A relay protection simulation system

Abstract

The present invention relates to the field of relay protection technology, and in particular to a relay protection simulation system, comprising a simulation unit and a parameter optimization unit, wherein the simulation unit comprises: a power system model for creating a simulated power system environment and simulating the operation of the power system; a protection device simulation module, which is constructed to simulate the working mode and reaction of an actual relay protection device, that is, to test the action parameters of the protection device under various fault scenarios and system states; and a fault simulation module, which creates various fault conditions and is used to test the working condition of the protection device when a fault occurs. The present invention provides a relay protection simulation system, which realizes real-time optimization of simulation results by combining the relay protection simulation system with a machine learning algorithm, and dynamically adjusts the action parameters of the protection device based on the optimization results, thereby improving the responsiveness and accuracy of the protection system and effectively reducing the risk of false operation and missed operation.

Description

Technical Field

[0001] The present invention relates to the technical field of relay protection, in particular to a relay protection simulation system. Background Art

[0002] The relay protection simulation system is a computerized tool used to simulate, test and optimize relay protection devices and schemes in power systems. Its main function is to verify and evaluate the reaction performance, accuracy, response speed, reliability, etc. of the relay protection device by simulating various fault scenarios in the power grid, so as to ensure that when a fault occurs in the real power grid, the relay protection system can cut off the faulty part in a timely and accurate manner to protect the power grid and equipment from further damage.

[0003] A Chinese patent application with publication number CN109596925A discloses a relay protection device simulation test system. It includes: a host computer for building a power system model based on RT-LAB; an RT-LAB simulator for running the power system model in real time; a power amplifier for amplifying the voltage and current signals in the power system model output by the simulator to the voltage and current signal range of the first type of relay protection device to be tested; a signal conversion device for conditioning the signals transmitted between the first type of relay protection device to be tested and the simulator; and a switch for converting the signals transmitted between the simulator and the second type of relay protection device to be tested. This invention can realize large-scale power system modeling and simulation, and simultaneously meet the testing of multiple traditional and intelligent relay protection devices. It has a simple structure and is easy to implement.

[0004] As mentioned in the above application, the relay protection simulation systems in the prior art are mostly tested based on preset fault scenarios and static parameter configurations, and are unable to adjust the parameters of the protection devices in real time according to the dynamic changes of the power grid. Even if the simulation results find that the parameters of the protection devices are inappropriate, manual intervention and multiple adjustments are often required, which is inefficient. Secondly, the identification and diagnosis of fault types in traditional simulation systems rely on pre-set rules and lack intelligent adaptive capabilities. Summary of the Invention

[0005] In order to solve the above problems, the present invention provides a relay protection simulation system.

[0006] The present invention adopts the following technical solution: a relay protection simulation system, including a simulation unit and a parameter optimization unit, wherein the simulation unit includes:

[0007] Power system model, used to create a simulated power system environment and simulate the operation of the power system;

[0008] The protection device simulation module is constructed to simulate the working mode and response of the actual relay protection device, that is, to test the operating parameters of the protection device under various fault scenarios and system states;

[0009] The measurement module is constructed to simulate various measurement devices in the power system, collect data on the real-time operating status of the power system, record it as power system operating status data, and pass this data as input signals to the protection device simulation module for analysis;

[0010] A simulation result evaluation module is configured to evaluate whether a simulation result meets the standards, and mark a simulation result that does not meet the standards as a simulation result that does not meet the standards;

[0011] The parameter optimization unit includes:

[0012] A data collection module, used to collect power system operation status data corresponding to the marked simulation results;

[0013] a first data analysis module, which inputs the collected power system operating status data into a pre-built first machine learning model and outputs a fault type;

[0014] The second data analysis module inputs the operating status data and the fault type into the second machine learning model, outputs the protection device adjustment parameters, and updates the protection device simulation module based on the protection device adjustment parameters.

[0015] As a further description of the above technical solution: the simulation unit also includes:

[0016] Fault simulation module, which creates various fault conditions to test the operation of protection devices when faults occur;

[0017] The user interface module is used to provide users with an operating interface for configuring system parameters, starting simulation, observing results, and viewing simulation data information during the simulation process. The simulation data information includes a graphical display of the simulation process, protection device status, and system waveform display function to facilitate user operation and analysis.

[0018] As a further description of the above technical solution: the power system operating status data includes phase current data, line current data, load data, phase voltage data, line voltage data and grid frequency data, and the power system operating status data is collected and obtained by a measurement module.

[0019] As a further description of the above technical solution: the method for constructing the first machine learning model includes:

[0020] Initialize the first machine learning model structure. The first machine learning model structure adopts an MLP type multi-layer forward network structure with four input layers, two hidden layers, and one output layer. The input layer includes the first input layer, the second input layer, the third input layer, and the fourth input layer. The number of nodes in the first input layer is 2, corresponding to phase current data and line current data respectively. The number of nodes in the second input layer is 1, corresponding to load data. The number of nodes in the third input layer is 2, corresponding to phase voltage data and line voltage data respectively. The number of nodes in the fourth input layer is 1, corresponding to grid frequency data. The hidden layer includes the first hidden layer and the second hidden layer. The number of nodes in the first hidden layer is 128, and the ReLU function is used as the activation function. The number of nodes in the second hidden layer is 64, and the ReLU function is used as the activation function. The output layer is the first output layer. The number of nodes in the first output layer is [1, n], predicting the fault type, where n is the number of fault types.

[0021] After initializing the first machine learning model structure, the power system operating status data and the fault types corresponding to the power system operating status data are used to train the first machine learning model. The power system operating status data and the fault types corresponding to the power system operating status data are obtained from the database. The database records the power system operating status data corresponding to each fault type of each power system model for each time, which is used to optimize the model. The optimizer is Adam, the loss function is the MSE loss function, the batch size is set to 32, the number of iterations is 200 rounds, and the training ends when the loss function converges, indicating that the training is completed.

[0022] As a further description of the above technical solution: the first machine learning model training method includes:

[0023] Converting the power system operation status data into a corresponding set of feature vectors;

[0024] The power system operation status data is used as the input of the machine learning model, and the machine learning model takes the fault type corresponding to each set of power system operation status data as the output, the fault type actually corresponding to each set of power system operation status data as the prediction target, and minimizing the loss function value of the machine learning model as the training target; training is stopped when the loss function value of the machine learning model is less than or equal to the preset target loss value.

[0025] As a further description of the above technical solution: the second machine learning model includes 3 input layers, 2 convolutional layers, 2 pooling layers, 1 RNN layer and 2 fully connected layers; the number of neurons in the input layer is 5; the 2 convolutional layers include the first convolutional layer and the second convolutional layer, the convolution kernel size of the first convolutional layer and the second convolutional layer is 3×3, the activation function is ReLU, the step size is 1, the margin is 0, the number of convolution kernels of the first convolutional layer is 32, and the number of convolution kernels of the second convolutional layer is 64; the 2 pooling layers include the first pooling layer and the second pooling layer, the two pooling layers have the same structure, the window size is 2×2, and the pooling method adopts the maximum pooling method, that is, in the pooling In the pooled window, only the maximum value is taken as the feature value of the corresponding position of the window after pooling; the RNN layer includes 64 LSTM units, 64 input channels and 64 output channels; the LSTM unit includes 5 components, and the 5 components include input gate, forget gate, cell state, output gate and hidden state; the time step number of the RNN layer input channel is 1; RNN is equipped with a random attenuation mechanism with a random attenuation probability of 0.2; the two fully connected layers include the first fully connected layer and the second fully connected layer; the first fully connected layer includes 128 neurons, and the activation function is ReLU; the second fully connected layer includes 1 neuron, which outputs the adjustment data of the protection device as the final output.

[0026] As a further description of the above technical solution: the training method of the second machine learning model includes:

[0027] The training method of the second machine learning model includes:

[0028] The adjustment data of V groups of historical protection devices are divided into training sets and validation sets. The training set contains the adjustment data of A groups of historical protection devices. The adjustment data of historical protection devices include operating status data, fault types and actual adjustment parameters of protection devices. The weight parameter set Q of all layers and the bias parameter set B of all layers are initialized. The parameters are repeatedly calculated and updated until the loss function converges loosely and the model training is completed.

[0029] As a further description of the above technical solution: the method for evaluating whether the simulation results meet the standards includes:

[0030] response time assessment, reliability assessment, and accuracy assessment;

[0031] The response time evaluation methods include:

[0032] According to the design requirements of the power grid, the protection needs of the equipment and the real-time operation requirements of the system, a response time standard is set and recorded as the standard response time;

[0033] During the simulation, the time from the occurrence of each fault to the action of the protection device is recorded as the real-time response time;

[0034] When the real-time response time is greater than the standard response time, the simulation result is marked.

[0035] As a further description of the above technical solution: the reliability assessment method includes:

[0036] By simulating different fault conditions multiple times, check whether the protection device simulation module can stably perform protection actions in different scenarios. If the protection device simulation module fails to perform protection actions, the simulation results will be marked.

[0037] As a further description of the above technical solution: the accuracy assessment method includes:

[0038] The fault simulation module simulates different types of faults to check whether the protection device simulation module can accurately identify and respond correctly. If a false operation or missed operation occurs, the simulation result will be marked.

[0039] Beneficial effects:

[0040] The present invention provides a relay protection simulation system, which evaluates whether the simulation results meet the standards, marks the simulation results that do not meet the standards, then collects the power system operation status data corresponding to the marked simulation results, inputs the data into a pre-built first machine learning model, outputs the fault type, and then inputs the operation status data and the fault type into a second machine learning model, outputs the protection device adjustment parameters, and updates the protection device simulation module based on the protection device adjustment parameters. That is, by combining the relay protection simulation system with the machine learning algorithm, real-time optimization of the simulation results is achieved, and the action parameters of the protection device are dynamically adjusted based on the optimization results. Through real-time analysis and automatic adjustment, not only the responsiveness and accuracy of the protection system are improved, but also the risks of false operation and missed operation are effectively reduced. This solution greatly shortens the design and debugging cycle of the simulation relay protection simulation system, enhances the intelligence and adaptability of the power system, and provides a more reliable guarantee for the safe operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further explained below in conjunction with the accompanying drawings and embodiments:

[0042] Figure 1 A module connection diagram of a simulation unit provided in an embodiment of the present invention;

[0043] Figure 2 A module connection diagram of the optimization unit provided in an embodiment of the present invention;

[0044] Figure 3 This is a flow chart of a response time evaluation method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the technical means, creative features, objectives and effects of the present invention easier to understand, the present invention is further described below with reference to specific diagrams. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless they conflict.

[0046] Example 1

[0047] See also Figure 1-Figure 3 The embodiment of the present invention provides a technical solution: a relay protection simulation system, comprising: a simulation unit and an optimization unit, wherein the simulation unit comprises:

[0048] Power system model: Create a simulated power system environment and simulate the operation of the power system, including the topology of the power grid, equipment parameters (transformers, circuit breakers, transmission lines, etc.), load and power generation;

[0049] It should be noted that the power system model is used to provide input signals and operating background for relay protection.

[0050] The protection device simulation module is constructed to simulate the working mode and response of the actual relay protection device, that is, to test the action parameters of the protection device under various fault scenarios and system conditions.

[0051] The measurement module is constructed to simulate various measurement devices in the power system, collect data on the real-time operating status of the power system, and pass this data as input signals to the protection device simulation module for analysis;

[0052] Fault simulation module, which creates various fault conditions to test the operation of protection devices when faults occur;

[0053] A simulation result evaluation module is configured to evaluate whether a simulation result meets the standards, and mark a simulation result that does not meet the standards as a simulation result that does not meet the standards;

[0054] The user interface module is used to provide users with an operation interface for configuring system parameters, starting simulation, observing results, and viewing simulation data information during the simulation process. The simulation data information includes a graphical display of the simulation process, protection device status, and system waveform display function to facilitate user operation and analysis;

[0055] The parameter optimization unit is used to analyze and optimize the protection setting parameters based on the simulation data.

[0056] Wherein, the parameter optimization unit includes:

[0057] A data collection module collects the power system operation status data obtained by the measurement module;

[0058] The power system operating status data includes phase current data, line current data, load data, phase voltage data, line voltage data and grid frequency data.

[0059] a first data analysis module, which inputs the collected power system operating status data into a pre-built first machine learning model and outputs a fault type;

[0060] The second data analysis module inputs the operating status data and the fault type into the second machine learning model, outputs the protection device adjustment parameters, and updates the protection device simulation module based on the protection device adjustment parameters.

[0061] In this embodiment, by evaluating whether the simulation results meet the standards, the simulation results that do not meet the standards are marked, and then the power system operation status data corresponding to the marked simulation results are collected and input into the pre-built first machine learning model to output the fault type. The operation status data and the fault type are then input into the second machine learning model to output the protection device adjustment parameters. The protection device simulation module is updated based on the protection device adjustment parameters. That is, by combining the relay protection simulation system with the machine learning algorithm, real-time optimization of the simulation results is achieved, and the action parameters of the protection device are dynamically adjusted based on the optimization results. Through real-time analysis and automatic adjustment, not only the responsiveness and accuracy of the protection system are improved, but also the risks of false operation and missed operation are effectively reduced. This solution greatly shortens the design and debugging cycle of the relay protection simulation system, enhances the intelligence and adaptability of the power system, and provides a more reliable guarantee for the safe operation of the power grid.

[0062] Example 2

[0063] Based on the above embodiments, this embodiment further discloses a method for constructing and training a first machine learning model:

[0064] The method for constructing the first machine learning model includes:

[0065] Initialize the first machine learning model structure. The first machine learning model structure adopts an MLP type multi-layer forward network structure with four input layers, two hidden layers, and one output layer. The input layer includes the first input layer, the second input layer, the third input layer, and the fourth input layer. The number of nodes in the first input layer is 2, corresponding to phase current data and line current data respectively; the number of nodes in the second input layer is 1, corresponding to load data, the number of nodes in the third input layer is 2, corresponding to phase voltage data and line voltage data respectively, and the number of nodes in the fourth input layer is 1, corresponding to grid frequency data; the hidden layer includes the first hidden layer and the second hidden layer. The number of nodes in the first hidden layer is 128, and the ReLU function is used as the activation function; the number of nodes in the second hidden layer is 64, and the ReLU function is used as the activation function; the output layer is the first output layer, and the number of nodes in the first output layer is [1, n], predicting the fault type, where n is the number of fault types.

[0066] After initializing the first machine learning model structure, the power system operating status data and the fault types corresponding to the power system operating status data are used to train the first machine learning model. The power system operating status data and the fault types corresponding to the power system operating status data are obtained from the database. The database records the power system operating status data corresponding to each fault type of each power system model for each time, which is used to optimize the model. The optimizer is Adam, the loss function is the MSE loss function, the batch size is set to 32, the number of iterations is 200 rounds, and the training ends when the loss function converges, indicating that the training is completed.

[0067] It should be noted that the Adam optimizer is one of the five major optimizers commonly used in machine learning, and its full name is Adaptive Moment Estimation.

[0068] It should be noted that the fault types include short circuit fault, ground fault, overload fault, open circuit fault and unbalance fault;

[0069] Among them, short-circuit faults include single-phase ground short circuit, two-phase short circuit, two-phase ground short circuit, three-phase short circuit and three-phase ground short circuit; grounding faults include single-phase grounding fault, two-phase grounding fault and three-phase grounding fault; overload faults include continuous overload fault and instantaneous overload fault; open circuit faults include single-phase open circuit fault, two-phase open circuit fault and three-phase open circuit fault; unbalanced faults include negative sequence current fault and zero sequence current fault.

[0070] The first machine learning model training method includes:

[0071] Converting the power system operation status data into a corresponding set of feature vectors;

[0072] The power system operation status data is used as input to a machine learning model, wherein the machine learning model uses the fault type corresponding to each set of power system operation status data as output, uses the fault type actually corresponding to each set of power system operation status data as a prediction target, and uses minimizing the loss function value of the machine learning model as a training target; and stops training when the loss function value of the machine learning model is less than or equal to a preset target loss value;

[0073] The loss function value of the first machine learning model is the mean square error;

[0074] Mean square error is one of the commonly used loss functions. By transforming the loss function formula Minimization is used to train the model so that the machine learning model can better fit the data, thereby improving the performance and accuracy of the model.

[0075] In the loss function, MSE is the loss function value of the first machine learning model, x is the feature vector group number; e is the number of feature vector groups; y x is the fault type output by the first machine learning model corresponding to the x-th group of feature vectors, is the fault type actually corresponding to the xth group of eigenvectors.

[0076] Example 2

[0077] Based on the above embodiments, this embodiment further discloses a method for constructing and training a second machine learning model:

[0078] The second machine learning model includes 3 input layers, 2 convolutional layers, 2 pooling layers, 1 RNN layer and 2 fully connected layers; the number of neurons in the input layer is 5; the 2 convolutional layers include the first convolutional layer and the second convolutional layer, the convolution kernel size of the first convolutional layer and the second convolutional layer is 3×3, the activation function is ReLU, the step size is 1, the margin is 0, the number of convolution kernels of the first convolutional layer is 32, and the number of convolution kernels of the second convolutional layer is 64; the 2 pooling layers include the first pooling layer and the second pooling layer, the two pooling layers have the same structure, the window size is 2×2, and the pooling method adopts the maximum pooling method, that is, within the pooling window, only the maximum value is taken as the window after pooling The feature values ​​at the corresponding positions; the RNN layer includes 64 LSTM units, 64 input channels and 64 output channels; the LSTM unit includes 5 components, including input gate, forget gate, cell state, output gate and hidden state; the time step number of the RNN layer input channel is 1; RNN is equipped with a random attenuation mechanism with a random attenuation probability of 0.2; the two fully connected layers include the first fully connected layer and the second fully connected layer; the first fully connected layer includes 128 neurons, and the activation function is ReLU; the second fully connected layer includes 1 neuron, which outputs the adjustment data of the protection device as the final output, where the regression calculation formula of the adjustment data Y of the protection device is:

[0079] Y = E × t + C;

[0080] Where E is the weight of the second fully connected layer, C is the bias value of the second fully connected layer, and t is a three-dimensional tensor.

[0081] The training method of the second machine learning model includes:

[0082] The adjustment data of the historical protection devices of group V are divided into a training set and a validation set. The training set contains the adjustment data of the historical protection devices of group A. The adjustment data of the historical protection devices include the operating status data, the fault type, and the actual adjustment parameters of the protection devices. The weight parameter set Q of all layers and the bias parameter set B of all layers are initialized. The forward propagation is used to calculate the predicted value y. The adjustment parameters of the actual protection devices are set to yt. The loss function loos formula is calculated as follows:

[0083]

[0084] Where yt r represents the actual adjustment parameters of the protection device in the adjustment data of the historical protection device of group r, y r represents the protection device adjustment parameter predicted from the rth group of historical protection device adjustment data, r represents the group number of the historical protection device adjustment data, and r≤A; the formula for backpropagation to calculate the gradient and update the parameters using the gradient descent method includes:

[0085]

[0086] In the formula, γ represents the learning rate, which is a preset value; represents the gradient of Q, represents the gradient of B; Q′ represents the updated weight parameter set Q; B′ represents the updated bias parameter set B;

[0087] The parameters are calculated and updated repeatedly until the model converges, that is, the model training is completed.

[0088] It should be noted that the adjustment parameters include action time, action current, overcurrent multiple, delay setting and differential protection sensitivity;

[0089] The action time refers to the time from triggering the protection action to actually disconnecting the circuit after the protection device detects a fault or abnormality. If the simulation results show that the response time is insufficient or too long, the action time needs to be adjusted. The action time should be reasonably set according to the operation requirements of the power grid and the type of fault.

[0090] The operating current refers to the trigger current value that determines the protection device when an overcurrent or short-circuit fault occurs. If the simulation results show that the protection device fails to cut off the current in time, it is necessary to adjust the operating current appropriately. This can be done by increasing or decreasing the set value of the operating current. Increasing the set current can reduce false operations, while decreasing the set current can increase sensitivity and respond to faults quickly.

[0091] The overcurrent multiple refers to the multiple relationship between the operating current of the protection device and the rated current of the equipment. A reasonable overcurrent multiple can ensure that the protection device can respond quickly when the fault current exceeds the normal operating current.

[0092] Delay setting means setting a certain delay for the protection device after a fault occurs to avoid false responses to instantaneous fluctuations or short-term disturbances. Based on the simulation results, the delay setting value is adjusted to prevent false operations of the protection device when the grid load fluctuates or the fault type is unclear, while ensuring timely response when a fault occurs.

[0093] Differential protection sensitivity is used to detect internal equipment faults. Low sensitivity can lead to missed internal faults, while high sensitivity can cause false trips. Adjust the sensitivity of the differential protection based on simulation results. If the system detects excessive false trips or missed trips, optimize the sensitivity setting to ensure that faults are identified quickly and accurately.

[0094] In this embodiment, a deep learning algorithm is used to establish a first machine learning model and a second machine learning model, which can accurately evaluate the fault type and the protection device adjustment parameters, realize automatic identification of the fault type and ensure automatic adjustment of the device parameters, reduce manual intervention, and improve operation efficiency.

[0095] Example 3

[0096] The method for evaluating whether the simulation result meets the standard includes:

[0097] response time assessment, reliability assessment, and accuracy assessment;

[0098] The response time evaluation methods include:

[0099] According to the design requirements of the power grid, the protection needs of the equipment and the real-time operation requirements of the system, a response time standard is set and recorded as the standard response time;

[0100] During the simulation, the time from the occurrence of each fault to the action of the protection device is recorded as the real-time response time;

[0101] When the real-time response time is greater than the standard response time, the simulation result is marked;

[0102] The reliability evaluation method includes:

[0103] By simulating different fault conditions multiple times, check whether the protection device simulation module can stably perform protection actions in different scenarios. If the protection device simulation module fails to perform protection actions, the simulation results will be marked.

[0104] The accuracy assessment method includes:

[0105] The fault simulation module simulates different types of faults to check whether the protection device simulation module can accurately identify and respond correctly. If a false operation or missed operation occurs, the simulation result will be marked.

[0106] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above-described embodiments. The above-described embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A relay protection simulation system, characterized in that: It includes a simulation unit and a parameter optimization unit, and the simulation unit includes: Power system model, used to create a simulated power system environment and simulate the operation of the power system; The protection device simulation module is constructed to simulate the working mode and response of the actual relay protection device, that is, to test the operating parameters of the protection device under various fault scenarios and system states; The measurement module is constructed to simulate various measurement devices in the power system, collect data on the real-time operating status of the power system, record it as power system operating status data, and pass this data as input signals to the protection device simulation module for analysis; A simulation result evaluation module is configured to evaluate whether a simulation result meets the standards, and mark a simulation result that does not meet the standards as a simulation result that does not meet the standards; The method for evaluating whether the simulation result meets the standard includes: response time assessment, reliability assessment, and accuracy assessment; The response time evaluation methods include: According to the design requirements of the power grid, the protection needs of the equipment and the real-time operation requirements of the system, a response time standard is set and recorded as the standard response time; During the simulation, the time from the occurrence of each fault to the action of the protection device is recorded as the real-time response time; When the real-time response time is greater than the standard response time, the simulation result is marked; The parameter optimization unit includes: A data collection module, used to collect power system operation status data corresponding to the marked simulation results; a first data analysis module, which inputs the collected power system operating status data into a pre-built first machine learning model and outputs a fault type; The second data analysis module inputs the operating status data and the fault type into the second machine learning model, outputs the protection device adjustment parameters, and updates the protection device simulation module based on the protection device adjustment parameters.

2. A relay protection simulation system according to claim 1, characterized in that: The simulation unit also includes: Fault simulation module, which creates various fault conditions to test the operation of protection devices when faults occur; The user interface module is used to provide users with an operating interface for configuring system parameters, starting simulation, observing results, and viewing simulation data information during the simulation process. The simulation data information includes a graphical display of the simulation process, protection device status, and system waveform display function.

3. A relay protection simulation system according to claim 2, characterized in that: The power system operation status data includes phase current data, line current data, load data, phase voltage data, line voltage data and grid frequency data, and the power system operation status data is collected and acquired by a measurement module.

4. A relay protection simulation system according to claim 3, characterized in that: The method for constructing the first machine learning model includes: Initialize the first machine learning model structure. The first machine learning model structure adopts an MLP type multi-layer forward network structure with four input layers, two hidden layers, and one output layer. The input layer includes the first input layer, the second input layer, the third input layer, and the fourth input layer. The number of nodes in the first input layer is 2, corresponding to phase current data and line current data respectively. The number of nodes in the second input layer is 1, corresponding to load data. The number of nodes in the third input layer is 2, corresponding to phase voltage data and line voltage data respectively. The number of nodes in the fourth input layer is 1, corresponding to grid frequency data. The hidden layer includes the first hidden layer and the second hidden layer. The number of nodes in the first hidden layer is 128, and the ReLU function is used as the activation function. The number of nodes in the second hidden layer is 64, and the ReLU function is used as the activation function. The output layer is the first output layer. The number of nodes in the first output layer is [1, n], predicting the fault type, where n is the number of fault types. After initializing the first machine learning model structure, the power system operating status data and the fault types corresponding to the power system operating status data are used to train the first machine learning model. The power system operating status data and the fault types corresponding to the power system operating status data are obtained from the database. The database records the power system operating status data corresponding to each fault type of each power system model for each time, which is used to optimize the model. The optimizer is Adam, the loss function is the MSE loss function, the batch size is set to 32, the number of iterations is 200 rounds, and the training ends when the loss function converges, indicating that the training is completed.

5. A relay protection simulation system according to claim 4, characterized in that: The first machine learning model training method includes: Converting the power system operation status data into a corresponding set of feature vectors; The power system operation status data is used as the input of the machine learning model, and the machine learning model takes the fault type corresponding to each set of power system operation status data as the output, the fault type actually corresponding to each set of power system operation status data as the prediction target, and minimizing the loss function value of the machine learning model as the training target; training is stopped when the loss function value of the machine learning model is less than or equal to the preset target loss value.

6. A relay protection simulation system according to claim 5, characterized in that: The second machine learning model includes 3 input layers, 2 convolutional layers, 2 pooling layers, 1 RNN layer and 2 fully connected layers; the number of neurons in the input layer is 5; the 2 convolutional layers include the first convolutional layer and the second convolutional layer, the convolution kernel size of the first convolutional layer and the second convolutional layer is 3×3, the activation function is ReLU, the step size is 1, the margin is 0, the number of convolution kernels of the first convolutional layer is 32, and the number of convolution kernels of the second convolutional layer is 64; the 2 pooling layers include the first pooling layer and the second pooling layer, the two pooling layers have the same structure, the window size is 2×2, and the pooling method adopts the maximum pooling method, that is, within the pooling window, only the maximum number of convolution kernels is taken. The maximum value is used as the feature value of the corresponding position of the window after pooling; the RNN layer includes 64 LSTM units, 64 input channels and 64 output channels; the LSTM unit includes 5 components, including input gate, forget gate, cell state, output gate and hidden state; the time step number of the RNN layer input channel is 1; RNN is equipped with a random attenuation mechanism with a random attenuation probability of 0.2; the two fully connected layers include the first fully connected layer and the second fully connected layer; the first fully connected layer includes 128 neurons, and the activation function is ReLU; the second fully connected layer includes 1 neuron, which outputs the adjustment data of the protection device as the final output.

7. A relay protection simulation system according to claim 6, characterized in that: The training method of the second machine learning model includes: The adjustment data of the historical protection device of group V are divided into a training set and a validation set. The adjustment data of the historical protection device is collected. The adjustment data of the historical protection device includes the operating status data, fault type and actual adjustment parameters of the protection device. The weight parameter set of all layers is initialized. and the set of bias parameters for all layers , repeatedly calculate and update the parameters until the loss function Until convergence, the model completes training.

8. A relay protection simulation system according to claim 1, characterized in that: The reliability evaluation method includes: By simulating different fault conditions multiple times, check whether the protection device simulation module can stably perform protection actions in different scenarios. If the protection device simulation module fails to perform protection actions, the simulation results will be marked.

9. A relay protection simulation system according to claim 8, characterized in that: The accuracy assessment method includes: The fault simulation module simulates different types of faults to check whether the protection device simulation module can accurately identify and respond correctly. If a false operation or missed operation occurs, the simulation result will be marked.

Images