Pumped storage power station simulation test method compatible with various PLCs and computer device

Abstract

The invention discloses a pumped storage power station simulation test method compatible with various PLCs and a computer device. The method comprises the following steps: constructing a test platform matched with a target power station; the test platform is integrated with a data receiving model with a general data interface, a preset symmetric residual network model, a preset long-short term memory model and a plurality of PLC communication protocols; processing the initial spatial features of the target power station based on a preset symmetric residual network model to obtain first information; analyzing target equipment parameter information, actual environment factor information and first information of the target power station based on the data fusion model to obtain a target operation strategy; processing the time sequence characteristics of the target power station through a preset long and short time memory model to obtain future operation state prediction information; and obtaining an instructive operation strategy based on the future operation state prediction information and the target operation strategy. According to the method, a simulation test scheme with high compatibility, high test efficiency, high test accuracy and low maintenance cost can be provided.

Description

Technical Field

[0001] The present disclosure relates to the technical field of pumped-storage power station simulation, and in particular to a pumped-storage power station simulation test method and a computer device compatible with multiple PLCs. Background Art

[0002] Pumped storage power stations are important regulating tools in the power grid. They can balance the load of the power grid by storing and releasing energy, ensuring the stable operation of the power system. PLC systems play a core role in the automation control of power stations due to their reliability and flexibility. However, due to compatibility issues between PLC systems from different manufacturers, this has brought challenges to the simulation test of power stations.

[0003] Specifically, systems from different PLC manufacturers may use different communication protocols and software interfaces, resulting in poor interoperability between systems and difficulty in achieving seamless integration and testing; due to compatibility issues, testers need to spend a lot of time to solve communication and integration problems between systems, which reduces the efficiency and speed of testing; with the development of technology and changes in power station needs, traditional simulation test solutions are difficult to adapt to new PLC systems or software versions, resulting in increased maintenance and upgrade costs; in an environment where multiple systems coexist, data integration and analysis become more complicated, which may lead to inaccuracy and inconsistency in test results; traditional simulation test solutions cannot fully simulate the complex environment and dynamic changes of pumped-storage power stations in actual operation, affecting the reliability of test results. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide a pumped-storage power station simulation test method and computer device compatible with multiple PLCs, which can solve the problems of poor compatibility, low test efficiency, poor test accuracy, and high maintenance costs existing in traditional simulation test solutions.

[0005] In a first aspect, the embodiment of the present disclosure provides a simulation test method for a pumped storage power station compatible with multiple PLCs, which adopts the following technical solution:

[0006] Constructing a test platform that matches the target power station; the test platform integrates a data receiving model, a preset symmetric residual network model, a preset long short-term memory model, and multiple PLC communication protocols; the data receiving model integrates a universal data interface with a data conversion function;

[0007] Processing the initial spatial features in the target power station based on the preset symmetric residual network model to obtain first information;

[0008] Analyze the target equipment parameter information, the actual environmental factor information, and the first information of the target power station based on the constructed data fusion model to obtain the target operation strategy of the target equipment under different environmental conditions and power station layouts;

[0009] Processing the time series characteristics of the target power station through the preset long short-term memory model to obtain the prediction information of the future operation state of the target power station;

[0010] Based on the future operation state prediction information and the target operation strategy, a guiding operation strategy is obtained.

[0011] Optionally, the processing of the initial spatial features in the target power station based on the preset symmetric residual network model to obtain the first information includes:

[0012] Extracting key spatial features of the target power station, preprocessing the key spatial features, and obtaining first spatial features;

[0013] Obtaining a spatial training set and a spatial test set based on the first spatial feature;

[0014] Construct a preset symmetric residual network model;

[0015] Training the preset symmetric residual network model based on the spatial training set, and testing the trained preset symmetric residual network model using the spatial test set;

[0016] Analyze the first spatial feature based on the trained preset symmetric residual network model to obtain the first information;

[0017] The first information includes the actual layout of several key spatial structures of the target power station, several potential abnormal problems, and a layout optimization plan.

[0018] Optionally, the key spatial features include at least one of the geographical location features of the power station, the structural layout features of the power station, the distribution features of the power station equipment, the distance relationship between different equipment, the equipment distribution density, the layout parameters of important equipment, the hot spot area information, the pipeline layout, the unit location, and the control room layout;

[0019] The important equipment layout parameters include at least one of generator set parameter information, transformer parameter information, and switchgear parameter information.

[0020] Optionally, the constructing a preset symmetric residual network model includes:

[0021] Determine a network structure; the network structure is a symmetrically designed structure; the basic unit in the network structure is a residual block;

[0022] A plurality of convolutional layers are configured inside the residual block; the number of input channels and the number of output channels of the convolutional layers are the same, and the convolutional kernel size and step size are consistent; the convolutional layer is a 1x1 convolution or a 3x3 convolution;

[0023] Adding an activation function after the convolutional layer; the activation function includes ReLU, Leaky ReLU or ELU;

[0024] Adding a batch normalization layer between the convolutional layer and the activation function;

[0025] Adding a skip connection between the input and output of the residual block, wherein parameters in the skip connection are shared with parameters inside the residual block;

[0026] Determine one of the convolutional layers as the input layer of the network;

[0027] Stacking a plurality of the residual blocks to form a main part of the network, wherein the output of each residual block is used as the input of the next residual block; and a pooling layer or a transition layer is provided between different residual blocks;

[0028] Configure an output layer; the output layer is a fully connected layer with a softmax activation function or a fully connected layer with a linear activation function;

[0029] Determine a loss function, an optimizer, and a preset learning rate; the loss function includes one or more of a cross entropy loss function and a mean square error loss function; the optimizer includes one or more of Adam and SGD.

[0030] Optionally, the processing of the time series characteristics of the target power station by using the preset long short-term memory model to obtain the prediction information of the future operation state of the target power station includes:

[0031] Extracting key timing features of the target power station, preprocessing the key timing features, and obtaining first timing features;

[0032] Obtain a time series training set and a time series test set based on the first time series feature;

[0033] Construct a preset long and short-term memory model;

[0034] Training the preset long short-term memory model based on the time series training set, and testing the trained preset long short-term memory model using the time series test set;

[0035] Based on the trained preset long short-term memory model, future operation state prediction information of the target power station is obtained.

[0036] Optionally, the constructing of a preset long short-term memory model includes:

[0037] Determine the model structure; the model structure includes an input layer, multiple LSTM layers and an output layer, the shape of the input layer matches the dimension of the input data; the LSTM layer includes an input gate, a forget gate and an output gate, each of the LSTM layers has a hidden state and a cell state, and the hidden state and cell state of each LSTM layer will be passed to the next LSTM layer; the output layer is configured with the number of output units and an activation function;

[0038] Configure the number of LSTM hidden units, learning rate, batch size, loss function, and optimizer.

[0039] Optionally, the key timing characteristics include at least one of power load changes, energy consumption information, energy output information, temperature changes inside the power station, and humidity changes inside the power station.

[0040] Optionally, obtaining a guiding operation strategy based on the future operation state prediction information and the target operation strategy includes:

[0041] Constructing a manifold regularization model; the manifold regularization model is suitable for processing different types of data, and the manifold regularization model is configured with a target manifold learning algorithm;

[0042] The manifold regularization model is trained using the first spatial feature and the first temporal feature, and the future operation state prediction information and the target operation strategy are analyzed using the trained manifold regularization model to obtain an energy consumption equipment area;

[0043] Obtaining the guiding operation strategy based on the energy consumption equipment area;

[0044] The guiding operation strategy includes one or more of an equipment optimization layout strategy, an equipment upgrade strategy, and an energy scheduling strategy for the corresponding area.

[0045] In a second aspect, the embodiment of the present disclosure further provides a pumped storage power station simulation test system compatible with multiple PLCs, including:

[0046] A test platform construction module, used to construct a test platform matching the target power station; the test platform integrates a data receiving model, a preset symmetric residual network model, a preset long short-term memory model and a plurality of PLC communication protocols, and the data receiving model integrates a universal data interface with a data conversion function;

[0047] A spatial feature processing module, used to process the initial spatial features in the target power station based on the preset symmetric residual network model to obtain first information;

[0048] An analysis module, used to analyze the target equipment parameter information, the actual environmental factor information, and the first information of the target power station based on the constructed data fusion model, and obtain a target operation strategy of the target equipment under different environmental conditions and power station layouts;

[0049] A time series feature processing module, used to process the time series features of the target power station through the preset long short-term memory model to obtain the prediction information of the future operation state of the target power station;

[0050] The acquisition module is used to obtain a guiding operation strategy based on the future operation state prediction information and the target operation strategy.

[0051] In a third aspect, the embodiments of the present disclosure further provide a computer device, which adopts the following technical solution:

[0052] The computer device comprises:

[0053] at least one processor; and,

[0054] a memory communicatively connected to the at least one processor; wherein,

[0055] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned pumped-storage power station simulation test methods compatible with multiple PLCs.

[0056] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium storing computer instructions for enabling a computer to execute any of the above-described pumped-storage power station simulation test methods compatible with multiple PLCs.

[0057] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, including a computer program / instruction, which implements the steps of any of the above methods when executed by a processor.

[0058] The simulation test method for a pumped-storage power station compatible with multiple PLCs disclosed in the present application can adapt to PLCs of different models and brands by integrating multiple PLC communication protocols, so that the test platform can be widely used in various pumped-storage power stations, thereby improving compatibility and versatility; through the processing of a data receiving model, a symmetric residual network model and a long short-term memory model, the spatial characteristics and temporal characteristics of the power station can be finely analyzed, thereby improving the accuracy and reliability of data processing; through the analysis of a data fusion model, the target equipment parameters, environmental factors and other influencing factors can be more comprehensively considered, and a more reasonable operation strategy can be provided for the power station, thereby improving the operation efficiency and stability of the power station equipment; through the long short-term memory model, the future operation status of the power station can be predicted, potential problems and risks can be discovered in advance, and the power station can be helped to formulate corresponding prevention and adjustment measures, thereby improving the safety and reliability of the power station; combined with the future operation status prediction information and the target operation strategy, a guiding operation strategy is provided for the power station, making the operation of the power station more intelligent and optimized, thereby improving the overall operation efficiency and economy, and providing stronger support for the stable operation of the power station.

[0059] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following preferred embodiments are specifically cited and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 A flow chart of a simulation test method for a pumped-storage power station compatible with multiple PLCs provided in an embodiment of the present disclosure.

[0062] Figure 2 A flowchart of a method for obtaining first information provided in an embodiment of the present disclosure.

[0063] Figure 3 A schematic diagram of a flow chart of a method for constructing a preset symmetric residual network model provided in an embodiment of the present disclosure.

[0064] Figure 4 A flowchart of a method for obtaining prediction information of future operating status of a target power station provided in an embodiment of the present disclosure.

[0065] Figure 5A flowchart of a method for constructing a preset long short-term memory model provided in an embodiment of the present disclosure.

[0066] Figure 6 A flowchart of a method for obtaining a guiding operation strategy provided in an embodiment of the present disclosure.

[0067] Figure 7 A principle block diagram of a pumped-storage power station simulation test system compatible with multiple PLCs provided in an embodiment of the present disclosure.

[0068] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0069] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0070] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0071] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0072] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0073] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0074] Reference Figure 1 In a first aspect, the present application discloses a simulation test method for a pumped storage power station compatible with multiple PLCs, comprising:

[0075] S100, build a test platform matching the target power station; the test platform integrates a data receiving model, a preset symmetric residual network model, a preset long short-term memory model and a variety of PLC communication protocols, and the data receiving model integrates a universal data interface with data conversion function.

[0076] Specifically, a test platform is built to integrate a data receiving model, a preset symmetric residual network model, a preset long short-term memory model and multiple PLC communication protocols. The data receiving model should have a universal data interface with data conversion function to adapt to different types of data input, that is, it can receive data from different types of PLCs and perform effective processing and conversion, and can realize data sharing and interaction with other models and systems, ensuring the efficiency and flexibility of data conversion and integration, and ensuring the smooth transmission and sharing of data.

[0077] Furthermore, the data receiving model may include a data receiving unit, a data processing unit and a data output unit. The data receiving unit is used to collect real-time data from different PLCs, the data processing unit is used to perform data conversion and cleaning, and the data output unit can pass the processed data to other models for further analysis.

[0078] The test platform is compatible with a variety of PLC devices and supports different communication protocols, ensuring efficient data transmission and stable communication.

[0079] Integrate common PLC communication protocols, such as Modbus, Profibus, Ethernet / IP, etc., and realize communication and data exchange between different PLC devices through adapters or configuration files.

[0080] In this embodiment, the universal data interface can parse the original data into a universal data format, convert the parsed data into a unified data exchange format, and package the converted data into a transmittable format, such as a JSON string or an XML document, thereby realizing mutual conversion and exchange of different PLC data formats.

[0081] By building a test platform that matches the target power station, the simulation of the test environment and the integration of data can be achieved, providing a perfect foundation for subsequent simulation tests, realizing the reception, processing and analysis of different types of data, and providing reliable basic support for subsequent simulation tests and decision-making. Overall, such a test platform can improve the intelligence level and operating efficiency of the system, and provide important technical support for power station operation optimization and performance improvement.

[0082] S200, processing initial spatial features in the target power station based on a preset symmetric residual network model to obtain first information.

[0083] The symmetric residual network model can effectively process spatial features, extract key information from the data, and provide useful reference for subsequent analysis and decision-making.

[0084] S300, analyzing the target equipment parameter information, the actual environmental factor information, and the first information of the target power station based on the constructed data fusion model to obtain the target operation strategy of the target equipment under different environmental conditions and power station layouts.

[0085] A data fusion model is constructed to analyze the target equipment parameter information, actual environmental factor information and the first information of the target power station, and to derive the target operation strategy of the target equipment under different environmental conditions and power station layouts; the data fusion model can effectively integrate data from different sources, help analyze the optimal operation strategy of the target equipment, and improve the performance and efficiency of the power station.

[0086] The target device parameter information may include operating parameters of the pump unit, such as power, flow, efficiency curve, etc.

[0087] The actual environmental factor information may include environmental factors around the power station, such as water source water level, temperature

[0088] Temperature, humidity and other data.

[0089] S400, processing the time series characteristics of the target power station through a preset long short-term memory model to obtain prediction information of the future operation state of the target power station.

[0090] The long short-term memory model can effectively capture the long-term dependencies in time series data, improve the accurate prediction of future operating status, and help formulate reasonable operating strategies.

[0091] S500, obtaining a guiding operation strategy based on the future operation state prediction information and the target operation strategy.

[0092] By combining the future operation status prediction information and the target operation strategy, a guiding operation strategy is obtained to optimize the operation and performance of the power plant. By formulating a guiding operation strategy, intelligent management and optimization of the power plant can be achieved, energy utilization efficiency and equipment performance can be improved, and operating costs can be further reduced.

[0093] Specifically, by real-time monitoring of the changes in various parameters and operating status of the power plant, timely adjustments can be made based on the forecast information and target strategies. For example, when a power plant load fluctuation is predicted, equipment parameters or load scheduling can be adjusted in real time to ensure stable operation of the power plant.

[0094] Based on future state prediction information and target operation strategies, emergency response plans can be formulated to prepare for possible emergencies. For example, when considering that future weather changes may cause water level fluctuations, corresponding emergency operation procedures can be set in advance to ensure that the power station can respond quickly in emergency situations.

[0095] Based on actual monitoring data and operating results, the operating strategy of the power plant can be continuously evaluated and optimized. Through continuous adjustment and improvement, the efficiency and performance of the power plant can be improved to achieve a more sustainable operating mode.

[0096] Through the implementation of the above guiding operation strategies, power plant managers can manage and operate power plants more scientifically and intelligently to cope with various complex operating conditions and challenges, maximize the efficiency, flexibility and reliability of power plants, and promote the effective use of clean energy and the development of intelligent energy systems.

[0097] The simulation test method for a pumped-storage power station compatible with multiple PLCs disclosed in the present application can adapt to PLCs of different models and brands by integrating multiple PLC communication protocols, so that the test platform can be widely used in various pumped-storage power stations, thereby improving compatibility and versatility; through the processing of a data receiving model, a symmetric residual network model, and a long short-term memory model, it can perform a refined analysis of the spatial characteristics and temporal characteristics of the power station, thereby improving the accuracy and reliability of data processing; through the analysis of a data fusion model, it can more comprehensively consider target equipment parameters, environmental factors, and other influencing factors, thereby providing a more reasonable operation strategy for the power station, thereby improving the operation efficiency and stability of the power station equipment; through the long short-term memory model, the future operation status of the power station can be predicted, potential problems and risks can be discovered in advance, and the power station can be helped to formulate corresponding prevention and adjustment measures, thereby improving the safety and reliability of the power station; combined with future operation status prediction information and target operation strategies, a guiding operation strategy is provided for the power station, thereby making the operation of the power station more intelligent and optimized, thereby improving the overall operation efficiency and economy.

[0098] In summary, this pumped-storage power station simulation test method provides all-round and refined power station operation analysis and guidance through the integrated application of multiple models, which can effectively improve the power station operation management level, improve the power station operation efficiency and reliability, and reduce operation risks and costs.

[0099] Reference Figure 2 The method for obtaining the first information specifically includes the following steps:

[0100] S210, extracting key spatial features of the target power station, preprocessing the key spatial features, and obtaining first spatial features.

[0101] Specifically, data mining and pattern recognition techniques can be used to extract key spatial features from power plant data and perform preprocessing, including data cleaning, feature extraction, normalizing data formats, removing noise, filling missing values, etc., to facilitate network processing.

[0102] The method disclosed in this step can ensure that the extracted spatial features are accurate and reliable, providing a high-quality data foundation for subsequent model training and analysis.

[0103] Among them, the key spatial characteristics include at least one of the geographical location characteristics of the power station, the structural layout characteristics of the power station, the distribution characteristics of the power station equipment, the distance relationship between different equipment, the equipment distribution density, the layout parameters of important equipment, the hot spot area information, the pipeline layout, the unit location, and the control room layout.

[0104] The important equipment layout parameters preferably include at least one of generator set parameter information, transformer parameter information, and switchgear parameter information.

[0105] S220, obtaining a spatial training set and a spatial test set based on the first spatial feature.

[0106] Specifically, the data in the random first spatial feature can be divided into a training set and a test set according to a certain ratio, for example, the training set and the test set can be obtained by dividing them according to a ratio of 7:3 or 8:2.

[0107] Alternatively, if there is a class imbalance in the dataset (i.e., the first spatial feature), you can consider using stratified sampling to ensure that the class distribution in the training set and the test set is similar, which can better evaluate the performance of the model on different categories.

[0108] In this application, a suitable partitioning scheme can be selected according to the specific situation, and it is ensured that the data distribution of the training set and the test set can represent the entire data set, so as to effectively evaluate the generalization ability of the model.

[0109] S230, constructing a preset symmetric residual network model.

[0110] S240, training a preset symmetric residual network model based on a spatial training set, and testing the trained preset symmetric residual network model using a spatial test set.

[0111] The symmetric residual network model is trained using the spatial training set, and then the trained model is verified and tuned using the spatial test set. Through training and testing, it is ensured that the model can accurately capture the correlation between the spatial characteristics of the power station, which improves the generalization ability and prediction accuracy of the model, that is, it can improve the accuracy of feature recognition and analysis.

[0112] S250, analyzing the first spatial feature based on the trained preset symmetric residual network model to obtain first information;

[0113] The first information includes the actual layout of several key spatial structures of the target power station, several potential abnormal problems, and layout optimization solutions.

[0114] The first spatial feature is analyzed using the trained preset symmetric residual network model to obtain information such as the actual layout of the key structure of the target power station, potential abnormal problems and optimization plans. By analyzing the first information, we can fully understand the structure and existing problems of the power station, provide important reference for formulating further optimization plans and improvement plans, and improve the efficiency and reliability of the power station.

[0115] The scheme disclosed in this embodiment first extracts the key spatial features of the target power station through a preset symmetric residual network model, and preprocesses these key spatial features to obtain the first spatial features. This step can help extract the features that have the greatest impact on the performance and structure of the power station, and provide a basis for subsequent analysis and optimization; then, based on the first spatial features, divide the spatial training set and the spatial test set according to an appropriate method to train and test the model. This step can ensure the generalization ability of the model on unknown data; construct a preset symmetric residual network model, which can usually better capture the complex relationship between spatial features and help improve the performance of the model; use the spatial training set to train the preset symmetric residual network model, and test the model through the spatial test set to evaluate its performance. This step can help verify the effectiveness and accuracy of the model; finally, based on the trained preset symmetric residual network model, analyze the first spatial feature to obtain first information, which includes the actual layout of the key spatial structure of the target power station, the potential abnormal problems and the layout optimization plan. This information can help optimize the structure and performance of the power station and improve the efficiency and reliability of the power station.

[0116] In this scheme, extracting key spatial features and preprocessing them can help improve the model's understanding and abstraction of power plant data; based on the preset symmetric residual network model, it can better capture the complex relationship between features and improve the performance of the model; through the division of training and test sets, the generalization ability of the model can be effectively evaluated; analyzing the first spatial feature can help discover problems in the power plant and propose optimization solutions, thereby improving the overall efficiency and reliability of the power plant.

[0117] Reference Figure 3 , the method for constructing the preset symmetric residual network model specifically includes the following steps:

[0118] S241, determine the network structure;

[0119] The network structure is a symmetrically designed structure;

[0120] The basic unit in the network structure is the residual block.

[0121] In this step, the network structure is designed to be symmetrical, and this structural symmetry is conducive to the learning and understanding of the model; residual blocks are used as the basic units of the network. Residual blocks help solve the gradient vanishing and gradient exploding problems in deep neural networks and speed up model training.

[0122] S242, multiple convolutional layers are configured inside the residual block; the number of input channels and the number of output channels of the convolutional layers are the same, and the convolution kernel size and step size are consistent;

[0123] The convolution layer is a 1x1 convolution or a 3x3 convolution.

[0124] In this step, the number of input and output channels of the convolution layer is the same, and the convolution kernel size and step size are consistent, which can keep the size of the feature map stable; using a 1x1 or 3x3 convolution kernel helps capture features of different scales.

[0125] S243, add an activation function after the convolution layer; the activation function includes ReLU, Leaky ReLU or ELU.

[0126] Using activation functions such as ReLU, Leaky ReLU, or ELU can introduce nonlinearity and increase the expressiveness of the model.

[0127] S244, add a batch normalization layer between the convolution layer and the activation function.

[0128] Batch normalization can accelerate model convergence, reduce the gradient vanishing problem, and enhance the generalization ability of the model.

[0129] S245, adding a skip connection between the input and output of the residual block, and the parameters in the skip connection are shared with the parameters inside the residual block.

[0130] Skip connections help alleviate the gradient vanishing problem and allow information to be transmitted more quickly; parameter sharing can improve the parameter efficiency of the model.

[0131] S246, determining a convolutional layer as an input layer of the network;

[0132] Multiple residual blocks are stacked to form the main part of the network, where the output of each residual block serves as the input of the next residual block; pooling layers or transition layers are set between different residual blocks.

[0133] Pooling layers or transition layers can reduce the dimension of feature maps, reduce computational complexity, and improve the computational efficiency of the model.

[0134] S247, configure the output layer; the output layer is a fully connected layer with a softmax activation function or a fully connected layer with a linear activation function.

[0135] The output layer uses a fully connected layer with a softmax activation function or a fully connected layer with a linear activation function, which can adapt to different types of tasks.

[0136] S248, determining a loss function, an optimizer, and a preset learning rate;

[0137] The loss function includes one or more of a cross entropy loss function and a mean square error loss function; the optimizer includes one or more of Adam and SGD.

[0138] Select a loss function suitable for the task, such as the cross entropy loss function for classification tasks and the mean square error loss function for regression tasks; select a suitable optimizer, such as Adam, SGD, etc., to speed up convergence and improve model performance; preset learning rate can effectively control the update speed of model parameters and avoid oscillation during training.

[0139] In this embodiment, the symmetrical design is conducive to simplifying the network structure, improving the interpretability and training efficiency of the network; the residual block can alleviate the gradient vanishing problem and accelerate the model convergence speed; by superimposing multiple convolutional layers, the nonlinear expression ability of the network can be increased; the convolution kernel with the same number of input and output channels can keep the size of the feature map stable and reduce information loss; the activation function introduces nonlinearity to enhance the expression ability of the network; the batch normalization layer helps to accelerate model training and improve the stability and generalization ability of the model; the jump connection helps to alleviate the gradient vanishing problem and accelerate information transmission; parameter sharing can improve the utilization of parameters and reduce overfitting; by stacking multiple residual blocks, the network depth can be increased and the feature abstraction ability can be improved; the pooling layer or transition layer can reduce the feature dimension and improve the computational efficiency; the design of the output layer selects an appropriate activation function according to the task requirements, which can better adapt to different types of tasks; selecting an appropriate loss function can evaluate the model performance and guide the model training; a suitable optimizer can accelerate the optimization process of the model parameters and improve the model convergence speed; setting an appropriate learning rate can avoid oscillation during training and ensure the convergence performance of the model.

[0140] In summary, the overall solution comprehensively utilizes a series of deep learning technologies and optimization methods, which can improve the performance of the model, speed up the training of the model, enhance the stability and generalization ability of the model, so as to better apply it to practical problems and provide more effective solutions.

[0141] Furthermore, the preset symmetric residual network model constructed also includes a pooling layer, which is used to reduce the spatial dimension of the feature map, reduce the amount of calculation, and increase the receptive field. The receptive field refers to the response range of neurons to input data. The pooling layer can expand the receptive field and help the network better capture the characteristics of the input data, thereby reducing the complexity of model training and improving computational efficiency while maintaining effective information.

[0142] Furthermore, a Dropout layer can be added at an appropriate position in the preset symmetric residual network model to prevent overfitting. Specifically, L2 regularization can be applied to penalize large weights and improve the generalization ability of the model.

[0143] Reference Figure 4 The method for obtaining the prediction information of the future operation status of the target power station specifically includes the following steps:

[0144] S410, extracting key timing features of the target power station, preprocessing the key timing features, and obtaining first timing features.

[0145] Specifically, appropriate feature extraction techniques (such as sliding window method, Fourier transform, etc.) can be used to extract key timing features of the target power station, and then these features are preprocessed (such as standardization, normalization, etc.) to obtain the first timing features.

[0146] In this step, extracting key features can reduce data dimensions and ease model complexity; preprocessing can make data easier to be processed by the model and improve model performance.

[0147] Among them, the key timing characteristics preferably include at least one of power load changes, energy consumption information, energy output information, temperature changes inside the power station, humidity changes inside the power station, reservoir water level changes, and environmental conditions.

[0148] Specifically, these time series data can be collected from various monitoring systems of the power station to ensure the integrity and accuracy of the data.

[0149] S420, obtaining a time series training set and a time series test set based on the first time series feature.

[0150] Specifically, the extracted first time series features can be divided into a training set and a test set according to certain division rules to prepare for model training and testing; this step can evaluate the generalization ability of the model and verify the performance of the model on unknown data.

[0151] S430, constructing a preset long short-term memory model.

[0152] The preset long short-term memory model is suitable for processing time series data, can capture long-term dependencies in the data, and is suitable for time series prediction tasks.

[0153] S440, training a preset long short-term memory model based on a time series training set, and testing the trained preset long short-term memory model using a time series test set.

[0154] Use the time series training set to train the preset long short-term memory model, then make predictions on the time series test set, and evaluate the performance and accuracy of the model. Through training and testing, the predictive ability of the model can be evaluated, the parameters of the model can be optimized, and the generalization ability of the model can be improved.

[0155] S450, based on the trained preset long short-term memory model, obtain future operation state prediction information of the target power station.

[0156] By using the trained LSTM model to predict future time series data and obtain the predicted information of the future operating status of the target power station, it is possible to accurately predict the future status of the target power station, help discover potential problems in advance, perform preventive maintenance, and improve the operating efficiency and reliability of the power station.

[0157] In this embodiment, through the trained preset long short-term memory model, the future operating state of the target power station can be accurately predicted, helping operators to make decisions and adjustments in advance; the automated prediction model can reduce labor costs and quickly and effectively provide the power station with prediction information on the future state; through accurate future state prediction, potential problems or abnormal situations can be discovered in advance, and corresponding early warning and preventive measures can be made to reduce operational risks; through accurate prediction of future operating states, it can help optimize the power station operation and maintenance plan and improve the operating efficiency and reliability of the power station; the model prediction results can provide decision support for management, so that it can better understand the current state and future trends of the power station and formulate decision-making strategies; through training and testing of the time series training set, the model parameters can be continuously optimized, the prediction accuracy can be improved, and the model can be more in line with the actual situation.

[0158] In summary, the overall solution can provide effective decision support for power station management and operation by combining the LSTM model to process the time series characteristics of the target power station, improve the operating efficiency and reliability of the power station, reduce potential risks, and bring better economic benefits and management effects.

[0159] Reference Figure 5 , the method for constructing the preset long short-term memory model specifically includes the following steps:

[0160] S431, determine the model structure;

[0161] The model structure includes an input layer, multiple LSTM layers and an output layer. The shape of the input layer matches the dimension of the input data. The LSTM layer includes an input gate, a forget gate and an output gate. Each LSTM layer has a hidden state and a cell state, and the hidden state and cell state of each LSTM layer will be passed to the next LSTM layer. The output layer is configured with the number of output units and an activation function.

[0162] Specifically, the feature dimension of the input layer matches the dimension of the input data, ensuring that the data can be smoothly passed into the model; the model includes multiple LSTM layers to capture time series information, and finally the output layer is used to output the prediction results; the unique structure of LSTM can effectively capture the long-term dependencies of time series data; hidden states and cell states can transmit information and model data; the number of output units in the output layer should be determined according to task requirements, and the activation function can be selected according to the task type, such as sigmoid can be used for binary classification, and softmax can be used for multi-classification.

[0163] Furthermore, the number of units in each LSTM layer is usually 12, 256, 512, etc.

[0164] S432, configure the number of LSTM hidden units, learning rate, batch size, loss function, and optimizer.

[0165] Among them, the number of configured LSTM hidden units determines the capacity of the model and affects the model's learning ability and accuracy.

[0166] The configuration of the learning rate can control the update speed of the model parameters during the training process, so that it will not be too high to cause oscillation, nor too low to cause slow convergence. Furthermore, you can consider using learning rate decay or learning rate scheduler.

[0167] The batch size defines the number of samples used in each iteration during training, affecting the training speed and stability of the model. Specifically, the batch size can be determined based on the available computing resources, and common choices are 32, 64, 128, etc.

[0168] The loss function is used to evaluate the gap between the model output and the true label. You can choose a loss function suitable for the task to guide model optimization. Specifically, you can choose a loss function based on the task type, such as mean square error (MSE) for regression and cross entropy for classification.

[0169] Choose a suitable optimizer to update model parameters. Common optimizers include Adam, SGD, RMSprop, etc., which can accelerate convergence and improve model performance.

[0170] In this embodiment, a suitable LSTM model structure can be designed according to task requirements and data characteristics, which can effectively capture time series information and improve prediction accuracy. By reasonably setting parameters such as the number of hidden units and learning rate, model performance can be optimized, the training process can be accelerated, and prediction accuracy can be improved.

[0171] Furthermore, in the constructed preset long short-term memory model, dropout or L2 regularization can also be used to prevent overfitting.

[0172] Reference Figure 6 , the method for obtaining the guiding operation strategy specifically includes the following steps:

[0173] S510, constructing a manifold regularization model; the manifold regularization model is suitable for processing different types of data, and a target manifold learning algorithm is configured in the manifold regularization model.

[0174] Specifically, a manifold regularization model suitable for processing different types of data is constructed, in which a target manifold learning algorithm is configured. At the same time, a suitable manifold learning algorithm is selected to learn the structure of the data and highlight the important features in the data. These algorithms can map high-dimensional data into low-dimensional manifold space in order to better understand the characteristics and laws of the data.

[0175] In the manifold regularization model, key parameters of the model, such as regularization strength and neighborhood size, can be set to adjust the sensitivity of the model to the intrinsic structure of the data.

[0176] In this step, the manifold regularization model is suitable for processing different types of data and helps to discover the potential structure within the data; through manifold learning, important features in the data can be effectively extracted to help subsequent analysis and decision making.

[0177] S520, using the first spatial feature and the first temporal feature to train the manifold regularization model, using the trained manifold regularization model to analyze future operation state prediction information and target operation strategy, and obtain the energy loss equipment area.

[0178] Specifically, the first spatial feature and the first temporal feature are used to train the manifold regularization model so that the model can learn the structure of the data, and the trained model is used to analyze future operation status prediction information and target operation strategies.

[0179] For example, suppose that in a certain area of ​​the power station, due to unreasonable equipment layout, energy is lost greatly during transmission. By analyzing the fused data using the trained manifold regularization model (i.e. analyzing future operating status prediction information and target operating strategies), this problem area can be pointed out.

[0180] In this step, by combining the future operating status prediction information and the target operating strategy, the characteristics and potential laws of the data can be analyzed more comprehensively; by analyzing the relationship between various data, problems and optimization space in equipment operation can be discovered.

[0181] S530, obtaining a guiding operation strategy based on the energy loss equipment area, where the guiding operation strategy includes one or more of an equipment optimization layout strategy, an equipment upgrade strategy, and an energy scheduling strategy for the corresponding area.

[0182] Specifically, according to the energy loss equipment area obtained by analysis, corresponding operation strategies are formulated, including equipment optimization layout strategy, equipment upgrade strategy, energy scheduling strategy, etc. That is, in this step, targeted operation strategies can be formulated according to the actual situation and analysis results, which are more targeted and effective; by optimizing equipment layout, upgrading equipment, adjusting energy scheduling, etc., the equipment utilization rate can be improved, energy loss can be reduced, and the overall operation efficiency can be improved.

[0183] With the guiding operation strategies obtained, power plant managers can re-plan the equipment layout in the area or upgrade related equipment to reduce energy loss. After implementing the optimization measures, they can continue to monitor energy consumption and output data to evaluate the effectiveness of the optimization measures.

[0184] The method disclosed in this embodiment analyzes future operating states and target operating strategies, and formulates a guiding operating strategy based on the situation of the energy loss equipment area. The strategy can be tailored according to actual conditions to improve pertinence and effectiveness. Through the equipment optimization layout strategy in the guiding operating strategy, the equipment layout can be reasonably planned, the coordination efficiency between equipment can be improved, and energy waste can be reduced. The guiding operating strategy includes an equipment upgrade strategy, and the equipment can be upgraded or replaced according to actual conditions to improve equipment performance and operating efficiency. The formulation of an energy scheduling strategy can help to reasonably allocate energy resources, improve energy utilization efficiency, and reduce energy costs. Through the implementation of the overall plan, energy loss equipment areas can be discovered and improved, equipment utilization can be improved, energy loss can be reduced, and operating costs can be reduced. Measures such as optimizing equipment layout, upgrading equipment, and reasonably scheduling energy can improve overall operating efficiency, reduce failure rates, and enhance the stability and reliability of equipment operation. The implementation of the guiding operating strategy can reduce human intervention, improve the level of automation, and reduce management costs.

[0185] In summary, the overall solution provides more targeted and guiding operation strategies for operation management through scientific data analysis and model construction, which helps to optimize equipment operation status, improve energy utilization efficiency, reduce operating costs, and improve overall operation efficiency and management level.

[0186] In this embodiment, the manifold regularization technology can effectively integrate the results of spatial analysis and temporal analysis to provide a comprehensive and detailed operation simulation view for the pumped storage power station. This comprehensive view helps to deeply understand the operation mechanism of the power station and guide the optimization and improvement of the power station. Through the above steps, we can effectively combine the spatial and temporal characteristics of the pumped storage power station to provide a more accurate and comprehensive simulation test for the operation of the power station, which helps to improve the efficiency and reliability of the power station operation, and at the same time provide important decision support for the management and maintenance of the power station.

[0187] Furthermore, the future operating status prediction information may include: predicting the changing trends of power plant output power, water level, pressure and other parameters in the future time period, predicting the load conditions of the power plant and the corresponding grid response in the future time period, and predictable operating states for different environmental conditions, power plant layouts and other factors.

[0188] The target operation strategy may include: determining the optimal equipment parameter configuration based on actual environmental factors and power plant layout, setting the operation mode of the target equipment, optimizing the control strategy to achieve the best power plant operation efficiency, and designing corresponding operation plans for different environmental conditions, including load scheduling, optimizing energy storage and other strategies.

[0189] For example, you can set operation targets based on the long-term operation targets and short-term needs of the power station, such as YY+232026P

[0190] Maximize energy conversion efficiency, minimize operating costs, etc.

[0191] The equipment operation mode can be set, such as giving priority to power generation during peak grid load periods and pumping water during low load periods.

[0192] Guidance operation strategies may include: adjusting power plant operation parameters based on future state prediction information, making equipment scheduling and preparations in advance, setting operation goals and equipment operation modes according to target operation strategies, monitoring power plant operation status in real time, and making adjustments based on prediction information and target strategies to maximize the efficiency and performance of the power plant.

[0193] For example, we can work with grid operators to dispatch loads based on real-time grid demand and forecasted loads, prioritize power generation when grid demand peaks, and pumped hydropower storage when demand is low.

[0194] The risks of operating strategies can be evaluated, including equipment failure, environmental changes, etc., and corresponding risk mitigation measures can be formulated; emergency plans can be established to deal with unpredictable events such as extreme weather or equipment failure; optimization algorithms such as linear programming and dynamic programming can be used to optimize the operating strategy of the power station; and multi-objective optimization strategies can be formulated by considering cost, efficiency and environmental impact.

[0195] In this application, based on the future state prediction information and the target operation strategy, a set of effective guiding operation strategies can be formulated to achieve efficient, stable and sustainable development of the target power station operation.

[0196] Example 1: Adapt to the simulation test of Siemens and Schneider PLC. The specific steps are as follows:

[0197] 1) Build a test platform adapted to Siemens and Schneider PLCs, integrating data reception model, symmetric residual network model and long short-term memory model.

[0198] 2) Process the initial spatial features based on the symmetric residual network model to obtain the first information of the power station.

[0199] 3) Data fusion analyzes the parameter information, environmental factors and primary information of Siemens and Schneider PLC systems to formulate target operation strategies.

[0200] 4) Use the long short-term memory model to process time series features and predict the future operating status of the power plant.

[0201] 5) Formulate guiding operation strategies based on forecast information and target operation strategies, and test the compatibility and operation effects of different PLC systems.

[0202] The test objectives of this embodiment are to verify the effectiveness of this solution in terms of compatibility with different PLC systems, optimize the power plant operation strategy, and improve the performance and efficiency of the power plant.

[0203] Through this embodiment, compatibility testing of Siemens and Schneider PLC systems can be achieved.

[0204] Example 2: Simulation test under different load conditions. The specific steps are as follows:

[0205] 1) Set the simulation parameters under high load and low load conditions, including load size, environmental factors, etc.

[0206] 2) Run simulation tests to obtain the operating status data of the power station under different load conditions.

[0207] 3) Compare and analyze the simulation results with the actual data to evaluate the accuracy and reliability of the simulation model.

[0208] The test goal of this embodiment is to verify the simulation performance under different load conditions and provide a reference for the power station to make adaptive adjustments to different load conditions in actual operation.

[0209] This embodiment demonstrates the simulation results of the power station operation status under high load and low load conditions, and compares and analyzes them with actual data.

[0210] Example 3: Use simulated faults to perform system robustness testing. The specific steps are as follows:

[0211] 1) Simulate different system failure conditions, such as equipment failure, communication interruption, etc., to trigger abnormal conditions in the power plant PLC system.

[0212] 2) Monitor the system's response to faults, record the fault handling process, and analyze the system's resilience and robustness.

[0213] 3) According to the fault test results, adjust and optimize the system to improve the system's fault handling efficiency and recovery capabilities.

[0214] The test objectives of this embodiment are: to perform system robustness testing by simulating faults, evaluate the reliability and stability of the power plant PLC system, provide improvement suggestions for system design and operation, and ensure that the power plant can still operate efficiently in the face of various abnormal situations.

[0215] In this embodiment, it is demonstrated that the method disclosed in the present application can test the response capability and fault handling efficiency of the power plant PLC system by simulating different system fault conditions.

[0216] Example 4: Real-time optimization scheduling of intelligent energy management system. The specific steps are as follows:

[0217] 1) Establish an intelligent energy management system to integrate power plant data, energy market information and user needs.

[0218] 2) Monitor the power plant operation status and environmental conditions in real time, collect real-time data and transmit it to the system.

[0219] 3) Based on real-time data and future forecast information, optimize the operation parameters of the power plant, including load scheduling, energy storage optimization, etc.

[0220] 4) Implement guiding operation strategies, adjust the power plant operation mode according to the latest situation, and ensure efficient and stable operation of the power plant.

[0221] The test goal of this embodiment is to improve the operating efficiency and performance of the power station, reduce energy costs, meet user needs, and achieve good interaction with the power grid to promote the development of smart energy systems through real-time optimization and scheduling.

[0222] Example 5: Emergency response and recovery capability testing, the specific steps are as follows:

[0223] 1) Set up simulation test scenarios for different emergency situations, such as sudden load increase, equipment failure, etc.

[0224] 2) Trigger test scenarios to evaluate the emergency response speed, response capability, and recovery efficiency of the power station.

[0225] 3) Analyze test results, identify existing problems and bottlenecks, and propose improvement suggestions and optimization measures.

[0226] The test goal of this embodiment is to evaluate the power station's ability to cope with emergencies through emergency response and recovery capability testing, improve emergency plans and response mechanisms, and ensure that the power station can respond quickly and resume normal operation in emergencies.

[0227] Through the above examples, we can fully verify the application effect and practical value of the simulation test method disclosed in this application in different aspects, provide guidance and reference for the construction and operation of smart energy systems, and promote the efficient utilization and sustainable development of smart grids and clean energy.

[0228] Reference Figure 7 The second aspect of the present application discloses a pumped storage power station simulation test system 10 compatible with multiple PLCs, comprising:

[0229] The test platform construction module 11 is used to construct a test platform matching the target power station; the test platform integrates a data receiving model, a preset symmetric residual network model, a preset long short-term memory model and a variety of PLC communication protocols, and the data receiving model integrates a universal data interface with a data conversion function;

[0230] A spatial feature processing module 12, configured to process the initial spatial features in the target power station based on a preset symmetric residual network model to obtain first information;

[0231] An analysis module 13 is used to analyze the target equipment parameter information, the actual environmental factor information, and the first information of the target power station based on the constructed data fusion model, and obtain a target operation strategy of the target equipment under different environmental conditions and power station layouts;

[0232] The time series feature processing module 14 is used to process the time series features of the target power station through a preset long short-term memory model to obtain the prediction information of the future operation state of the target power station;

[0233] The acquisition module 15 is used to obtain the guiding operation strategy based on the future operation state prediction information and the target operation strategy.

[0234] The computer device according to the embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0235] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the computer device to perform desired functions. In one embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, so that the computer device executes all or part of the steps of the aforementioned various embodiments of the present disclosure, the pumped-storage power station simulation test method compatible with multiple PLCs.

[0236] Those skilled in the art should be able to understand that in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the protection scope of the present disclosure.

[0237] like Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure is shown, which is a schematic diagram of the structure of a computer device suitable for implementing the embodiment of the present disclosure. Figure 8 The computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0238] like Figure 8 As shown, the computer device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the computer device are also stored. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0239] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as tapes, hard disks, etc.; and communication devices. The communication device can allow the computer device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data. Figure 8 A computer device having various devices is shown, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0240] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of the simulation test method of a pumped-storage power station compatible with multiple PLCs of an embodiment of the present disclosure are executed.

[0241] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0242] According to the computer-readable storage medium of the embodiment of the present disclosure, non-transitory computer-readable instructions are stored thereon. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the simulation test method of a pumped-storage power station compatible with multiple PLCs of the aforementioned embodiments of the present disclosure are executed.

[0243] The above-mentioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (e.g., memory card) and media with built-in ROM (e.g., ROM box).

[0244] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.

[0245] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0246] In the present disclosure, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "include", "comprise", "have", etc. are open words, meaning "including but not limited to"

[0247] The words "or" and "and" as used herein refer to the words "and / or" and are used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" as used herein refers to the phrase "such as but not limited to" and is used interchangeably therewith.

[0248] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0249] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0250] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0251] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0252] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A simulation test method for a pumped storage power station compatible with multiple PLCs, characterized in that: include: Constructing a test platform that matches the target power station; the test platform integrates a data receiving model, a preset symmetric residual network model, a preset long short-term memory model, and multiple PLC communication protocols; the data receiving model integrates a universal data interface with a data conversion function; Processing the initial spatial features in the target power station based on the preset symmetric residual network model to obtain first information; Analyze the target equipment parameter information, the actual environmental factor information, and the first information of the target power station based on the constructed data fusion model to obtain the target operation strategy of the target equipment under different environmental conditions and power station layouts; Processing the time series characteristics of the target power station through the preset long short-term memory model to obtain the prediction information of the future operation state of the target power station; Based on the future operation state prediction information and the target operation strategy, a guiding operation strategy is obtained.

2. The simulation test method for a pumped storage power station compatible with multiple PLCs according to claim 1 is characterized in that: The processing of the initial spatial features in the target power station based on the preset symmetric residual network model to obtain the first information includes: Preprocessing the extracted key spatial features of the target power station to obtain a first spatial feature; Based on the first spatial feature, a spatial training set and a spatial test set are obtained; YY+232026P Construct a preset symmetric residual network model; Training the preset symmetric residual network model based on the spatial training set, and testing the trained preset symmetric residual network model using the spatial test set; Analyze the first spatial feature based on the trained preset symmetric residual network model to obtain the first information; The first information includes the actual layout of several key spatial structures of the target power station, several potential abnormal problems, and a layout optimization plan.

3. The simulation test method for a pumped storage power station compatible with multiple PLCs according to claim 2 is characterized in that: The key spatial features include at least one of the geographical location features of the power station, the structural layout features of the power station, the distribution features of the power station equipment, the distance relationship between different equipment, the equipment distribution density, the layout parameters of important equipment, the hot spot area information, the pipeline layout, the unit location, and the control room layout; The important equipment layout parameters include at least one of generator set parameter information, transformer parameter information, and switchgear parameter information.

4. The simulation test method for a pumped storage power station compatible with multiple PLCs according to claim 2 is characterized in that: The method of constructing a preset symmetric residual network model includes: Determine a network structure; the network structure is a symmetrically designed structure, and the basic unit in the network structure is a residual block; A plurality of convolutional layers are configured inside the residual block; the number of input channels and the number of output channels of the convolutional layers are the same, and the convolutional kernel size and step length are consistent; The convolution layer is a 1x1 convolution or a 3x3 convolution; Add an activation function after the convolution layer; the activation function includes ReLU, Leaky YY+232026P ReLU or ELU; Adding a batch normalization layer between the convolutional layer and the activation function; Adding a skip connection between the input and output of the residual block, wherein parameters in the skip connection are shared with parameters inside the residual block; Determine one of the convolutional layers as the input layer of the network; Stacking a plurality of the residual blocks to form a main part of the network, wherein the output of each residual block is used as the input of the next residual block; and a pooling layer or a transition layer is provided between different residual blocks; Configure an output layer; the output layer is a fully connected layer with a softmax activation function or a fully connected layer with a linear activation function; Determine a loss function, an optimizer, and a preset learning rate; the loss function includes one or more of a cross entropy loss function and a mean square error loss function; the optimizer includes one or more of Adam and SGD.

5. The simulation test method for a pumped storage power station compatible with multiple PLCs according to claim 4 is characterized in that: The method of processing the time series characteristics of the target power station by using the preset long short-term memory model to obtain the prediction information of the future operation state of the target power station includes: Preprocessing the extracted key time series features of the target power station to obtain a first time series feature; Obtain a time series training set and a time series test set based on the first time series feature; Construct a preset long and short-term memory model; Training the preset long short-term memory model based on the time series training set, and testing the trained preset long short-term memory model using the time series test set; Based on the trained preset long short-term memory model, future operation state prediction information of the target power station is obtained.

6. The simulation test method for a pumped storage power station compatible with multiple PLCs according to claim 5 is characterized in that: The step of constructing a preset long short-term memory model includes: Determine the model structure; The model structure includes an input layer, multiple LSTM layers and an output layer, and the shape of the input layer matches the dimension of the input data; The LSTM layer includes an input gate, a forget gate and an output gate, each of the LSTM layers has a hidden state and a cell state, and the hidden state and the cell state of each LSTM layer will be passed to the next LSTM layer; The output layer is configured with the number of output units and an activation function; Configure the number of LSTM hidden units, learning rate, batch size, loss function, and optimizer.

7. The simulation test method for a pumped storage power station compatible with multiple PLCs according to claim 4 is characterized in that: The obtaining of the guiding operation strategy based on the future operation state prediction information and the target operation strategy includes: Constructing a manifold regularization model; the manifold regularization model is suitable for processing different types of data, and the manifold regularization model is configured with a target manifold learning algorithm; The manifold regularization model is trained using the first spatial feature and the first temporal feature, and the future operation state prediction information and the target operation strategy are analyzed using the trained manifold regularization model to obtain an energy consumption equipment area; Obtaining the guiding operation strategy based on the energy consumption equipment area; The guiding operation strategy includes one or more of an equipment optimization layout strategy, an equipment upgrade strategy, and an energy scheduling strategy for the corresponding area.

8. A computer device, characterized in that: The computer device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the pumped-storage power station simulation test method compatible with multiple PLCs as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the pumped-storage power station simulation test method compatible with multiple PLCs as described in any one of claims 1-7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images