Power plant relay protection setting value optimization method and system based on optimization algorithm

Abstract

The invention relates to the technical field of relay protection constant value optimization, in particular to a power plant relay protection constant value optimization method and system based on an optimization algorithm. The method comprises the steps of obtaining time sequence operation data and historical fault data of a power plant; performing data preprocessing on the acquired data; performing feature extraction and fusion on the preprocessed data, and performing multi-scale feature extraction and prediction on the fused data to obtain an initial relay protection constant value; optimizing the initial relay protection constant value by using a taboo particle swarm algorithm to obtain an optimized relay protection constant value; according to the method, the optimal constant value combination can be more comprehensively searched in the complex solution space, so that the optimized constant value can better adapt to complex and changeable operation conditions of the power system, for example, reliable action can be realized under different load levels, fault types and system topological structures.

Description

Technical Field

[0001] The present invention relates to the technical field of relay protection setting optimization, and in particular to a method and system for optimizing relay protection setting of a power plant based on an optimization algorithm. Background Art

[0002] In the operation of modern power plants, the relay protection system plays a vital role, and the rationality of its setting is directly related to the safe and stable operation of the power system. With the continuous expansion of the power system scale, the increasingly complex operation mode and the influence of new energy access, the traditional relay protection setting method can no longer meet the current needs.

[0003] On the one hand, the time series operation data and historical fault data generated during the operation of the power plant are massive, high-dimensional, complex and changeable. These data contain rich system operation status information, but are also mixed with a lot of noise and abnormal values. Without effective processing and analysis, it is difficult to extract valuable features and rules for the setting of relay protection settings.

[0004] On the other hand, the dynamic characteristics of the power system require that the relay protection setting can be adaptively adjusted according to different operating conditions and fault conditions. However, the traditional setting calculation method is often based on fixed models and parameters, lacking adaptability and flexibility to real-time changes in the system, resulting in protection misoperation or refusal to operate under certain complex conditions, seriously affecting the reliability and stability of the power system.

[0005] In addition, the existing optimization algorithms have the defects of slow convergence speed and easy to fall into local optimal solution when dealing with the optimization problem of relay protection setting value, and cannot efficiently search for the global optimal setting value combination. At the same time, there is a lack of comprehensive, accurate and intelligent means for the evaluation of setting values, making it difficult to ensure that the optimized setting values ​​can meet the protection performance requirements in various actual operation scenarios.

[0006] Therefore, in order to improve the accuracy, adaptability and reliability of relay protection settings in power plants, there is an urgent need for a relay protection setting optimization method and system that can fully mine and utilize operating data and combine advanced optimization algorithms and intelligent evaluation technologies. Summary of the invention

[0007] In order to solve the above-mentioned problems, the present invention provides a method and system for optimizing relay protection settings of a power plant based on an optimization algorithm.

[0008] In the first aspect, the present invention provides a power plant relay protection setting optimization method based on an optimization algorithm, which adopts the following technical solution:

[0009] A power plant relay protection setting optimization method based on an optimization algorithm, comprising:

[0010] Obtaining power plant timing operation data and historical fault data;

[0011] Perform data preprocessing on the acquired data;

[0012] Perform feature extraction and fusion on the preprocessed data, and perform multi-scale feature extraction and prediction on the fused data to obtain the initial relay protection setting;

[0013] The initial relay protection setting is optimized by using the taboo particle swarm algorithm to obtain the optimized relay protection setting.

[0014] The optimized relay protection settings are evaluated using a deep belief network;

[0015] Output the optimization results that are qualified for evaluation.

[0016] Furthermore, the acquired data is preprocessed, including data cleaning and standardization; wherein data cleaning includes removing noise and outliers, and eliminating abnormal data points with high deviation from the mean, wherein the cleaning conditions are set as follows:

[0017]

[0018] Among them, μ i and σ i are the mean and standard deviation calculated for the i-th data source in the historical time window:

[0019]

[0020] Among them, T is the historical time window.

[0021] Furthermore, the preprocessed data is subjected to feature extraction and fusion, including extracting spatial features from the standardized features through CNN, and using GCN to combine the spatiotemporal association of multimodal data to generate a fused feature vector Z t :

[0022] Z t =GCN(F t ,A)

[0023] where F t =Conv2D(X t ,W)+b is the convolution feature of each data source, X t is the input matrix of the time step t of the multimodal data, consisting of multiple W is the convolution kernel weight matrix, b is the bias term, and A is the adjacency matrix, which represents the spatiotemporal correlation between different features and has a dimension of N×N.

[0024] Furthermore, the fused data is subjected to multi-scale feature extraction and prediction, including the spatiotemporal fusion feature Z t Perform multi-scale convolution operations, using convolution kernels of different sizes W k Extract features, convolution result H k Represents the characteristics of the kth time scale:

[0025] H k =Conv1D(Z t ,W k )

[0026] Among them, H k is the convolution feature matrix of time scale k, W k is the weight of the kth convolution kernel, controlling the feature extraction of different time ranges. k Use a gating mechanism to control the flow of information, expressed as:

[0027]

[0028] Among them, g k is the gate value, which indicates the importance weight of the feature and is generated by the Sigmoid activation function σ; is the gating unit weight matrix, which represents the learning parameters of the current time scale feature. is the bias term of the gating unit, which is used to adjust the output value. is the activation feature matrix after gating processing.

[0029] Furthermore, the multi-scale feature extraction and prediction of the fused data also includes the activation features at different time scales. Perform weighted fusion to generate the final prediction result

[0030]

[0031] in, is the final prediction output, which is used to represent the relay protection parameters in a certain period of time in the future. k is the weight of the kth time scale, which is determined through model training and is used to balance the contribution of features at different time scales.

[0032] Furthermore, the initial relay protection constant is optimized by using the taboo particle swarm algorithm to obtain the optimized relay protection constant, including initializing the particle swarm and the taboo table based on the initial relay protection constant, updating the individual optimum and the global optimum of the particles based on the fitness function and updating the particle speed and position, performing taboo processing on the new position of the particle based on the taboo table, and obtaining the optimized relay protection constant through updating and iteration.

[0033] Furthermore, the use of a deep belief network to evaluate the optimized relay protection settings includes optimizing the deep belief network structure using random search, and training each layer of the deep belief network structure using restricted Boltzmann machines, wherein the training step size and learning rate are dynamically adjusted through an improved contrast divergence algorithm to accelerate convergence, and a dynamic adjustment mechanism for the evaluation threshold is established based on statistical analysis of power plant data, and qualified relay protection settings are evaluated through relay protection setting evaluation outputs.

[0034] In the second aspect, a power plant relay protection setting optimization system based on an optimization algorithm comprises:

[0035] The data acquisition module is configured to acquire the sequential operation data and historical fault data of the power plant;

[0036] The preprocessing module is configured to perform data preprocessing on the acquired data;

[0037] The feature module is configured to extract and fuse features of the preprocessed data, and extract and predict multi-scale features of the fused data to obtain an initial relay protection setting;

[0038] The optimization module is configured to optimize the initial relay protection setting value by using a taboo particle swarm algorithm to obtain an optimized relay protection setting value;

[0039] An evaluation module is configured to evaluate the optimized relay protection setting using a deep belief network;

[0040] The output module is configured to output the optimization result that is evaluated as qualified.

[0041] In a third aspect, the present invention provides a computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device, for a method for optimizing relay protection settings of a power plant based on an optimization algorithm.

[0042] In a fourth aspect, the present invention provides a terminal device comprising a processor and a computer-readable storage medium, wherein the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, wherein the instructions are suitable for being loaded by the processor and executing the method for optimizing relay protection settings of a power plant based on an optimization algorithm.

[0043] In summary, the present invention has the following beneficial technical effects:

[0044] 1. The present invention can more accurately reflect the real operating status of the system and provide a reliable basis for subsequent constant value calculation by comprehensively collecting and finely preprocessing the power plant's sequential operation data and historical fault data, removing noise and abnormal values. At the same time, the initial relay protection constant is optimized based on the taboo particle swarm algorithm. The algorithm introduces a taboo search mechanism based on the traditional particle swarm algorithm, which effectively avoids the problem of falling into the local optimal solution. It can more comprehensively search for the optimal constant combination in the complex solution space, so that the optimized constant can better adapt to the complex and changeable operating conditions of the power system, such as reliable operation under different load levels, fault types and system topology structures.

[0045] 2. CNN is used to extract spatial features and GCN is used to combine spatiotemporal correlation to generate fused feature vectors, as well as multi-scale feature extraction and prediction technology to fully explore the multi-dimensional information in the data. Compared with traditional single-scale or simple feature extraction methods, it can more accurately capture the subtle changes in the power system under different operating conditions, thereby obtaining a more accurate initial relay protection setting and reducing the setting error caused by insufficient feature extraction.

[0046] 3. In the process of multi-scale feature extraction and prediction, by weighted fusion of features at different time scales and determining the weight of each scale based on model training, the generated relay protection setting can comprehensively consider the short-term and long-term system operation trends, further enhancing the adaptability of the setting to dynamic changes in the system, ensuring timely and accurate response to faults under various operating conditions.

[0047] 4. The optimized relay protection settings are evaluated using a deep belief network, and the network structure is optimized using random search. This method can automatically learn the complex mapping relationship between the settings and the system operating status. Compared with traditional evaluation methods based on fixed rules or simple experience, it has stronger generalization ability and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of a method for optimizing relay protection settings of a power plant based on an optimization algorithm according to Example 1 of the present invention. DETAILED DESCRIPTION

[0049] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0050] Example 1

[0051] Reference Figure 1 , a power plant relay protection setting optimization method based on an optimization algorithm in this embodiment includes:

[0052] Obtaining power plant timing operation data and historical fault data;

[0053] Perform data preprocessing on the acquired data;

[0054] Perform feature extraction and fusion on the preprocessed data, and perform multi-scale feature extraction and prediction on the fused data to obtain the initial relay protection setting;

[0055] The initial relay protection setting is optimized by using the taboo particle swarm algorithm to obtain the optimized relay protection setting.

[0056] The optimized relay protection settings are evaluated using a deep belief network;

[0057] Output the optimization results that are qualified for evaluation.

[0058] Specifically:

[0059] S1. Collect various data related to relay protection from the power plant's monitoring system, historical operation data, and power equipment parameter database, including line current, voltage, power, equipment rated parameters, fault records, etc.

[0060] Multimodal data collected from different sources can be defined as D = {d1, d2, ..., d N}, where: d i Represents the original time series data collected by the i-th data source. Each data source d i The time series data is represented as: in, is the jth eigenvalue collected at time t. All collected data D are stored in the time series database for further processing.

[0061] S2. Data preprocessing and fusion

[0062] Before data fusion, the raw data is first cleaned, standardized, and feature extracted to ensure data quality and consistency.

[0063] Data cleaning: remove noise and outliers, and remove abnormal data points that deviate greatly from the mean. Set the cleaning conditions as follows:

[0064]

[0065] Among them, μ i and σ i are the mean and standard deviation calculated for the i-th data source in the historical time window:

[0066]

[0067] Among them, T is the historical time window.

[0068] Standardization: Map the values ​​of each data source to a unified dimension, that is, the cleaned data Normalize the data to the range [0,1].

[0069]

[0070] in, and are the minimum and maximum values ​​of the time window.

[0071] Feature extraction and fusion: The standardized features are used to extract spatial features through CNN, and GCN is used to combine the spatiotemporal correlation of multimodal data to generate a fused feature vector Z t :

[0072] Z t =GCN(F t ,A)

[0073] where F t =Conv2D(X t ,W)+b is the convolution feature of each data source, X t is the input matrix of the time step t of the multimodal data, consisting of multiple W is the convolution kernel weight matrix, b is the bias term. A is the adjacency matrix, which represents the spatiotemporal correlation between different features and has a dimension of N×N.

[0074] S3. Multi-scale feature extraction and intelligent prediction

[0075] This module is responsible for fusing the spatiotemporal features Z t The multi-scale dynamic features are extracted from the model and the relay protection setting is predicted with high accuracy. The multi-scale gated Tanh unit (M-GTU) is introduced to enhance the model's ability to capture features of different time scales.

[0076] Multi-scale feature extraction: spatiotemporal fusion feature Z t Perform multi-scale convolution operations, using convolution kernels of different sizes W k Extract features. Convolution result H k Represents the characteristics of the kth time scale:

[0077] H k =Conv1D(Z t ,W k )

[0078] Among them, H k is the convolution feature matrix of time scale k, W k is the weight of the kth convolution kernel, which controls the feature extraction of different time ranges.

[0079] Gating processing mechanism: for each time scale feature H k Use a gating mechanism to control the flow of information. The calculation formula is:

[0080]

[0081] Among them, g k is the gate value, which represents the importance weight of the feature and is generated by the Sigmoid activation function σ. is the gating unit weight matrix, which represents the learning parameters of the current time scale feature. is the bias term of the gating unit, which is used to adjust the output value. is the activation feature matrix after gating processing.

[0082] Multi-scale feature fusion and prediction: Activation features at different time scales Perform weighted fusion to generate the final prediction result

[0083]

[0084] in, It is the final prediction output, used to indicate the preliminary relay protection setting. k is the weight of the kth time scale, which is determined through model training and is used to balance the contribution of features at different time scales.

[0085] S4. Determine the size of the particle swarm: According to the complexity of the problem and the computing resources, determine the number of particles n in the particle swarm, which is generally between 20 and 100.

[0086] Set the position and speed range: According to the actual value range of the relay protection setting, set the upper and lower limits of the particle position xi and speed vi to ensure that the particles search within a reasonable range.

[0087] Initialize the taboo table: create an empty taboo table TabuList to record the solutions that have been visited, and set the taboo length TL, which is the maximum number of solutions recorded in the taboo table.

[0088] Determine the termination condition of the algorithm: You can set the maximum number of iterations MaxIter or reach a certain accuracy requirement as the termination condition of the algorithm.

[0089] Generate initial particle swarm

[0090] The initial position Xi of particles is randomly generated within the set position range, and the position of each particle represents a set of relay protection settings.

[0091] Randomly initialize the particle's velocity Vi, which determines the particle's moving direction and step size in the search space.

[0092] Calculate the fitness function

[0093] Define the fitness function f(x) to evaluate the quality of each set of relay protection settings. Usually, the fitness function can be constructed based on the performance indicators of relay protection, such as the accuracy, rapidity, and reliability of protection actions.

[0094] For each particle i, calculate the fitness value f(xi) corresponding to its current position xi.

[0095] Update the individual optimum and global optimum of particles

[0096] Individual optimal update: For each particle i, compare the fitness value f(xi) of its current position with the fitness value f(pi) of the individual historical optimal position pi. If f(xi) < f(pi), update the individual optimal position pi = xi.

[0097] Global optimal update: Among the individual optimal positions of all particles, find the position with the minimum (or maximum, depending on the optimization goal) fitness value as the global optimal position g.

[0098] Iterative process of taboo particle swarm algorithm

[0099] Update speed and position: Update the particle's speed vi and position xi according to the basic formula of the particle swarm algorithm:

[0100] v i (t+1)=ωv i (t)+c1r1(p i ―x i (t))+c2r2(g―x i (t))

[0101] x i (t+1)=x i (t)+v i (t+1)

[0102] Among them, w is the inertia weight, C1 and C2 are learning factors, r1 and r2 are random numbers between 0 and 1, and t is the number of iterations.

[0103] After updating the particle position, the newly generated position is tabooed. Check whether the new position xi(t+1) is in the taboo table TabuList. If it is in the taboo table, adjust it according to a certain strategy, such as randomly generating a new position or fine-tuning the current position within a certain range until a feasible position that is not in the taboo table is generated.

[0104] Add the newly generated position xi(t+1) to the taboo list TabuList. If the length of the taboo list exceeds the taboo length TL, delete the earliest added record to keep the length of the taboo list unchanged.

[0105] Recalculate the fitness function: For the updated particle position xi(t+1), recalculate its fitness value f(xi(t+1)).

[0106] Update individual optimal and global optimal: According to the above method, update the individual optimal position pi and the global optimal position g of the particle.

[0107] Check whether the termination conditions of the algorithm are met, such as reaching the maximum number of iterations MaxIter or the fitness value of the global optimal position has no obvious change in multiple consecutive iterations.

[0108] If the termination condition is met, the relay protection setting corresponding to the global optimal position g is output as the optimized result; otherwise, it returns to continue the iteration.

[0109] (1) Construct a deep belief network DBN. By constructing a deep belief network structure with multiple hidden layers, it can fully learn the complex intrinsic characteristics and potential patterns of the data. The number of hidden layers and nodes are dynamically adjusted according to the complexity of the data and the scale of the problem. In the initial stage, a smaller network structure is determined through experiments, such as 3 hidden layers, with 100, 50, and 20 nodes in each layer. Then, the network structure is further optimized using an automatic hyperparameter random search optimization algorithm to find the optimal hidden layer configuration to balance the model's fitting ability and computational complexity.

[0110] (2) Based on improved RBM training: In the training of each layer of restricted Boltzmann machine (RBM), an improved contrast divergence algorithm, namely the fast continuous contrast divergence algorithm (FPC), is used. This algorithm accelerates the convergence speed of RBM and improves its learning ability for complex data distribution by dynamically adjusting the training step size and learning rate. During the training process, the momentum term is introduced so that the model can better utilize historical gradient information when updating parameters, avoid falling into the local optimal solution, and enhance the stability and robustness of the model.

[0111] (3) When training RBM layer by layer, an adaptive layer-by-layer training strategy is adopted. First, the input data is subjected to principal component analysis (PCA), and the initial learning rate and number of training steps of each layer of RBM are determined according to the principal component contribution rate of the data. During the training process, the reconstruction error and information entropy of the output features of each layer of RBM are monitored, and the training parameters of the subsequent layers are dynamically adjusted to ensure that each layer can effectively learn the important features of the data and avoid excessive compression or loss of feature information.

[0112] (4) Add an output layer on top of the DBN and use the Connectionist Temporal Classification (CTC) loss function combined with the traditional mean square error (MSE) loss function as the objective function for supervised fine-tuning. The CTC loss function is often used to handle the classification problem of sequence data and can effectively deal with the time series correlation and label inconsistency problems that may exist in relay protection setting evaluation, while the MSE loss function is used to directly optimize the error between the predicted setting and the true setting. By adjusting the weights of these two loss functions, the performance of the model in terms of classification accuracy and setting prediction accuracy can be balanced.

[0113] (5) During the fine-tuning process, the attention mechanism is introduced to enable the model to automatically focus on the key features and information in the input data. By calculating the attention weights between the input features and the hidden layer states, the model can more effectively focus on the parts that are closely related to the relay protection setting evaluation and ignore irrelevant noise information, thereby improving the accuracy and pertinence of the evaluation. At the same time, an adaptive learning rate adjustment strategy (such as AdaGrad, RMSProp or Adam optimizer) is used to automatically adjust the learning rate of each parameter according to the update history of the parameters, accelerate the convergence speed of the model, and alleviate the gradient vanishing or gradient exploding problems to a certain extent.

[0114] (6) Use the k-fold cross-validation method (such as k = 5 or 10) to evaluate and select multiple trained DBN models. Divide the data set into k non-overlapping subsets, select one of the subsets as the validation set each time, and the remaining subsets as the training set, and train and validate the model k times. By calculating the average evaluation indicators of each model on the validation set (such as accuracy, recall rate, F1 value, root mean square error, etc.), select the model with the best performance as the final evaluation model.

[0115] (7) According to the actual operation of the power plant and the statistical analysis of historical data, a dynamic adjustment mechanism for the evaluation threshold is established. For example, under different operating conditions (such as peak load period, valley load period, equipment maintenance period, etc.), the reasonable range of relay protection settings may change. Therefore, it is necessary to dynamically adjust the evaluation threshold according to the real-time operating condition information so that the evaluation results are more in line with the actual situation and operating requirements. At the same time, the parameters and thresholds of the model are continuously updated by using online learning and incremental learning methods so that it can adapt to the changes in the operating status of the power system and the emerging fault modes, and realize adaptive relay protection setting evaluation.

[0116] By using the deep belief network to evaluate the relay protection settings optimized by the taboo particle swarm algorithm, various factors and complex situations can be considered more accurately and comprehensively, the reliability and practicality of the evaluation results can be improved, and strong support can be provided for the optimization of the relay protection system of the power plant and the safe and stable operation.

[0117] Example 2

[0118] This embodiment provides a power plant relay protection setting optimization system based on an optimization algorithm, including:

[0119] The data acquisition module is configured to acquire the sequential operation data and historical fault data of the power plant;

[0120] The preprocessing module is configured to perform data preprocessing on the acquired data;

[0121] The feature module is configured to extract and fuse features of the preprocessed data, and extract and predict multi-scale features of the fused data to obtain an initial relay protection setting;

[0122] The optimization module is configured to optimize the initial relay protection setting value by using a taboo particle swarm algorithm to obtain an optimized relay protection setting value;

[0123] An evaluation module is configured to evaluate the optimized relay protection setting using a deep belief network;

[0124] The output module is configured to output the optimization result that is evaluated as qualified.

[0125] A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the method described.

[0126] A terminal device includes a processor and a computer-readable storage medium, wherein the processor is used to implement various instructions; and the computer-readable storage medium is used to store multiple instructions, wherein the instructions are suitable for being loaded by the processor and executing the described method.

[0127] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A power plant relay protection setting optimization method based on optimization algorithm, characterized in that: include: Obtaining power plant timing operation data and historical fault data; Perform data preprocessing on the acquired data; Perform feature extraction and fusion on the preprocessed data, and perform multi-scale feature extraction and prediction on the fused data to obtain the initial relay protection setting; The initial relay protection setting is optimized by using the taboo particle swarm algorithm to obtain the optimized relay protection setting. The optimized relay protection settings are evaluated using a deep belief network; Output the optimization results that are qualified for evaluation.

2. The method for optimizing relay protection settings of a power plant based on an optimization algorithm according to claim 1, characterized in that: The data preprocessing includes data cleaning and standardization. The data cleaning includes removing noise and outliers, and removing abnormal data points with high deviation from the mean. The cleaning conditions are set as follows: Among them, μ i and σ i are the mean and standard deviation calculated for the i-th data source in the historical time window: Among them, T is the historical time window.

3. The method for optimizing relay protection settings of a power plant based on an optimization algorithm according to claim 2, characterized in that: The preprocessed data is subjected to feature extraction and fusion, including extracting spatial features through CNN after the standardized features, and using GCN to combine the spatiotemporal association of multimodal data to generate a fused feature vector Z t : Z t =GCN(F t ,A) where F t =Conv2D(X t ,W)+b is the convolution feature of each data source, X t is the input matrix of the time step t of the multimodal data, consisting of multiple W is the convolution kernel weight matrix, b is the bias term, and A is the adjacency matrix, which represents the spatiotemporal correlation between different features and has a dimension of N×N.

4. The method for optimizing relay protection settings of a power plant based on an optimization algorithm according to claim 3 is characterized in that: The multi-scale feature extraction and prediction of the fused data includes the spatiotemporal fusion feature Z t Perform multi-scale convolution operations, using convolution kernels of different sizes W k Extract features, convolution result H k Represents the characteristics of the kth time scale: H k =Conv1D(Z t ,W k ) Among them, H k is the convolution feature matrix of time scale k, W k is the weight of the kth convolution kernel, controlling the feature extraction of different time ranges. k Use a gating mechanism to control the flow of information, expressed as: Among them, g k is the gate value, which indicates the importance weight of the feature and is generated by the Sigmoid activation function σ; is the gating unit weight matrix, which represents the learning parameters of the current time scale feature. is the bias term of the gating unit, which is used to adjust the output value. is the activation feature matrix after gating processing.

5. The method for optimizing relay protection settings of a power plant based on an optimization algorithm according to claim 4, characterized in that: The multi-scale feature extraction and prediction of the fused data also includes the activation features at different time scales. Perform weighted fusion to generate the final prediction result in, is the final prediction output, which is used to represent the relay protection parameters in a certain period of time in the future. k is the weight of the kth time scale, which is determined through model training and is used to balance the contribution of features at different time scales.

6. A power plant relay protection setting optimization method based on optimization algorithm according to claim 5, characterized in that: The method uses a taboo particle swarm algorithm to optimize the initial relay protection constant to obtain the optimized relay protection constant, including initializing a particle swarm and a taboo table based on the initial relay protection constant, updating the individual optimum and the global optimum of the particles based on the fitness function and updating the particle speed and position, performing taboo processing on the new position of the particle based on the taboo table, and obtaining the optimized relay protection constant through updating and iteration.

7. A power plant relay protection setting optimization method based on optimization algorithm according to claim 6, characterized in that: The method of evaluating the optimized relay protection setting by using a deep belief network includes optimizing the deep belief network structure by using random search, and training each layer of the deep belief network structure by using a restricted Boltzmann machine, wherein the training step size and the learning rate are dynamically adjusted by using an improved contrast divergence algorithm to accelerate the convergence speed, and a dynamic adjustment mechanism for the evaluation threshold is established based on the statistical analysis of power plant data, and a qualified relay protection setting is evaluated and output through the relay protection setting evaluation.

8. A power plant relay protection setting optimization system based on optimization algorithm, characterized in that: include: The data acquisition module is configured to acquire the sequential operation data and historical fault data of the power plant; The preprocessing module is configured to perform data preprocessing on the acquired data; The feature module is configured to extract and fuse features of the preprocessed data, and extract and predict multi-scale features of the fused data to obtain an initial relay protection setting; The optimization module is configured to optimize the initial relay protection setting value by using a taboo particle swarm algorithm to obtain an optimized relay protection setting value; An evaluation module is configured to evaluate the optimized relay protection setting using a deep belief network; The output module is configured to output the optimization result that is evaluated as qualified.

9. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing the method according to claim 1 .

10. A terminal device, comprising a processor and a computer-readable storage medium, wherein the processor is used to implement each instruction; and the computer-readable storage medium is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the method as claimed in claim 1 .

Images