate solutions. The mutation operation will randomly change certain genes in the chromosome of the candidate solution with a certain probability, thereby introducing new mutation factors.

[0097] Iteration and stopping conditions: The above selection, crossover and mutation operations are iterated multiple times, and each generation will produce a new set of candidate solutions. The model correction unit will evaluate the quality of these candidate solutions according to the fitness function and continuously update the population.

[0098] The iteration process will continue until the stopping condition is met. The stopping condition can be that the preset number of iterations is reached, the prediction error of the model is less than a certain threshold, or the fitness of the population has not been significantly improved in consecutive generations.

[0099] Through the above steps, the model correction unit can continuously optimize the dust regulation task simulation model and improve its prediction accuracy and adaptability, thereby providing more reliable support for the decision-making unit and achieving precise control of dust concentration.

[0100] Specifically, in the intelligent dust control system provided by the present invention, the decision generation unit is further used for:

[0101] The decision generation unit receives real-time dust regulation task data from the sensor, inputs the real-time dust regulation task data into the optimized dust regulation task simulation model, and performs real-time simulation calculation. The optimized dust regulation task simulation model predicts the best electric field current setting according to the current load condition and dust concentration parameters;

[0102] After the simulation is completed, the decision generation unit analyzes the simulation results and generates corresponding control instructions based on the simulation results. When the control instructions are generated, the decision generation unit sends the control instructions to the controller of the electrostatic precipitator.

[0103] The decision-making unit first receives real-time dust control task data from sensors. These data include key parameters such as the current load of the power plant, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, temperature, etc. These data are the basis for the decision-making unit to perform subsequent processing and simulation calculations.

[0104] The received real-time dust control task data will be input into the optimized dust control task simulation model. This model is obtained after multiple iterations of optimization by the model correction unit and has high prediction accuracy and adaptability.

[0105] The optimized dust control task simulation model performs real-time simulation calculations based on the input real-time data and the current load conditions, dust concentration parameters, etc. The model takes various factors into consideration and predicts the electric field current setting required to achieve the best dust removal effect under the current conditions.

[0106] After the simulation is completed, the decision-making unit will conduct a detailed analysis of the simulation results, including evaluating whether the predicted electric field current setting is reasonable, whether it can meet the dust concentration control requirements, and whether it will have a positive impact on the operating efficiency and economic benefits of the power plant.

[0107] Based on the analysis of the simulation results, the decision generation unit will generate corresponding control instructions. These instructions are designed to instruct the controller of the electrostatic precipitator on how to adjust the magnitude of the electric field current to achieve precise control of dust concentration. The control instructions will clearly indicate key information such as the electric field that needs to be adjusted, the target current value, and the adjustment time.

[0108] When the control instruction is generated, the decision generation unit will send it to the controller of the electrostatic precipitator. After receiving the instruction, the controller will immediately perform the corresponding operation and adjust the electric field current to the target value, thereby achieving dust concentration control.

[0109] During the execution of the control instructions, the decision generation unit will also continuously monitor the operating status of the electrostatic precipitator and the change in dust concentration. If it is found that the actual operating results deviate from the expected target, the decision generation unit will promptly adjust the control strategy or regenerate the control instructions to effectively control the dust concentration.

[0110] Through the above steps, the decision generation unit can predict the optimal electric field current setting in real time and accurately according to the current load conditions and dust concentration parameters of the power plant, and guide the controller of the electrostatic precipitator to make adjustments by generating corresponding control instructions, thereby achieving precise control of dust concentration and improving the operating efficiency and economic benefits of the power plant.

[0111] The intelligent dust regulation system provided by the present invention solves the problem that the secondary current of the electrostatic precipitator needs to be manually adjusted when the load of the power plant increases or decreases through the following technical solutions:

[0112] The data acquisition unit is responsible for acquiring the operation and maintenance data of the intelligent dust control system, including power plant load data, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, electric field current of the electrostatic precipitator, and flue gas temperature, etc. These data are stored in the database in real time, providing a basis for subsequent data processing and decision-making.

[0113] The data acquisition unit establishes data acquisition channels with various monitoring points of the power plant's electrostatic precipitator, collects data such as dust concentration, flue gas flow, temperature, and electric field current at the inlet and outlet of the power plant's electrostatic precipitator in real time, and performs data integrity checks, outlier detection, and data range verification to improve data accuracy and reliability.

[0114] The data processing unit is responsible for obtaining dust control tasks, extracting data features from the tasks, and obtaining dust control task index data. Then, the corresponding historical data in the database is retrieved based on these index data, and the deep learning model is used for training to obtain a dust control task simulation model. The model can receive real-time dust control tasks and output simulation results. During the execution of the dust control task, the data processing unit will also collect the actual operation data after execution and compare it with the simulation results. If the error range is greater than the preset value, the simulation model will be optimized.

[0115] The model correction unit obtains the data generated by the data processing unit in the process of building and optimizing the dust control task simulation model, and forms a data processing unit operation data set. Then, the dust control task simulation model is optimized based on the genetic algorithm to improve the accuracy and adaptability of the model.

[0116] The decision generation unit uses the optimized dust control task simulation model to process the real-time dust control task data and outputs the real-time simulation results. According to the simulation results, the decision generation unit generates corresponding control instructions and sends them to the controller of the electrostatic precipitator to automatically adjust the size of the electric field current, thereby achieving precise control of dust concentration.

[0117] Through the above technical solution, the intelligent dust regulation system provided by the present invention can automatically adjust the secondary current of the electrostatic precipitator according to the change of the power plant load without manual intervention, thereby solving the problem of manually adjusting the secondary current of the electrostatic precipitator when the load increases or decreases. The present invention not only improves the operating efficiency and dust removal effect of the electrostatic precipitator, but also reduces the operating difficulty of the operator and the consumption rate of the plant electricity, thereby increasing the economic benefits of the power plant.

[0118] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if the modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include the modifications and variations, and the above-described embodiments of the present invention do not constitute a limitation on the scope of protection of the present invention.

Claims

1. Intelligent dust control system, characterized in that, include: A data acquisition unit is used to acquire operation and maintenance data of the intelligent dust control system, the operation and maintenance data of the intelligent dust control system includes power plant load data, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, electric field current of the electrostatic precipitator and flue gas temperature, and stores the acquired operation and maintenance data of the intelligent dust control system in a database; A data acquisition unit is used to collect dust concentration, flue gas flow, temperature, electric field current data and corresponding standard safety parameters at the inlet and outlet of the electric precipitator of the power plant, and store the collected data in a database; a data processing unit for acquiring dust control tasks, extracting data features of dust control tasks, obtaining dust control task index data, retrieving corresponding historical data in a database according to the dust control task index data, obtaining historical data corresponding to the dust control tasks, training using a deep learning model of historical data corresponding to the dust control tasks, obtaining a dust control task simulation model, receiving real-time dust control tasks, substituting the real-time dust control tasks into the dust control task simulation model, obtaining real-time dust control task simulation results, collecting dust concentration, flue gas flow, temperature and electric field current data at the inlet and outlet of the electric precipitator of the power plant during the execution of the dust control task, obtaining the operating data of the electric precipitator of the power plant after the execution of the dust control task, comparing the operating data of the electric precipitator of the power plant after the execution of the dust control task with the simulation results of the real-time dust control task, and optimizing the dust control task simulation model if the error range between the simulation results of the real-time dust control task and the operating data of the electric precipitator of the power plant after the execution of the dust control task is greater than a preset value; A model correction unit is used to obtain data generated in the process of constructing the dust regulation task simulation model in the data processing unit and in the process of data processing of the dust regulation task simulation model, obtain a data processing unit operation data set, and optimize the dust regulation task simulation model using a genetic algorithm based on the data processing unit operation data set to obtain an optimized dust regulation task simulation model; The decision generation unit is used to use the optimized dust control task simulation model to process the data of the real-time dust control task, output the real-time simulation results, and generate corresponding control instructions according to the real-time simulation results. The control instructions are sent to the controller of the electrostatic precipitator. The controller of the electrostatic precipitator automatically adjusts the size of the electric field current according to the control instructions to achieve dust concentration control.

2. The intelligent dust control system according to claim 1, characterized in that: The data acquisition unit is further used for: The data acquisition unit establishes a connection with sensors and data sources of the intelligent dust control system, wherein the sensors include dust concentration monitors for the inlet and outlet of the electrostatic precipitator, a flue gas flow meter, an electric field current monitor for the electrostatic precipitator, and a flue gas temperature sensor; The data acquisition unit sends data requests to various data sources. The data requests include power plant load data, dust concentration at the inlet and outlet of the electrostatic precipitator, flue gas flow, electrostatic precipitator electric field current and flue gas temperature information. After receiving the request, the data source sends the corresponding data to the data acquisition unit in a standardized format.

3. The intelligent dust control system according to claim 1, characterized in that: The data acquisition unit is also used for: The data acquisition unit establishes a data acquisition channel with each monitoring point of the electric precipitator of the power plant. After the data acquisition channel is established, the data acquisition unit collects data such as dust concentration, flue gas flow, temperature and electric field current at the inlet and outlet of the electric precipitator of the power plant in real time; The data collection unit performs data integrity check, outlier detection and data range verification on the collected data to obtain verified data, which will be stored in the database.

4. The intelligent dust control system according to claim 1, characterized in that: The data processing unit is further used for: The data processing unit retrieves the corresponding historical data in the database according to the dust regulation task index data, and the dust regulation task index data includes power plant load data, dust concentration data at the inlet and outlet of the electrostatic precipitator, flue gas flow data and temperature data; The retrieved historical data are preprocessed, and the preprocessed and integrated historical data are used as input of the deep learning model to train the deep learning model and obtain a dust regulation task simulation model; The data processing unit verifies the dust control task simulation model, applies the dust control task simulation model to a portion of historical data that has not participated in training, and compares the difference between the predicted results of the dust control task simulation model and the actual results. If the error range is greater than the preset value, the dust control task simulation model needs to be optimized.

5. The intelligent dust control system according to claim 4, characterized in that: The data processing unit is further used for: The data processing unit receives dust control task requests from power plants or other monitoring systems in real time, performs preliminary analysis on the received tasks, and then extracts data features of the received real-time dust control tasks. The extracted features include dust concentration target value, flue gas flow expectation, temperature requirement, and electric field current setting. The extracted real-time dust control task feature data is used as input and substituted into the pre-trained dust control task simulation model. The simulation result of the real-time dust control task is obtained through calculation by the pre-trained dust control task simulation model. The simulation results of the real-time dust regulation task include the predicted dust concentration, flue gas flow, temperature and electric field current data at the inlet and outlet of the electrostatic precipitator.

6. The intelligent dust control system according to claim 1, characterized in that: The model correction unit is further used for: The data generated by the model correction unit during operation include data for constructing a dust regulation task simulation model, input and output data when the model performs data processing, forming a data processing unit operation data set, and encoding the data in the data processing unit operation data set; Initialize a population containing multiple candidate solutions, where the candidate solutions are parameter configurations of the dust regulation task simulation model. The candidate solutions are randomly generated and encoded as chromosomes of the genetic algorithm. After initializing the population, the model correction unit performs genetic operations including selection, crossover, and mutation to produce the next generation. The genetic operations are iterated multiple times until the stopping condition is met.

7. The intelligent dust control system according to claim 1, characterized in that: The decision making unit is further used for: The decision generation unit receives real-time dust regulation task data from the sensor, inputs the real-time dust regulation task data into the optimized dust regulation task simulation model, and performs real-time simulation calculation. The optimized dust regulation task simulation model predicts the best electric field current setting according to the current load condition and dust concentration parameters; After the simulation is completed, the decision generation unit analyzes the simulation results and generates corresponding control instructions based on the simulation results. When the control instructions are generated, the decision generation unit sends the control instructions to the controller of the electrostatic precipitator.

Images