Unit configuration adjustment method and system based on multi-algorithm optimization

Abstract

The invention discloses a unit configuration adjustment method and system based on multi-algorithm optimization, and belongs to the technical field of power system optimization, and the method specifically comprises the steps: obtaining and preprocessing unit operation data, dividing working condition types, recognizing optimal operation parameters under each working condition, and carrying out the modeling analysis; matching historical optimal working condition parameters in real time by constructing a unit operation knowledge graph, and setting a joint optimization space in combination with constraint conditions; obtaining an optimal parameter combination in the optimization space by using a pre-trained machine learning model and a hybrid optimization algorithm; unit configuration is adjusted, the running state is monitored in real time, and model parameters are optimized according to real-time feedback; according to the invention, the operation efficiency and stability of the unit are improved, and intelligent and adaptive unit configuration adjustment is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system optimization, and in particular to a method and system for adjusting unit configuration based on multi-algorithm optimization. Background Art

[0002] In industrial production, especially in power systems, unit configuration adjustment is a crucial link. With the continuous expansion of the scale and increase in complexity of power systems, the unit configuration adjustment problem has become increasingly important. Unit configuration adjustment methods include traditional optimization methods and intelligent optimization algorithms. Among them, traditional optimization methods mainly use traditional optimization methods such as nonlinear programming, heuristic algorithms and priority methods to solve the unit configuration adjustment problem. Although the problem has been solved to a certain extent, there are problems such as large amount of calculation, slow convergence speed, and easy to fall into local optimality; intelligent optimization algorithms include genetic algorithms, ant colony algorithms, and particle swarm algorithms. They mainly simulate natural evolution or group intelligent behavior to find the optimal solution to the problem. However, although intelligent optimization algorithms have achieved remarkable results in unit configuration adjustment, a single algorithm is often difficult to cope with all complex situations, and there are problems such as slow convergence speed and easy to fall into local optimality.

[0003] For example, the patent with the authorization announcement number CN116632931A discloses a method and system for configuring the network-related control parameters of the unit, including: for the local fault of the unit, the network-related control parameters of the unit are configured through simulation. If the effect after configuration meets the set conditions, the adaptability of the configuration parameters to other key faults of the system is further tested, and the network-related control parameters of the unit are adjusted. If the effect after configuration does not meet the set conditions, the local fault is re-simulated and the parameters are reconfigured. Therefore, this technical solution can optimize the configuration of unit parameters in multiple types of units, consider the unit's own performance and its impact on system performance, and also consider the adaptability of the unit's network-related control parameters to multiple faults, and consider the coordinated configuration of multiple unit control parameters and their impact on the overall performance of the system.

[0004] The above existing technologies all have the following problems: they rely on the simulation environment to simulate the effects of unit failures and parameter configurations, resulting in deviations between the simulation results and the actual situation; they require manual judgment on whether the effects after configuration meet the set conditions and adjust the parameters accordingly; and they lack the ability to monitor and dynamically adjust the unit's operating status in real time. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a unit configuration adjustment method and system based on multi-algorithm optimization, which acquires and preprocesses unit operation data, divides operating conditions into categories, identifies the optimal operating parameters under each operating condition and performs modeling analysis; by constructing a unit operation knowledge graph, the historical optimal operating parameters are matched in real time, and a joint optimization space is set in combination with constraint conditions; the optimal parameter combination is obtained in the optimization space by using a pre-trained machine learning model and a hybrid optimization algorithm; the unit configuration is adjusted, the operating status is monitored in real time, and the model parameters are optimized according to real-time feedback; the present invention improves the unit operation efficiency and stability, and realizes intelligent and adaptive unit configuration adjustment.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A unit configuration adjustment method based on multi-algorithm optimization, comprising:

[0008] Step S1: Acquire the unit operation data and perform preprocessing, and divide the unit operation status into different operating condition categories based on the preprocessed unit operation data;

[0009] Step S2: In each operating condition category, select the optimal operating parameter combination, generate the unit operating optimal operating condition table, and perform modeling analysis on the optimal operating parameters;

[0010] Step S3: Construct a knowledge graph of unit operation, and match the real-time operating parameter values ​​with the nodes in the knowledge graph through a similarity measurement strategy to obtain the historical optimal operating parameters. At the same time, based on the historical optimal operating parameters and combined with the constraints of unit operation, set a joint optimization space;

[0011] Step S4: loading the pre-trained machine learning model, and at the same time, inputting the parameter combination in the joint optimization space into the machine learning model, and obtaining the optimal parameter combination through the hybrid optimization algorithm;

[0012] Step S5: Based on the optimal parameter combination, the unit configuration is adjusted, and the adjusted unit operating status is monitored in real time. At the same time, the machine learning model parameters are optimized according to the real-time feedback information.

[0013] Specifically, the specific steps of step S3 include:

[0014] S3.1: Obtain environmental parameters and historical unit maintenance records, combine the optimal operating condition table and modeling results generated in step S2, and generate a multi-source data set;

[0015] S3.2: Define the entities, relationships and attributes of the knowledge graph, and use graph neural networks and graph embedding methods to automatically extract and construct nodes and edges of the knowledge graph from multi-source data sets to form a dynamic unit operation knowledge graph;

[0016] S3.3: Collect unit operating parameters in real time, measure the similarity between real-time unit operating parameters and nodes in the knowledge graph by integrating fuzzy logic and combining deep learning algorithms, and comprehensively evaluate the similarity between real-time operating conditions and historical optimal operating conditions. ;

[0017] S3.4: According to the similarity results, The corresponding unit operating parameters are taken as the historical optimal operating parameters, where: express The maximum value of

[0018] S3.5: Based on the historical optimal operating parameters and combined with the constraints of unit operation, a multi-objective optimization model is constructed;

[0019] S3.6: Use a multi-objective optimization algorithm to solve the multi-objective optimization model and generate a multi-dimensional parameter adjustment plan. At the same time, according to real-time working condition feedback, dynamically adjust the parameter fluctuation range and step size to form a joint optimization space.

[0020] Specifically, the specific steps of S3.2 include:

[0021] S3.21: Define entities, relationships, and attributes of the knowledge graph and obtain multi-source datasets;

[0022] S3.22: Automatically extract entities from multi-source data using natural language processing methods, and automatically extract relationships between entities from multi-source data using pattern matching methods;

[0023] S3.23: Load the pre-trained graph neural network model and use the graph neural network model to learn the interactions and dependencies between entities and relationships;

[0024] S3.24: Map the nodes and edges in the graph structure data into a low-dimensional vector space through graph embedding methods, and construct the nodes and edges of the knowledge graph based on the embedding vectors generated by the extracted entities, relationships, and graph embedding;

[0025] S3.25: Dynamically update the nodes and edges in the knowledge graph based on the unit operating parameters collected in real time.

[0026] Specifically, the specific steps of S3.3 include:

[0027] S3.31: Use sensors to collect unit operating parameters in real time and load dynamic unit operation knowledge graph;

[0028] S3.32: Fuse the unit operating parameters collected in real time with the data in the knowledge graph to obtain fused data, and convert the fused data set into a fuzzy set using fuzzy logic;

[0029] S3.33: Use the neural network model to extract features from the fused fuzzy data set, perform representation learning on the nodes in the knowledge graph, and convert the nodes into vectors.

[0030] Specifically, the specific steps of S3.3 also include:

[0031] S3.34: Based on the output results of the neural network model and the results of fuzzy logic processing, the similarity between the real-time operating parameters and the nodes in the knowledge graph is measured. The formula is:

[0032] ;

[0033] in, represents the similarity measure, represents the weight on dimension i, represents the value of the real-time operating condition parameter in dimension i, Represents the value of the knowledge graph node on dimension i, represents the exponent of the nonlinear transformation on dimension i, q represents the adjustment factor, and n represents the dimension of the node vector;

[0034] S3.35: based on the similarity measurement result, select N historical operating condition nodes with the highest similarity to the real-time operating condition;

[0035] If the identifier of the historical optimal working condition is in the screening result of the node, the similarity between the real-time working condition and the historical optimal working condition is calculated;

[0036] If the identifier of the historical optimal working condition is not in the screening result of the node, the similarity between the real-time working condition and the historical optimal working condition is comprehensively evaluated by comparing the similarity scores in step S3.34.

[0037] Specifically, the steps of the hybrid optimization algorithm in step S4 include:

[0038] S4.1: Load the pre-trained machine learning model and the parameter range in the joint optimization space in step S3, and randomly generate M parameter combinations in the joint optimization space as initial evaluation points;

[0039] S4.2: Use the prediction performance indicator based on the machine learning model as the objective function, and use the objective function to evaluate each initial evaluation point and record the evaluation results;

[0040] S4.3: training the Bayesian optimization model using the initial evaluation point data and the corresponding objective function value obtained in step S4.2, and calculating the acquisition function using the prediction result of the Bayesian optimization model in each iteration;

[0041] S4.4: Select the next evaluation point according to the value of the acquisition function, evaluate the objective function at the selected evaluation point, and record the result. At the same time, update the Bayesian optimization model according to the new evaluation result;

[0042] S4.5: Set the number of iterations. When the preset number of iterations is reached, stop the iteration and output the optimal parameter combination found in the iteration process and its corresponding objective function value as the final optimization result.

[0043] Specifically, the entities of the knowledge graph in S3.2 refer to units, components, operating conditions, and environmental parameters, and the attributes of the knowledge graph include temperature values, pressure ranges, and maintenance time.

[0044] A unit configuration adjustment system based on multi-algorithm optimization, comprising: a data processing module, a working condition identification module, a matching module, a hybrid optimization module, and a unit adjustment module;

[0045] The data processing module is used to obtain the unit operation data and perform preprocessing;

[0046] The operating condition identification module is used to classify the unit operating status into different operating condition categories according to the preprocessed unit operating data, and identify the optimal operating parameter combination under each operating condition;

[0047] The matching module is used to match the real-time operating condition parameters with the nodes in the constructed unit operation knowledge graph through similarity measurement to obtain the historical optimal operating condition parameters;

[0048] The hybrid optimization module is used to load the pre-trained machine learning model, combine the parameter combination in the joint optimization space, and obtain the optimal parameter combination through the hybrid optimization algorithm;

[0049] The unit adjustment module adjusts the unit configuration based on the optimal parameter combination, monitors the adjusted unit operating status in real time, and optimizes the machine learning model parameters according to real-time feedback information.

[0050] Specifically, the operating condition identification module includes: an operating condition classification unit and an operating condition identification unit;

[0051] The operating condition classification unit is used to classify the unit operating state into different operating conditions using a clustering algorithm;

[0052] The operating condition identification unit selects the optimal operating parameter combination in each operating condition category through an optimization algorithm and generates an optimal operating condition table for the unit.

[0053] Specifically, the matching module includes: a knowledge graph construction unit and a real-time matching unit;

[0054] The knowledge graph construction unit is used to construct a knowledge graph including operating condition characteristics, parameter combinations and effect evaluation information according to the optimal operating parameters;

[0055] The real-time matching unit is used to match the real-time operating parameters with the nodes in the knowledge graph using a similarity measurement strategy to locate the historical optimal operating parameters.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. The present invention proposes a unit configuration adjustment system based on multi-algorithm optimization, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0058] 2. The present invention proposes a unit configuration adjustment method based on multi-algorithm optimization. Through systematic data preprocessing and operating condition division, it realizes the refined management and analysis of the unit operation data, effectively improves the recognition accuracy of the unit operation status, and screens out the optimal operating parameter combination in each operating condition category. It not only provides a scientific guidance basis for the unit operation, but also deepens the understanding of the unit performance through modeling analysis, which helps to optimize the unit's operating strategy, improve operating efficiency, and reduce energy consumption and failure rate.

[0059] 3. The present invention proposes a unit configuration adjustment method based on multi-algorithm optimization, constructs a unit operation knowledge graph and introduces a similarity measurement strategy, realizes the rapid matching of real-time operating conditions with historical optimal operating conditions, and provides an accurate reference for unit adjustment; a joint optimization space is set in combination with the constraints of unit operation, and a pre-trained machine learning model and a hybrid optimization algorithm are used for parameter optimization, which improves the accuracy and efficiency of parameter adjustment, and not only ensures that the unit always operates in the optimal state, but also continuously optimizes the parameters of the machine learning model through real-time feedback information, thereby improving the adaptability and prediction accuracy of the machine learning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of a unit configuration adjustment method based on multi-algorithm optimization according to the present invention;

[0061] Figure 2 This is a principle flow chart of a method for adjusting unit configuration based on multi-algorithm optimization according to the present invention;

[0062] Figure 3 This is a flow chart for realizing the optimal parameter combination of a unit configuration adjustment method based on multi-algorithm optimization according to the present invention;

[0063] Figure 4 This is an architecture diagram of a unit configuration adjustment system based on multi-algorithm optimization according to the present invention. DETAILED DESCRIPTION

[0064] Example 1

[0065] See also Figure 1 and Figure 2 , an embodiment of the present invention provides: a unit configuration adjustment method based on multi-algorithm optimization, comprising the following steps:

[0066] Step S1: Acquire the unit operation data and perform preprocessing, and divide the unit operation status into different operating condition categories based on the preprocessed unit operation data;

[0067] In the present invention, the unit operating status is divided into different operating condition categories by adopting a dynamic clustering analysis strategy, and the dynamic clustering analysis strategy refers to first using a dynamic time warping algorithm for preprocessing, measuring the distance between data, and then using an adaptive clustering analysis method to cluster according to the Euclidean distance results, so as to dynamically divide the unit operating status into different operating condition categories, wherein the operating condition category reflects the operating status of the unit under different operating conditions.

[0068] It should be noted that the unit operation data is a series of information about the unit's working status obtained from the unit operation system, which records the unit's operating status at different time points and is the basis for evaluating unit performance, monitoring operating status, and performing fault diagnosis. The unit operating status refers to the unit's working condition or mode at present or in the past, including normal status, fault status, overload status, low load status and other operating conditions. At the same time, the unit operation data is the basis for analyzing the unit's operating status, and the unit's operating status is identified by analyzing the changing trends and characteristics of the unit's operating data. For example, by monitoring changes in power output, temperature, and pressure parameters, it can be determined whether the unit is in a normal or abnormal state. Therefore, the unit operation data is the basis for analyzing the unit's operating status, and the unit's operating status is the result of operating data analysis and processing.

[0069] Furthermore, the specific steps of step S1 include:

[0070] S1.1: Obtain unit operation data from the unit operation monitoring system, including but not limited to temperature, pressure, flow, and vibration parameters, and perform data cleaning, data transformation, and feature selection on the unit operation data;

[0071] S1.2: Select a hierarchical clustering method based on data characteristics and analysis requirements, and determine the optimal number of clusters, i.e., the number of working condition categories, through the silhouette coefficient;

[0072] S1.3: Use the dynamic time warping algorithm to calculate the Euclidean distance of the pre-processed unit operation data, and use the hierarchical clustering method to cluster the Euclidean distance calculation results, generate clustering results, and evaluate the clustering results to ensure that the clustering effect meets expectations. At the same time, analyze the characteristics of each operating condition category and explain the unit operation status it represents. Among them, the calculation formulas of the hierarchical clustering method and the dynamic time warping algorithm are the existing technical content in this field, and are not the inventive solution of this application, and will not be repeated here;

[0073] S1.4: Apply clustering results to actual scenarios of unit operation optimization and fault diagnosis, collect feedback, and continuously optimize clustering parameters.

[0074] Step S2: In each operating condition category, select the optimal operating parameter combination, generate the unit operating optimal operating condition table, and perform modeling analysis on the optimal operating parameters;

[0075] Furthermore, the specific steps of step S2 include:

[0076] S2.1: For each operating condition category, all unit operating data belonging to the category are screened out from the preprocessed unit operating data to form different parameter combinations;

[0077] S2.2: Set maximizing efficiency, minimizing energy consumption, and improving stability as optimization goals. Calculate the performance index value corresponding to each parameter combination according to the optimization goals. The calculation formula for the performance index value is:

[0078] ;

[0079] in, Represents the comprehensive performance index value, , , represents the weight of the optimization target, E represents the efficiency value under each parameter combination, c represents the total energy consumption under each parameter combination, It represents the maximum value of total energy consumption under each parameter combination, and S represents the stability of each parameter combination;

[0080] S2.3: Filter out the optimal operating parameter combination in each operating condition category according to the performance index value;

[0081] S2.4: Arrange the optimal operating parameter combination in each operating condition category into a table, including the operating condition category identification, the optimal operating parameter combination and its corresponding performance indicator value;

[0082] S2.5: Select a modeling method for the machine learning model for modeling, and use the optimal operating parameters as a training set to train the machine learning model;

[0083] S2.6: Analyze machine learning model results to understand the relationships between parameters and how they affect performance metrics.

[0084] Step S3: Construct a knowledge graph of unit operation, and match the real-time operating parameter values ​​with the nodes in the knowledge graph through a similarity measurement strategy to obtain the historical optimal operating parameters. At the same time, based on the historical optimal operating parameters and combined with the constraints of unit operation, set a joint optimization space;

[0085] Among them, the constraints include: safety thresholds and energy efficiency indicators.

[0086] Step S4: loading the pre-trained machine learning model, and at the same time, inputting the parameter combination in the joint optimization space into the machine learning model, and obtaining the optimal parameter combination through the hybrid optimization algorithm;

[0087] Step S5: Based on the optimal parameter combination, the unit configuration is adjusted, and the adjusted unit operating status is monitored in real time. At the same time, the machine learning model parameters are optimized according to the real-time feedback information.

[0088] Furthermore, the specific steps of step S5 include:

[0089] S5.1: According to the optimal parameter combination obtained by Bayesian optimization, adjust the configuration parameters of the unit, such as temperature, pressure, and flow control parameters, to ensure that the adjustment process is safe and smooth, and avoid unnecessary damage to the unit;

[0090] S5.2: Monitor the unit operation data in real time and pre-process the unit operation data monitored in real time, including cleaning, denoising, and normalization operations, analyze the unit operation status, and identify the characteristics and trends of the unit operation status, such as whether it is in a stable operation state and whether there are signs of abnormality or failure;

[0091] S5.3: Use real-time data to evaluate the accuracy of current machine learning models ,like , then use the Bayesian optimization method to optimize the parameters of the machine learning model according to the real-time feedback information, wherein the calculation process of the Bayesian optimization is the prior art content in this field, is not the inventive solution of the present application, and is not described in detail here;

[0092] S5.4: Redeploy the optimized machine learning model to the monitoring system, continue to collect data and evaluate the model performance, and optimize the model parameters again based on the new evaluation results and feedback information, and repeat this process until the machine learning model is .

[0093] Example 2

[0094] See also Figure 3In this embodiment, the specific steps of step S3 include:

[0095] S3.1: Obtain environmental parameters and historical unit maintenance records, combine the optimal operating condition table and modeling results generated in step S2, and generate a multi-source data set;

[0096] Among them, environmental parameters include temperature, humidity, and air pressure; unit maintenance records include fault type, maintenance time, and replaced parts.

[0097] S3.2: Define the entities, relationships and attributes of the knowledge graph, and use graph neural networks and graph embedding methods to automatically extract and construct nodes and edges of the knowledge graph from multi-source data sets to form a dynamic unit operation knowledge graph;

[0098] The entities of the knowledge graph in S3.2 refer to units, components, operating conditions, and environmental parameters. The attributes of the knowledge graph include temperature values, pressure ranges, and maintenance time. The relationships include inclusion, influence, and cause.

[0099] Exemplarily, there is a containment relationship between the unit and the unit equipment components, and there is a cause relationship between the fault type and the maintenance record.

[0100] S3.3: Collect unit operating parameters in real time, measure the similarity between real-time unit operating parameters and nodes in the knowledge graph by integrating fuzzy logic and combining deep learning algorithms, and comprehensively evaluate the similarity between real-time operating conditions and historical optimal operating conditions. ;

[0101] S3.4: According to the similarity results, The corresponding unit operating parameters are taken as the historical optimal operating parameters, where: express The maximum value of

[0102] S3.5: Based on the historical optimal operating parameters and combined with the constraints of unit operation, a multi-objective optimization model is constructed;

[0103] S3.6: Use a multi-objective optimization algorithm to solve the multi-objective optimization model and generate a multi-dimensional parameter adjustment plan. At the same time, according to real-time working condition feedback, dynamically adjust the parameter fluctuation range and step size to form a joint optimization space.

[0104] The specific steps of S3.2 include:

[0105] S3.21: Define entities, relationships, and attributes of the knowledge graph and obtain multi-source datasets;

[0106] S3.22: Automatically extract entities from multi-source data using natural language processing methods, and automatically extract relationships between entities from multi-source data using pattern matching methods, wherein the calculation formulas of the natural language processing method and the pattern matching method are prior art contents in the art, and are not the inventive solutions of the present application, and are not described in detail here;

[0107] S3.23: Load the pre-trained graph neural network model and use the graph neural network model to learn the interactions and dependencies between entities and relationships;

[0108] Furthermore, the specific steps of S3.23 include:

[0109] (1) Load the pre-trained graph convolutional network model;

[0110] (2) Convert the extracted entities and relationships into graph-structured data, usually by treating entities as nodes and relationships as edges, and constructing the corresponding adjacency matrix or graph object;

[0111] (3) According to the characteristics of the specific task and dataset, configure the graph convolutional network model parameters, including learning rate, number of iterations, number of layers, and hidden layer size;

[0112] (4) Using the trained graph convolutional network model to infer the graph structure data and learn the interactions and dependencies between entities and relationships, wherein the graph convolutional network model updates the representation of each node by aggregating the information of neighboring nodes, thereby capturing the complex relationships between nodes. The reasoning process and result output process of the graph convolutional network model are the prior art content in this field, and are not the inventive solution of this application, and are not described in detail here;

[0113] (5) Output the node representation or relationship prediction results learned by the graph convolutional network model.

[0114] S3.24: Map the nodes and edges in the graph structure data into a low-dimensional vector space through graph embedding methods, and construct the nodes and edges of the knowledge graph based on the embedding vectors generated by the extracted entities, relationships, and graph embedding;

[0115] Furthermore, the specific steps of S3.24 include:

[0116] (1) Collect graph-structured data containing entity and relationship information, clean the data, remove noise and outliers, and extract nodes and edges in the graph;

[0117] (2) Use DeepWalk's graph embedding method to train graph structure data. During the training process, the graph convolutional network model maps the nodes and edges in the graph to a low-dimensional vector space. The training process of DeepWalk's graph embedding method is the prior art content in this field, which is not the inventive solution of this application and is not described in detail here. At the same time, the mapping process of the graph convolutional network model is the prior art content in this field, which is not the inventive solution of this application and is not described in detail here.

[0118] (3) Evaluate the quality of the embedding vector by node classification, and adjust the graph convolutional network model parameters according to the evaluation results, wherein the calculation formula of the node classification method is the prior art content in this field, which is not the inventive solution of this application and is not described in detail here;

[0119] (4) Based on the extracted entities and relationships, and the embedding vectors generated by graph embedding, the nodes and edges of the knowledge graph are constructed, where the embedding vectors are used as the features of the nodes;

[0120] (5) Optimize the constructed knowledge graph, such as removing redundant information, merging similar nodes, and deploying the knowledge graph in actual scenarios.

[0121] S3.25: Dynamically update the nodes and edges in the knowledge graph based on the unit operating parameters collected in real time, including adding new nodes, updating node attributes, and modifying or deleting edge operations.

[0122] The specific steps of S3.3 include:

[0123] S3.31: Use sensors to collect unit operating parameters in real time and load dynamic unit operation knowledge graph;

[0124] Among them, the dynamic unit operation knowledge graph contains the unit's historical operating conditions, operating rules, and constraint information.

[0125] S3.32: Fuse the real-time collected unit operating parameters with the data in the knowledge graph to obtain fused data, and use fuzzy logic to convert the fused data set into a fuzzy set to handle the uncertainty and ambiguity in the data;

[0126] S3.33: Extract features from the fused fuzzy data set using a neural network model, perform representation learning on the nodes in the knowledge graph, and convert the nodes into vectors or points in a high-dimensional space for similarity measurement, wherein the process and steps of feature extraction are prior art content in this field, and are not the inventive solution of the present application, and are not described in detail here;

[0127] S3.34: Based on the output results of the neural network model and the results of fuzzy logic processing, the similarity between the real-time operating parameters and the nodes in the knowledge graph is measured. The formula is:

[0128] ;

[0129] in, represents the similarity measure, Represents the weight on dimension i, which is used to indicate the importance of different dimensions to similarity measurement. represents the value of the real-time operating condition parameter in dimension i, Represents the value of the knowledge graph node on dimension i, Represents the exponent of the nonlinear transformation on dimension i, which is used to adjust the differences in different dimensions The degree of influence, if When , the effect of the difference is linear. If When , the larger difference will be reduced, q represents the adjustment factor, which is used to control the rate of difference accumulation in different dimensions. When , the formula degenerates into the normalized form of weighted Manhattan distance, if The overall difference will be magnified if When , the overall difference will be reduced, n represents the dimension of the node vector;

[0130] S3.35: based on the similarity measurement result, select N historical operating condition nodes with the highest similarity to the real-time operating condition;

[0131] If the identifier of the historical optimal working condition is in the screening result of the node, the similarity between the real-time working condition and the historical optimal working condition is calculated;

[0132] If the identifier of the historical optimal working condition is not in the screening result of the node, the similarity between the real-time working condition and the historical optimal working condition is comprehensively evaluated by comparing the similarity scores in step S3.34.

[0133] The steps of the hybrid optimization algorithm in step S4 include:

[0134] S4.1: Load the pre-trained machine learning model and the parameter range in the joint optimization space in step S3, and randomly generate M parameter combinations in the joint optimization space as initial evaluation points;

[0135] S4.2: Use the prediction performance indicator based on the machine learning model as the objective function, and use the objective function to evaluate each initial evaluation point and record the evaluation results;

[0136] Furthermore, the specific steps of S4.2 include:

[0137] S4.21: Load the pre-trained machine learning model and determine the mapping relationship between the input parameters and output prediction results of the machine learning model;

[0138] S4.22: Select the accuracy metric as the objective function;

[0139] S4.23: For each initial evaluation point, i.e., a set of parameter combinations, use this set of parameters as the input of the machine learning model, run the machine learning model, and obtain the corresponding prediction results;

[0140] S4.24: Calculate the accuracy index based on the prediction results and the true label, and record the prediction performance index value corresponding to each initial evaluation point.

[0141] S4.3: training the Bayesian optimization model using the initial evaluation point data and the corresponding objective function value obtained in step S4.2, and calculating the acquisition function using the prediction result of the Bayesian optimization model in each iteration;

[0142] Furthermore, the specific steps of S4.3 include:

[0143] S4.31: Obtain the initial evaluation point data and the corresponding objective function value, i.e., the accuracy index, from step S4.1;

[0144] S4.32: Select the RBF kernel function to describe the covariance relationship between the parameter combination and the objective function value, and use the initial evaluation point data as training data to initialize the Gaussian process model, including setting the mean function, covariance matrix and noise term of the Gaussian process model;

[0145] S4.33: Using the initial evaluation point data to train the Gaussian process model to learn the mapping relationship between the parameter combination and the objective function value, wherein the training process of the Gaussian process model is the prior art content in this field, is not the inventive solution of the present application, and is not described in detail here;

[0146] S4.34: In each iteration, the current Gaussian process model is used to predict the objective function value of the unevaluated parameter combination, that is, the predicted mean and variance, wherein the prediction process of the Gaussian process model is the prior art content in the art, is not the inventive solution of the present application, and is not described in detail here;

[0147] S4.35: Calculate an EI acquisition function according to the prediction result, wherein the EI acquisition function is used to evaluate the expected benefits of different parameter combinations, and the calculation process of the EI acquisition function is the prior art content in this field, which is not the inventive solution of the present application and is not described in detail here;

[0148] S4.36: Select the parameter combination that maximizes the acquisition function value as the next evaluation point, evaluate the objective function at the selected evaluation point, and record the new evaluation result;

[0149] S4.37: Add the data and objective function value of the new evaluation point to the training data and retrain the Gaussian process model;

[0150] S4.38: Repeat the iterative process of steps S4.34 to S4.37 until a preset number of iterations is reached.

[0151] S4.4: Select the next evaluation point according to the value of the acquisition function, evaluate the objective function at the selected evaluation point, and record the result. At the same time, update the Bayesian optimization model according to the new evaluation result;

[0152] S4.5: Set the number of iterations. When the preset number of iterations is reached, stop the iteration and output the optimal parameter combination found in the iteration process and its corresponding objective function value as the final optimization result.

[0153] Example 3

[0154] See also Figure 4 Another embodiment provided by the present invention is a unit configuration adjustment system based on multi-algorithm optimization, comprising:

[0155] Data processing module, operating condition identification module, matching module, hybrid optimization module, unit adjustment module;

[0156] Data processing module, used to obtain unit operation data and perform preprocessing;

[0157] The operating condition identification module is used to classify the unit operating status into different operating condition categories according to the pre-processed unit operating data, and identify the optimal operating parameter combination under each operating condition;

[0158] A matching module is used to match the real-time operating parameters with the nodes in the constructed unit operation knowledge graph through similarity measurement to obtain the historical optimal operating parameters;

[0159] The hybrid optimization module is used to load the pre-trained machine learning model, combine the parameter combinations in the joint optimization space, and obtain the optimal parameter combination through the hybrid optimization algorithm;

[0160] The unit adjustment module adjusts the unit configuration based on the optimal parameter combination, monitors the operating status of the adjusted unit in real time, and optimizes the machine learning model parameters based on real-time feedback information.

[0161] The working condition identification module includes: a working condition classification unit and a working condition identification unit;

[0162] An operating condition classification unit, used to classify the unit operating status into different operating conditions using a clustering algorithm;

[0163] The operating condition identification unit selects the optimal operating parameter combination in each operating condition category through the optimization algorithm and generates the optimal operating condition table for the unit.

[0164] The matching module includes: knowledge graph construction unit and real-time matching unit;

[0165] A knowledge graph construction unit, used to construct a knowledge graph containing operating condition characteristics, parameter combinations and effect evaluation information according to the optimal operating parameters;

[0166] The real-time matching unit is used to match the real-time operating parameters with the nodes in the knowledge graph using a similarity measurement strategy to quickly locate the historical optimal operating parameters.

[0167] The unit adjustment module includes: configuration adjustment unit, real-time monitoring unit, and model optimization unit;

[0168] A configuration adjustment unit is used to send adjustment instructions to the unit control system according to the optimal parameter combination to achieve automatic adjustment of the unit configuration;

[0169] Real-time monitoring unit, used to monitor the unit operation status in real time through sensors and control systems and collect feedback data;

[0170] The model optimization unit is used to optimize the parameters of the machine learning model using online learning methods based on real-time feedback information and unit operation results, so as to improve the accuracy and adaptability of the machine learning model.

[0171] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

Claims

1. A unit configuration adjustment method based on multi-algorithm optimization, characterized in that: include: Step S1: Acquire the unit operation data and perform preprocessing, and divide the unit operation status into different operating condition categories based on the preprocessed unit operation data; Step S2: In each operating condition category, select the optimal operating parameter combination, generate the unit operating optimal operating condition table, and perform modeling analysis on the optimal operating parameters; Step S3: Construct a knowledge graph of unit operation, and match the real-time operating parameter values ​​with the nodes in the knowledge graph through a similarity measurement strategy to obtain the historical optimal operating parameters. At the same time, based on the historical optimal operating parameters and combined with the constraints of unit operation, set a joint optimization space; Step S4: loading the pre-trained machine learning model, and at the same time, inputting the parameter combination in the joint optimization space into the machine learning model, and obtaining the optimal parameter combination through the hybrid optimization algorithm; Step S5: Based on the optimal parameter combination, the unit configuration is adjusted, and the adjusted unit operating status is monitored in real time. At the same time, the machine learning model parameters are optimized according to the real-time feedback information.

2. A unit configuration adjustment method based on multi-algorithm optimization as claimed in claim 1, characterized in that: The specific steps of step S3 include: S3.1: Obtain environmental parameters and historical unit maintenance records, combine the optimal operating condition table and modeling results generated in step S2, and generate a multi-source data set; S3.2: Define the entities, relationships and attributes of the knowledge graph, and use graph neural networks and graph embedding methods to automatically extract and construct nodes and edges of the knowledge graph from multi-source data sets to form a dynamic unit operation knowledge graph; S3.3: Collect unit operating parameters in real time, measure the similarity between real-time unit operating parameters and nodes in the knowledge graph by integrating fuzzy logic and combining deep learning algorithms, and comprehensively evaluate the similarity between real-time operating conditions and historical optimal operating conditions. ; S3.4: According to the similarity results, The corresponding unit operating parameters are taken as the historical optimal operating parameters, where: express The maximum value of S3.5: Based on the historical optimal operating parameters and combined with the constraints of unit operation, a multi-objective optimization model is constructed; S3.6: Use a multi-objective optimization algorithm to solve the multi-objective optimization model and generate a multi-dimensional parameter adjustment plan. At the same time, according to real-time working condition feedback, dynamically adjust the parameter fluctuation range and step size to form a joint optimization space.

3. A unit configuration adjustment method based on multi-algorithm optimization as claimed in claim 2, characterized in that: The specific steps of S3.2 include: S3.21: Define entities, relationships, and attributes of the knowledge graph and obtain multi-source datasets; S3.22: Automatically extract entities from multi-source data using natural language processing methods, and automatically extract relationships between entities from multi-source data using pattern matching methods; S3.23: Load the pre-trained graph neural network model and use the graph neural network model to learn the interactions and dependencies between entities and relationships; S3.24: Map the nodes and edges in the graph structure data into a low-dimensional vector space through graph embedding methods, and construct the nodes and edges of the knowledge graph based on the embedding vectors generated by the extracted entities, relationships, and graph embedding; S3.25: Dynamically update the nodes and edges in the knowledge graph based on the unit operating parameters collected in real time.

4. A unit configuration adjustment method based on multi-algorithm optimization as claimed in claim 3, characterized in that: The specific steps of S3.3 include: S3.31: Use sensors to collect unit operating parameters in real time and load dynamic unit operation knowledge graph; S3.32: Fuse the unit operating parameters collected in real time with the data in the knowledge graph to obtain fused data, and convert the fused data set into a fuzzy set using fuzzy logic; S3.33: Use the neural network model to extract features from the fused fuzzy data set, perform representation learning on the nodes in the knowledge graph, and convert the nodes into vectors.

5. The unit configuration adjustment method based on multi-algorithm optimization according to claim 4, characterized in that: The specific steps of S3.3 also include: S3.34: Based on the output results of the neural network model and the results of fuzzy logic processing, the similarity between the real-time operating parameters and the nodes in the knowledge graph is measured. The formula is: ； in, represents the similarity measure, represents the weight on dimension i, represents the value of the real-time operating condition parameter in dimension i, Represents the value of the knowledge graph node on dimension i, represents the exponent of the nonlinear transformation on dimension i, q represents the adjustment factor, and n represents the dimension of the node vector; S3.35: based on the similarity measurement result, select N historical operating condition nodes with the highest similarity to the real-time operating condition; If the identifier of the historical optimal working condition is in the screening result of the node, the similarity between the real-time working condition and the historical optimal working condition is calculated; If the identifier of the historical optimal working condition is not in the screening result of the node, the similarity between the real-time working condition and the historical optimal working condition is comprehensively evaluated by comparing the similarity scores in step S3.

34.

6. A unit configuration adjustment method based on multi-algorithm optimization as claimed in claim 5, characterized in that: The steps of the hybrid optimization algorithm in step S4 include: S4.1: Load the pre-trained machine learning model and the parameter range in the joint optimization space in step S3, and randomly generate M parameter combinations in the joint optimization space as initial evaluation points; S4.2: Use the prediction performance indicator based on the machine learning model as the objective function, and use the objective function to evaluate each initial evaluation point and record the evaluation results; S4.3: using the initial evaluation point data obtained in step S4.2 and the corresponding objective function value to train the Bayesian optimization model, and in each iteration, using the prediction results of the Bayesian optimization model to calculate the acquisition function; S4.4: Select the next evaluation point according to the value of the acquisition function, evaluate the objective function at the selected evaluation point, and record the result. At the same time, update the Bayesian optimization model according to the new evaluation result; S4.5: Set the number of iterations. When the preset number of iterations is reached, stop the iteration and output the optimal parameter combination found in the iteration process and its corresponding objective function value as the final optimization result.

7. A unit configuration adjustment method based on multi-algorithm optimization as claimed in claim 6, characterized in that: The entities of the knowledge graph in S3.2 refer to units, components, operating conditions, and environmental parameters, and the attributes of the knowledge graph include temperature values, pressure ranges, and maintenance time.

8. A unit configuration adjustment system based on multi-algorithm optimization, which is used to implement a unit configuration adjustment method based on multi-algorithm optimization as described in any one of claims 1 to 7, characterized in that: include: Data processing module, operating condition identification module, matching module, hybrid optimization module, unit adjustment module; The data processing module is used to obtain the unit operation data and perform preprocessing; The operating condition identification module is used to classify the unit operating status into different operating condition categories according to the preprocessed unit operating data, and identify the optimal operating parameter combination under each operating condition; The matching module is used to match the real-time operating condition parameters with the nodes in the constructed unit operation knowledge graph through similarity measurement to obtain the historical optimal operating condition parameters; The hybrid optimization module is used to load the pre-trained machine learning model, combine the parameter combination in the joint optimization space, and obtain the optimal parameter combination through the hybrid optimization algorithm; The unit adjustment module adjusts the unit configuration based on the optimal parameter combination, monitors the adjusted unit operating status in real time, and optimizes the machine learning model parameters according to real-time feedback information.

9. The unit configuration adjustment system based on multi-algorithm optimization according to claim 8, characterized in that: The working condition identification module includes: a working condition classification unit and a working condition identification unit; The operating condition classification unit is used to classify the unit operating state into different operating conditions using a clustering algorithm; The operating condition identification unit selects the optimal operating parameter combination in each operating condition category through an optimization algorithm and generates an optimal operating condition table for the unit.

10. The unit configuration adjustment system based on multi-algorithm optimization according to claim 9, characterized in that: The matching module includes: a knowledge graph construction unit and a real-time matching unit; The knowledge graph construction unit is used to construct a knowledge graph including operating condition characteristics, parameter combinations and effect evaluation information according to the optimal operating parameters; The real-time matching unit is used to match the real-time operating parameters with the nodes in the knowledge graph using a similarity measurement strategy to locate the historical optimal operating parameters.

Images