Intelligent optimization control method for supercritical thermal power generating unit

Abstract

The invention provides an intelligent optimization control method for a supercritical thermal power generating unit, and relates to the technical field of thermal power generation, and the method comprises the steps: obtaining real-time operation parameters and historical operation parameters of each generator unit in a power plant, and summarizing and outputting initial data; selecting a first model from a model database in combination with the selection instruction, training and optimizing the first model by using the initial data, and outputting a preset analysis model; based on a preset analysis model and in combination with a preset evaluation index, performing optimization analysis on the initial data, and outputting an optimization analysis result; and performing feature extraction on an optimization analysis result, selecting a control strategy and a control method matched with the extracted features from a strategy database by combining a preset feature strategy comparison table, and adjusting operation parameters of each generator set based on the control strategy and the control method. On the basis of guaranteeing the safe operation of the unit and equipment, the intervention of operators on a key system is reduced, the potential of the unit is excavated, and the economical efficiency of the unit is improved.

Description

Technical Field

[0001] The invention relates to the technical field of thermal power generation, and in particular to an intelligent optimization control method for a supercritical thermal power unit. Background Art

[0002] The production process of supercritical thermal power units is complex. As the units run continuously for a long time, the equipment will gradually age and its characteristics will change greatly, causing the performance of the control systems of important parameters such as main steam temperature, steam pressure, and environmental protection to decline, forcing operators to frequently intervene manually, greatly increasing the amount of operations and the pressure of monitoring. Moreover, operators intervene in the control system mostly from the perspective of safe operation of the unit, often ignoring the economic efficiency of the unit. Therefore, units with a long operation time generally have the problem of keeping the set values ​​of key systems such as main steam temperature, steam pressure, and denitrification at a low level to prevent parameters from exceeding the standard. This phenomenon will cause the unit's coal consumption to increase, ammonia slip and urea usage to increase, and even cause the unit's AGC and primary frequency regulation performance to decline, resulting in a decline in the unit's economic efficiency.

[0003] At present, most of the supercritical unit control methods or systems are built using standard modules such as PID, and their parameters cannot be adaptively adjusted as the unit characteristics change. After the unit has been running for a long time, the control performance will deteriorate.

[0004] Therefore, the present invention provides an intelligent optimization control method for a supercritical thermal power unit. Summary of the invention

[0005] The present invention provides an intelligent optimization control method for a supercritical thermal power unit, which can reduce the intervention of operating personnel on key systems and reduce the pressure of monitoring on the panel on the basis of ensuring the safe operation of the unit and equipment, while tapping the potential of the unit and improving the economy of the unit.

[0006] The present invention provides an intelligent optimization control method for a supercritical thermal power unit, comprising:

[0007] Step 1: Obtain the real-time operating parameters and historical operating parameters of each generator set in the power plant, and summarize and output the initial data;

[0008] Step 2: Selecting a first model from a model database in combination with the selection instruction, and using the initial data to train and optimize the first model, and outputting a preset analysis model;

[0009] Step 3: Based on the preset analysis model and in combination with preset evaluation indicators, the initial data is optimized and analyzed, and the optimization analysis results are output;

[0010] Step 4: Extract features from the optimization analysis results, and select control strategies and methods that match the extracted features from the strategy database in combination with a preset feature strategy comparison table, and adjust the operating parameters of each generator set based on the control strategies and control methods.

[0011] Preferably, the obtaining of real-time operating parameters of each generator set in the power plant includes:

[0012] Acquire the user's monitoring requirement information, and select an adapted preset monitoring device from the device database based on the monitoring requirement information;

[0013] Based on the preset monitoring device, the operating parameter data of each generator set is acquired in real time, and the real-time operating parameter data is output in combination with the timestamp corresponding to the operating parameter data.

[0014] Preferably, step 1 further includes:

[0015] Feature extraction is performed on the real-time operation parameter data to construct a first feature set, and corresponding historical operation parameters are matched in a historical database based on the first feature set, and the historical operation parameter data is output.

[0016] Preferably, before the initial data is summarized and outputted, the following steps are included:

[0017] Based on the monitoring requirement information and the first feature set, selecting a matching preprocessing method from a method database;

[0018] The real-time operating parameter data and the historical operating parameter data are preprocessed based on the preprocessing method.

[0019] Preferably, the combining selection instruction selects the first model from the model database, comprising:

[0020] Obtain the manual model selection instructions input by the user and the self-model selection instructions generated by the system, and output the model selection instructions based on the priorities corresponding to the instructions;

[0021] Based on the model selection instruction, a first matching model is selected from a model database.

[0022] Preferably, the training and optimizing the first model using the initial data includes:

[0023] Using a preset data partitioning method to partition the initial data to obtain a training data set, a validation data set, and a test data set;

[0024] The first model is trained and optimized based on the training data set, the validation data set, and the test data set.

[0025] Preferably, step 3 includes:

[0026] Extracting features from the monitoring demand information, and constructing a second feature set based on the extracted features;

[0027] Based on the second feature set and in combination with a preset feature-factor comparison table, corresponding indicator screening factors are obtained, and a screening factor set is constructed;

[0028] In combination with the preset factor-indicator mapping table, a first indicator matching each indicator screening factor in the screening factor set is selected from the indicator database, and an indicator candidate pool is constructed;

[0029] The system obtains the self-selection instructions of indicators generated by the preset algorithm in real time. At the same time, it captures the manual indicator selection instructions input by the preset port in real time, and outputs the indicator selection instruction set in combination with the priority information corresponding to each instruction;

[0030] Based on the indicator selection instruction set, a matching preset evaluation indicator is selected from the indicator candidate pool, and an evaluation indicator set is constructed;

[0031] Input the evaluation index set into a preset analysis model, and adjust and update the configuration of the preset analysis model in combination with a preset adaptive algorithm, and at the same time, output the model format requirement data after the configuration is updated;

[0032] At the same time, obtaining corresponding data format information of all data contained in the initial data, and outputting an initial data format comparison table;

[0033] Selecting a preset format conversion method that matches the model format requirement information and the initial data format comparison table from a method database;

[0034] Based on the model format requirement data and the initial data format comparison table, the initial data is format converted using the preset format conversion method to output the data to be analyzed;

[0035] Combined with the evaluation indicator set, the updated preset analysis model is configured to perform optimization analysis on the data to be analyzed, and an optimization analysis result is output.

[0036] Preferably, step 4 includes:

[0037] Inputting a preset operating threshold condition into the preset analysis model to generate a preset boundary condition;

[0038] Obtaining a self-generated optimization index outputted by a preset analysis model under the preset boundary conditions and an artificial optimization index manually selected, and outputting an optimization index set based on the self-generated optimization index and the artificial optimization index;

[0039] Inputting the initial data into the preset analysis model for predictive analysis to obtain a first prediction result under the variable structure predictive control method and a second prediction result under the generalized predictive control method;

[0040] Based on the optimization index set, the first prediction result and the second prediction result, and in combination with the preset strategy-method formulation process, an intelligent control strategy and an intelligent control method are designed and formulated, and an index-strategy-method comparison table is constructed based on the mapping relationship between the optimization index set, the intelligent control strategy and the intelligent control method;

[0041] Extracting features from the optimization analysis results, and constructing an optimized feature set based on the extracted features;

[0042] Combined with the preset feature-index mapping table, an optimization index matching each feature in the optimization feature set is obtained, and an optimization index set to be executed is output;

[0043] In combination with the indicator-strategy-method comparison table, the intelligent control strategies and intelligent control methods matching the optimization indicators in the optimization indicator set to be executed are obtained, and a list of strategies-methods to be executed is output;

[0044] Based on the intelligent control strategies and intelligent control methods in the list of strategies and methods to be executed, the corresponding operating parameters in each generator set are controlled and adjusted, and process data is generated in real time and fed back to the preset data analysis model.

[0045] The present invention provides an intelligent optimization control method for a supercritical thermal power unit. The present invention realizes intelligent optimization control of the operating parameters of the generator set by acquiring real-time and historical operating parameters, combining model training and optimization, as well as feature extraction and control strategy selection. The present invention can perform intelligent optimization analysis based on real-time and historical data, select the optimal control strategy and method, thereby improving the efficiency of the power plant generator set, reducing emissions, optimizing system operation, and further achieving the goal of energy conservation and emission reduction, and improving the economy and reliability of power plant operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 The present invention provides a flow chart of an intelligent optimization control method for a supercritical thermal power unit. DETAILED DESCRIPTION

[0048] 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 below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0049] like Figure 1 As shown, an embodiment of the present invention provides an intelligent optimization control method for a supercritical thermal power unit, comprising:

[0050] Step 1: Obtain the real-time operating parameters and historical operating parameters of each generator set in the power plant, and summarize and output the initial data;

[0051] Step 2: Select a first model from the model database in combination with the selection instruction, train and optimize the first model using the initial data, and output a preset analysis model;

[0052] Step 3: Based on the preset analysis model and combined with the preset evaluation indicators, the initial data is optimized and analyzed, and the optimization analysis results are output;

[0053] Step 4: Extract features from the optimization analysis results, and select control strategies and methods that match the extracted features from the strategy database in combination with the preset feature strategy comparison table, and adjust the operating parameters of each generator set based on the control strategy and control method.

[0054] In this embodiment, real-time operating parameters: operating parameters of each generator set in the power plant at the current moment, such as temperature, pressure, power, etc.;

[0055] In this embodiment, historical operating parameters: operating parameter data of each generator set in the power plant over a period of time in the past, used for analysis and comparison, for example, load curves and temperature changes of the generator sets in the past week;

[0056] In this embodiment, initial data: data integrated by acquiring real-time operating parameters and historical operating parameters, serving as the starting point for optimization analysis, for example, including information such as real-time load, historical fault records, and generator model;

[0057] In this embodiment, the selection instruction: an instruction or rule for guiding the selection of a suitable model in the model database;

[0058] In this embodiment, the model database: a database storing various models, used to select a suitable model according to the selection instruction;

[0059] In this embodiment, the first model: an initial data model selected from a model database according to a selection instruction, for training and optimization;

[0060] In this embodiment, the preset analysis model: a trained and optimized model for analyzing and predicting the initial data, for example, a neural network model after data training and optimization;

[0061] In this embodiment, the preset evaluation index is used to evaluate the optimization analysis results and help judge the quality of system performance;

[0062] In this embodiment, the optimization analysis results: the results obtained after the optimization of the preset analysis model and evaluation indicators guide the subsequent control decision;

[0063] In this embodiment, the preset feature strategy comparison table: a table containing the comparison relationship between features and strategies, which is preset;

[0064] In this embodiment, the strategy database: a database storing various control strategies and methods;

[0065] In this embodiment, the control strategy and method: the control strategy and method selected according to the feature extraction result is used to adjust the operating parameters of each generator set.

[0066] The implementation principle and beneficial effects of this embodiment: The present invention realizes intelligent optimization control of the operating parameters of the generator set by acquiring real-time and historical operating parameters, combining model training and optimization, as well as feature extraction and control strategy selection. The present invention can perform intelligent optimization analysis based on real-time and historical data, select the optimal control strategy and method, thereby improving the efficiency of the power plant generator set, reducing emissions, optimizing system operation, and further achieving the goal of energy conservation and emission reduction, and improving the economy and reliability of power plant operation.

[0067] An embodiment of the present invention provides an intelligent optimization control method for a supercritical thermal power unit, which obtains real-time operating parameters of each generator unit in a power plant, including:

[0068] Obtaining the user's monitoring demand information, and selecting an adapted preset monitoring device from the device database based on the monitoring demand information;

[0069] Based on the preset monitoring equipment, the operating parameter data of each generator set is obtained in real time, and the real-time operating parameter data is output in combination with the timestamp corresponding to the operating parameter data.

[0070] In this embodiment, monitoring demand information: user demand information on parameters and frequency required for monitoring equipment, for example, the user needs to obtain load, temperature and vibration data of the generator set every minute;

[0071] In this embodiment, the device database: a database storing information of various monitoring devices, used to select an adapted monitoring device, for example, including technical parameters and model information of various sensors and monitoring instruments;

[0072] In this embodiment, the preset monitoring device: an adapted monitoring device selected from a device database according to monitoring requirement information, for example, a temperature sensor and a vibration monitor are selected as the preset monitoring devices;

[0073] In this embodiment, the operating parameter data: the real-time operating parameter data of each generator set, such as load, temperature, vibration, etc. For example, the load of generator set A is 100MW and the temperature is 300°C;

[0074] In this embodiment, the timestamp is used to mark the time point of data collection to ensure the time sequence and accuracy of the data. For example, each data point is accompanied by a timestamp indicating the time of data collection;

[0075] In this embodiment, real-time operating parameter data: operating parameter data of each generator set obtained in real time based on a preset monitoring device, combined with real-time operating parameter data output by a timestamp, for example, load, temperature and vibration data of generator set A obtained every minute, with corresponding timestamp information.

[0076] The implementation principle and beneficial effects of this embodiment: The present invention selects an adaptive monitoring device according to the user's monitoring demand information, obtains the operating parameter data of each generator set in real time, and outputs the real-time operating parameter data in combination with the timestamp information to realize real-time monitoring of the operating status of the generator set in the power plant. By acquiring and monitoring the operating parameter data of the generator set in real time, the present invention can timely discover abnormal conditions, warn of possible faults in advance, help optimize the control strategy, improve the operating efficiency of the power plant, reduce downtime due to faults, and improve equipment reliability and safety. At the same time, it also helps to save energy, reduce costs, and realize the intelligence and optimization of power plant operation.

[0077] An embodiment of the present invention provides an intelligent optimization control method for a supercritical thermal power unit, wherein step 1 further includes:

[0078] Feature extraction is performed on the real-time operation parameter data to construct a first feature set, and based on the first feature set, corresponding historical operation parameters are matched in a historical database to output the historical operation parameter data.

[0079] In this embodiment, the first feature set: a feature set extracted from the real-time operating parameter data, used to describe the operating state of the generator set, for example, including features such as load size, temperature change rate, vibration frequency, etc.;

[0080] In this embodiment, the historical database: a database storing historical operating parameter data, used to store the operating data of the generator set in the past period of time, for example, including the load, temperature, and vibration data of the generator set in the past week;

[0081] In this embodiment, historical operating parameter data: operating parameter data of the generator set recorded in the past period of time, used to compare and analyze the operating conditions in different time periods, for example, the load of generator set A last week was 120MW and the temperature was 280°C.

[0082] The implementation principle and beneficial effects of this embodiment: The present invention extracts features from real-time operating parameter data to construct a first feature set, and then matches the corresponding historical operating parameter data in a historical database to obtain past operating status data for analysis and comparison. The present invention can discover information such as the changing trends and periodic laws of the operation of the generator set through the analysis of historical operating parameter data, help predict possible problems in the future, optimize control strategies, and improve the operating efficiency and reliability of the power plant. At the same time, by combining real-time and historical data for comprehensive analysis, it is helpful to formulate more accurate control plans, reduce the risk of failures, and improve the overall performance and economic benefits of the power plant.

[0083] An intelligent optimization control method for a supercritical thermal power unit provided by an embodiment of the present invention includes, before aggregating and outputting initial data, the following steps:

[0084] Based on the monitoring requirement information and the first feature set, a matching preprocessing method is selected from a method database;

[0085] The real-time operating parameter data and the historical operating parameter data are preprocessed based on the preprocessing method.

[0086] In this embodiment, the method database: a database storing various preprocessing methods, used to select an adaptive preprocessing method according to monitoring demand information and feature sets, for example, including preprocessing methods such as data cleaning, data smoothing, and data normalization;

[0087] In this embodiment, the preprocessing method is a method for preprocessing data, which is intended to extract useful information, reduce noise or adjust data distribution, etc. For example, it may include data smoothing, data dimension reduction, outlier processing and other methods;

[0088] In this embodiment, preprocessing refers to the process of cleaning, converting or adjusting data for subsequent analysis and processing, for example, removing outliers and normalizing real-time operating parameter data, and smoothing historical operating parameter data.

[0089] The implementation principle and beneficial effects of this embodiment: The present invention selects an adaptive preprocessing method in the method database according to the monitoring demand information and the first feature set, and then uses these methods to preprocess the real-time operating parameter data and the historical operating parameter data to ensure data quality and applicability. The present invention processes the data through the preprocessing method, which can reduce the noise and outliers in the data and make the data more accurate and reliable. This helps to improve the accuracy of subsequent data analysis and modeling, optimize the formulation of control strategies, and further improve the operating efficiency and stability of the power plant. Through preprocessing, the data can also be made easier to understand and apply, providing more powerful support for subsequent data processing and decision-making.

[0090] An intelligent optimization control method for a supercritical thermal power unit provided by an embodiment of the present invention selects a first model from a model database in combination with a selection instruction, comprising:

[0091] Obtain the manual model selection instructions input by the user and the self-model selection instructions generated by the system, and output the model selection instructions based on the priorities corresponding to the instructions;

[0092] Based on the model selection instruction, a first matching model is selected from the model database.

[0093] In this embodiment, the manual model selection instruction is an instruction manually input by the user, which is used to guide the system to select a model suitable for the current situation. For example, the user may specify to select a neural network-based model for predicting the load change of the generator set;

[0094] In this embodiment, the model self-selection instruction is an instruction automatically generated by the system according to certain rules or algorithms, which is used to select a model according to data characteristics or requirements. For example, the system may automatically select to use the ARIMA model for load forecasting according to the time series characteristics of the data;

[0095] In this embodiment, the model selection instruction: combines the model manual selection instruction and the model self-selection instruction, and outputs the final model selection instruction according to the priority corresponding to each instruction. For example, if the model manual selection instruction specified by the user has a higher priority than the system self-selection instruction, the system will give priority to the user-specified model.

[0096] The implementation principle and beneficial effects of this embodiment: The present invention outputs the final model selection instruction based on the manual model selection instruction input by the user and the model self-selection instruction generated by the system, combined with the priority of each instruction. Then the first matching model is selected in the model database based on this instruction. By combining the manual selection instruction and the system self-selection instruction, the present invention can fully consider the needs of the user and the intelligent selection of the system, thereby ensuring that the most suitable model for the current situation is selected. In this way, the accuracy and applicability of the model can be improved, the control strategy can be further optimized, and the operating efficiency and performance of the power plant can be improved. At the same time, this method of combining manual and automatic selection can improve the flexibility and intelligence of the system, and bring more convenience and benefits to the management and operation of the power plant.

[0097] An embodiment of the present invention provides an intelligent optimization control method for a supercritical thermal power unit, which uses initial data to train and optimize a first model, including:

[0098] The initial data is divided into a training data set, a validation data set and a test data set using a preset data division method;

[0099] The first model is trained and optimized based on the training data set, the validation data set, and the test data set.

[0100] In this embodiment, the preset data partitioning method refers to a pre-set data set partitioning method for partitioning the initial data into a training data set, a validation data set, and a test data set. This helps to evaluate the performance of the model on different data sets. For example, the common 70%-15%-15% partitioning ratio can be used to divide the data into a training set, a validation set, and a test set;

[0101] In this embodiment, training data set: a data set used to train a model, through which the model learns parameters, for example, including historical operating parameter data and corresponding output results;

[0102] In this embodiment, validation data set: a data set used to adjust model hyperparameters and evaluate model performance. By using the validation data set, overfitting of the model on the training data can be avoided. For example, it is used to adjust the learning rate of the neural network or select the optimal model complexity.

[0103] In this embodiment, the test data set is a data set used to ultimately evaluate the performance of the model. The model is tested on this data set to evaluate its generalization ability. For example, simulating future real-time operating parameter data is used to verify the performance of the model in actual operation.

[0104] Implementation principles and beneficial effects of this embodiment: The present invention divides the initial data set into a training data set, a verification data set and a test data set according to a preset data division method, and then trains and optimizes the first model based on these data sets. The training data is used for model parameter learning, the verification data is used to adjust the model hyperparameters, and the test data is used to finally evaluate the model performance. The present invention can improve the generalization ability and stability of the model by reasonably dividing the data set and using them to train and optimize the model. The training data set is used for model learning, the verification data set is used to adjust the model to avoid overfitting, and the test data set is used to finally evaluate the model performance. This can ensure that the model has good predictive ability and generalization ability in practical applications, and further improve the operating efficiency and control accuracy of the power plant.

[0105] An embodiment of the present invention provides an intelligent optimization control method for a supercritical thermal power unit, wherein step 3 includes:

[0106] Extracting features from the monitoring demand information, and constructing a second feature set based on the extracted features;

[0107] Based on the second feature set and in combination with the preset feature-factor comparison table, corresponding indicator screening factors are obtained, and a screening factor set is constructed;

[0108] Combined with the preset factor-indicator mapping table, the first indicator matching each indicator screening factor in the screening factor set is selected from the indicator database, and an indicator candidate pool is constructed;

[0109] The system obtains the self-selection instructions of indicators generated by the preset algorithm in real time. At the same time, it captures the manual indicator selection instructions input by the preset port in real time, and outputs the indicator selection instruction set in combination with the priority information corresponding to each instruction;

[0110] Based on the indicator selection instruction set, a matching preset evaluation indicator is selected from the indicator candidate pool, and an evaluation indicator set is constructed;

[0111] Input the evaluation indicator set into the preset analysis model, and adjust and update the configuration of the preset analysis model in combination with the preset adaptive algorithm, and at the same time, output the model format requirement data after the configuration update;

[0112] At the same time, the corresponding data format information of all data contained in the initial data is obtained, and an initial data format comparison table is output;

[0113] Selecting a preset format conversion method that matches the model format requirement information and the initial data format comparison table from a method database;

[0114] Based on the model format requirement data and the initial data format comparison table, the initial data is converted into a format using a preset format conversion method, and the data to be analyzed is output;

[0115] Combined with the evaluation indicator set, the updated preset analysis model is configured to optimize the data to be analyzed and output the optimization analysis results.

[0116] In this embodiment, the second feature set: a feature set obtained by extracting features from monitoring demand information, used to construct a basis for evaluation indicators and optimization analysis, for example, extracting features such as the slope of a load curve and frequency changes from real-time operating data of a thermal power unit;

[0117] In this embodiment, the preset feature-factor comparison table: a comparison table including mapping relationships between each feature in the second feature set and the index screening factor, is preset;

[0118] In this embodiment, the indicator screening factor: the characteristic factor obtained according to the preset characteristic-factor comparison table is used for subsequent indicator selection and construction of the evaluation indicator set;

[0119] In this embodiment, the screening factor set: a set consisting of indicator screening factors;

[0120] In this embodiment, the preset factor-indicator mapping table: a table containing the mapping relationship between the indicator screening factors and the evaluation indicators, which is preset;

[0121] In this embodiment, the indicator database: a database containing various indicators in various power generation systems;

[0122] In this embodiment, the first indicator: an evaluation indicator selected from an indicator database;

[0123] In this embodiment, the candidate index pool includes a set of candidate evaluation indexes obtained by matching factors in the screening factor set, for example, indicators such as "load balance" and "frequency stability";

[0124] In this embodiment, preset algorithm: a preset algorithm used to generate an indicator self-selection instruction;

[0125] In this embodiment, the indicator self-selection instruction is an instruction generated by a preset algorithm and used to automatically select an evaluation indicator, for example, an instruction for the system to automatically generate an evaluation indicator based on real-time data characteristics;

[0126] In this embodiment, the preset port is a pre-set interface or channel used for data transmission and interaction between the system and the user. For example, a port is set in the system specifically for receiving user input commands;

[0127] In this embodiment, manual indicator selection instructions: instructions input manually, used to guide the system to select specific indicators or parameters, for example, the user may specify that the system give priority to certain important operating indicators;

[0128] In this embodiment, priority information: information used to indicate the importance or priority order of different instructions or operations, for example, instructions with high priority will be executed first;

[0129] In this embodiment, the indicator selection instruction set: an instruction set generated by the system, including manual indicator selection instructions and self-selection instructions, for selecting specific indicators or factors, for example, a set of instructions generated by the system based on user input and algorithms;

[0130] In this embodiment, the evaluation index set is a set of indicators used to evaluate system performance or results, for example, including indicators such as efficiency and load balance of a power plant;

[0131] In this embodiment, preset adaptive algorithm: a pre-set algorithm used to automatically adjust parameters or configurations according to system status or requirements, for example, the system may automatically adjust the parameters of the control algorithm according to real-time data;

[0132] In this embodiment, configuration adjustment and update: an operation of adjusting and updating the system configuration according to the evaluation results or requirements, for example, adjusting the control strategy according to the evaluation index results;

[0133] In this embodiment, model format requirement data: data in a specific format required by the model, for example, a neural network model may require input of data of a specific dimension and range;

[0134] In this embodiment, data format information: information used to describe the structure and type of data, for example, whether the data is time series data or classification data;

[0135] In this embodiment, the initial data format comparison table: a table recording the correspondence between the format information of the initial data and the format information required by the model;

[0136] In this embodiment, the preset format conversion method: a pre-set method for converting initial data into the format required by the model, for example, converting time series data into a matrix format;

[0137] In this embodiment, the data to be analyzed refers to data prepared for analysis after format conversion, for example, data processed by a preset format conversion method.

[0138] The implementation principle and beneficial effects of this embodiment: The present invention constructs an evaluation index set through the steps of feature extraction, factor selection, index matching, etc., and uses a preset analysis model and an adaptive algorithm to adjust and update the configuration, thereby optimizing the analysis of the data to be analyzed. The present invention can better meet user needs and automatically adapt to system status by combining manual and automatic instruction selection. At the same time, through format conversion and data optimization analysis, the accuracy of the analysis results and the intelligence of the system can be improved, the operating efficiency and control accuracy of the power plant can be further optimized, and the system can be helped to more effectively cope with complex control requirements and data processing, thereby improving the overall performance and efficiency of the system.

[0139] An embodiment of the present invention provides an intelligent optimization control method for a supercritical thermal power unit, wherein step 4 includes:

[0140] Inputting the preset operating threshold conditions into the preset analysis model to generate preset boundary conditions;

[0141] Obtaining a self-generated optimization index outputted by a preset analysis model under preset boundary conditions and an artificial optimization index manually selected, and outputting an optimization index set based on the self-generated optimization index and the artificial optimization index;

[0142] Inputting the initial data into a preset analysis model for predictive analysis, obtaining a first prediction result under a variable structure predictive control method and a second prediction result under a generalized predictive control method;

[0143] Based on the optimization index set, the first prediction result and the second prediction result, and in combination with the preset strategy-method formulation process, an intelligent control strategy and an intelligent control method are designed and formulated, and an index-strategy-method comparison table is constructed based on the mapping relationship between the optimization index set, the intelligent control strategy and the intelligent control method;

[0144] Extract features from the optimization analysis results, and construct an optimized feature set based on the extracted features;

[0145] Combined with the preset feature-index mapping table, obtain the optimization index that matches each feature in the optimization feature set, and output the optimization index set to be executed;

[0146] Combined with the index-strategy-method comparison table, obtain the intelligent control strategies and intelligent control methods that match the optimization indicators in the optimization index set to be executed, and output the list of strategies-methods to be executed;

[0147] Based on the intelligent control strategies and intelligent control methods in the list of strategies and methods to be executed, the corresponding operating parameters in each generator set are controlled and adjusted, and process data is generated in real time and fed back to the preset data analysis model.

[0148] In this embodiment, preset operating threshold conditions: pre-set conditions used to guide the operating threshold of the system under specific circumstances, for example, setting the generator load rate not to exceed 90%;

[0149] In this embodiment, preset boundary conditions: conditions generated according to preset operation threshold conditions, used to define the boundary of system operation, for example, boundary conditions set according to load rate;

[0150] In this embodiment, the self-generated optimization index: an index for optimization that is automatically generated by the preset analysis model output, for example, an efficiency index generated by the system based on data;

[0151] In this embodiment, the manual optimization index is an index manually selected for optimization, for example, a key performance index selected by an operator based on experience;

[0152] In this embodiment, the optimization index set includes a set of self-generated optimization indexes and manual optimization indexes, for example, including efficiency, load balance and other indexes;

[0153] In this embodiment, the variable structure predictive control method is a model-based control method that uses a system model in each control cycle to predict the system behavior for a period of time in the future and optimizes the control input to achieve optimization of system performance, for example, dynamically adjusting the control strategy according to real-time data;

[0154] In this embodiment, the first prediction result: the first prediction result obtained under the variable structure predictive control method, for example, predicting the load change in the next hour;

[0155] In this embodiment, the generalized predictive control method is a prediction-based control method that uses a system model to predict the system response for a period of time in the future and adjusts the control input according to these prediction results to achieve optimal control of the system, for example, using a recursive algorithm for real-time calculation and prediction;

[0156] In this embodiment, the second prediction result: the second prediction result obtained under the generalized predictive control method, for example, predicting the power grid load demand for the next day;

[0157] In this embodiment, the preset strategy-method formulation process: specifies the process of formulating intelligent control strategies and methods, for example, including steps such as determining optimization objectives, selecting control strategies, and formulating control methods;

[0158] In this embodiment, intelligent control strategy and intelligent control method: strategies and methods for optimizing control system performance, the strategy specifies the overall direction of control, and the method specifies the specific control means and algorithms;

[0159] In this embodiment, the indicator-strategy-method comparison table: a table recording the mapping relationship between the optimization indicators, the intelligent control strategies and the intelligent control methods, for example, specifying that a specific control strategy and control method are used under certain optimization indicators;

[0160] In this embodiment, the optimization feature set is a feature set extracted from the optimization analysis results, which is used to guide the selection of optimization indicators. These features can reflect the performance, status or other important information of the system;

[0161] In this embodiment, the preset feature-index mapping table: a table containing the mapping relationship between each feature in the optimization feature set and the optimization index, which is used to select the matching optimization index according to the optimization feature set;

[0162] In this embodiment, the set of optimization indicators to be executed is: a set of indicators to be optimized determined according to the optimization feature set and the mapping table, and these indicators will be used to determine the intelligent control strategy and the intelligent control method;

[0163] In this embodiment, the list of strategies and methods to be executed: a list of intelligent control strategies and methods to be executed determined according to the indicator-strategy-method comparison table, which strategies and methods will be applied to the system for real-time control;

[0164] In this embodiment, process data refers to real-time data generated during the control process, which is used to feed back into a preset data analysis model for further analysis and adjustment.

[0165] The implementation principle and beneficial effects of this embodiment: The present invention generates preset boundary conditions according to preset operating threshold conditions, and then generates an optimization index set according to automatically generated and manually selected optimization indicators. Next, the results obtained by the predictive analysis and the optimization index set are used to formulate intelligent control strategies and methods, and an indicator-strategy-method comparison table is constructed. Finally, features are extracted according to the optimization analysis results, an optimization feature set is generated, corresponding optimization indicators are selected, and intelligent control strategies and methods are executed. By combining automatically generated and manually selected indicators, the system of the present invention can more comprehensively evaluate system performance and formulate intelligent control strategies and methods based on the prediction results. This method can help the system adjust operating parameters more accurately, improve the stability and efficiency of the system, and further optimize the operation and control effects of the power plant. At the same time, by establishing an indicator-strategy-method comparison table, the system can be made more intelligent and adaptive, and the overall performance and resilience of the system can be improved.

[0166] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent optimization control method for a supercritical thermal power unit, characterized in that: include: Step 1: Obtain the real-time operating parameters and historical operating parameters of each generator set in the power plant, and summarize and output the initial data; Step 2: Selecting a first model from a model database in combination with the selection instruction, and using the initial data to train and optimize the first model, and outputting a preset analysis model; Step 3: Based on the preset analysis model and in combination with preset evaluation indicators, the initial data is optimized and analyzed, and the optimization analysis results are output; Step 4: Extract features from the optimization analysis results, and select control strategies and methods that match the extracted features from the strategy database in combination with a preset feature strategy comparison table, and adjust the operating parameters of each generator set based on the control strategies and control methods.

2. The intelligent optimization control method for a supercritical thermal power unit according to claim 1, characterized in that: The obtaining of real-time operating parameters of each generator set in the power plant includes: Acquire the user's monitoring requirement information, and select an adapted preset monitoring device from the device database based on the monitoring requirement information; Based on the preset monitoring device, the operating parameter data of each generator set is acquired in real time, and the real-time operating parameter data is output in combination with the timestamp corresponding to the operating parameter data.

3. The intelligent optimization control method for a supercritical thermal power unit according to claim 2, characterized in that: Step 1 also includes: Feature extraction is performed on the real-time operation parameter data to construct a first feature set, and corresponding historical operation parameters are matched in a historical database based on the first feature set, and the historical operation parameter data is output.

4. The intelligent optimization control method for a supercritical thermal power unit according to claim 3 is characterized in that: Before the initial data is outputted, the following steps are included: Based on the monitoring requirement information and the first feature set, selecting a matching preprocessing method from a method database; The real-time operating parameter data and the historical operating parameter data are preprocessed based on the preprocessing method.

5. The intelligent optimization control method for a supercritical thermal power unit according to claim 1, characterized in that: The combining selection instruction selects a first model from a model database, comprising: Obtain the manual model selection instructions input by the user and the self-model selection instructions generated by the system, and output the model selection instructions based on the priorities corresponding to the instructions; Based on the model selection instruction, a first matching model is selected from a model database.

6. The intelligent optimization control method for a supercritical thermal power unit according to claim 1, characterized in that: The using the initial data to train and optimize the first model includes: Using a preset data partitioning method to partition the initial data to obtain a training data set, a validation data set, and a test data set; The first model is trained and optimized based on the training data set, the validation data set, and the test data set.

7. The intelligent optimization control method for a supercritical thermal power unit according to claim 2, characterized in that: Step 3 includes: Extracting features from the monitoring demand information, and constructing a second feature set based on the extracted features; Based on the second feature set and in combination with a preset feature-factor comparison table, corresponding indicator screening factors are obtained, and a screening factor set is constructed; In combination with the preset factor-indicator mapping table, a first indicator matching each indicator screening factor in the screening factor set is selected from the indicator database, and an indicator candidate pool is constructed; The system obtains the self-selection instructions of indicators generated by the preset algorithm in real time. At the same time, it captures the manual indicator selection instructions input by the preset port in real time, and outputs the indicator selection instruction set in combination with the priority information corresponding to each instruction; Based on the indicator selection instruction set, a matching preset evaluation indicator is selected from the indicator candidate pool, and an evaluation indicator set is constructed; Input the evaluation index set into a preset analysis model, and adjust and update the configuration of the preset analysis model in combination with a preset adaptive algorithm, and at the same time, output the model format requirement data after the configuration is updated; At the same time, obtaining corresponding data format information of all data contained in the initial data, and outputting an initial data format comparison table; Selecting a preset format conversion method that matches the model format requirement information and the initial data format comparison table from a method database; Based on the model format requirement data and the initial data format comparison table, the initial data is format converted using the preset format conversion method to output the data to be analyzed; Combined with the evaluation indicator set, the updated preset analysis model is configured to perform optimization analysis on the data to be analyzed, and an optimization analysis result is output.

8. The intelligent optimization control method for a supercritical thermal power unit according to claim 1, characterized in that: Step 4 includes: Inputting a preset operating threshold condition into the preset analysis model to generate a preset boundary condition; Obtaining a self-generated optimization index outputted by a preset analysis model under the preset boundary conditions and an artificial optimization index manually selected, and outputting an optimization index set based on the self-generated optimization index and the artificial optimization index; Inputting the initial data into the preset analysis model for predictive analysis to obtain a first prediction result under the variable structure predictive control method and a second prediction result under the generalized predictive control method; Based on the optimization index set, the first prediction result and the second prediction result, and in combination with the preset strategy-method formulation process, an intelligent control strategy and an intelligent control method are designed and formulated, and an index-strategy-method comparison table is constructed based on the mapping relationship between the optimization index set, the intelligent control strategy and the intelligent control method; Extracting features from the optimization analysis results, and constructing an optimized feature set based on the extracted features; Combined with the preset feature-index mapping table, an optimization index matching each feature in the optimization feature set is obtained, and an optimization index set to be executed is output; In combination with the indicator-strategy-method comparison table, the intelligent control strategies and intelligent control methods matching the optimization indicators in the optimization indicator set to be executed are obtained, and a list of strategies-methods to be executed is output; Based on the intelligent control strategies and intelligent control methods in the list of strategies and methods to be executed, the corresponding operating parameters in each generator set are controlled and adjusted, and process data is generated in real time and fed back to the preset data analysis model.

Images