Secondary equipment test method, device and equipment based on generative large model

Abstract

The present invention relates to the technical field of secondary equipment testing in substations, and discloses a method, device, and equipment for secondary equipment testing based on a generative large model. The method includes obtaining test requirements for different signal specifications, generating test cases according to standard signals through a test case generation model, where the standard signals are obtained based on classification by a standard signal model, and represent signal specifications followed by different substations and / or different secondary equipment; the standard signal model is configured to identify common attributes between device signals of different signal specifications to form standard signals; and using the test cases to perform collaborative testing to form test results. The present invention identifies common attributes between device signals of different signal specifications through the standard signal model to form standard signals, and then generates test cases for collaborative testing with the standard signals, improving the test collaboration, interoperability, and test efficiency between substations and / or secondary equipment with different signal specifications.

Description

Technical Field

[0001] The present invention relates to the technical field of substation secondary equipment testing, and particularly to a method, device, and equipment for secondary equipment testing based on a generative large model. Background Art

[0002] Substation secondary equipment, such as relay protection devices, as a core component of the safe and stable operation of the power grid, its efficient inspection and testing in various links such as factory, grid connection, construction, and commissioning are crucial. The intelligent substation based on the IEC61850 standard provides a basis for the automation and informatization construction of the power system. There are already some automated testing equipment applied to the detection of substation secondary equipment in China, and most of these equipment have certain automated testing functions. Relay protection testers adopting the IEC61850 protocol have been put into use in some power systems, and these instruments can complete some automatic testing tasks through docking with the communication protocol of the equipment.

[0003] Power system real-time digital simulation is a rapidly developing field. Especially abroad, real-time simulation technology has been applied in multiple fields, especially for the testing of power systems and substation secondary equipment. In China, although the digital dynamic real-time simulation system has achieved certain testing functions, its simulation scale and application scenarios still have limitations. The application of system-level testing technology has also been proposed at home and abroad. Especially in the full-station commissioning of intelligent substations, relevant testing technologies and solutions are still in the exploration stage. The existing system-level testing mainly relies on multiple relatively independent testing equipment, such as relay protection testers, time synchronization detection tools, etc. These equipment usually only test a single equipment or subsystem, lacking a comprehensive verification of the entire secondary system. For example, in the face of system-level testing between substations with different signal specifications or between different secondary equipment, generally, multiple relatively independent substation systems or independent secondary equipment are tested separately.

[0004] Although the current automatic testing of substation secondary equipment has improved the testing efficiency to a certain extent, it still faces problems such as low automation level and complex configuration, which seriously restrict the efficient commissioning and acceptance of intelligent substations and secondary equipment. Many units in China have developed automatic testing software or functional modules for digital relay protection testers and have been applied in multiple power supply enterprises, testing institutions, and scientific research institutes across the country.

[0005] However, since the current automated testing of secondary equipment in substations is still limited to single-function testing or subsystem testing, there is a lack of a global view of the entire secondary equipment system in the substation. In addition, there is a wide variety of current secondary equipment in substations (such as relay protection devices), and there are differences in the service models of relay protection devices produced by each manufacturer. There are different signal specifications between different substations or different secondary equipment within a substation. At the same time, the interoperability of different testing equipment and testing software is poor, and it is impossible to conduct collaborative testing and acceptance of multiple systems. Especially in the scenario of collaborative commissioning between multiple substations with different signal specifications or multiple secondary equipment within a substation with different signal specifications, it seriously affects the test collaboration and efficiency of multiple systems.

[0006] Therefore, the existing technology has problems of poor test collaboration and low test efficiency due to different signal specifications between different substations or different secondary equipment. Summary of the Invention

[0007] The present invention provides a method, device, and equipment for testing secondary equipment based on a generative large model to solve the technical problems of poor test collaboration and low test efficiency between different substations using different signal specifications and / or different secondary equipment in a substation.

[0008] The present invention provides a method for testing secondary equipment based on a generative large model, and the method includes:

[0009] Obtain the test requirements of the secondary equipment in the substation; the test requirements at least include equipment test signals with different signal specifications between different substations and / or different secondary equipment in the substation;

[0010] Through a pre-trained test case generation model, generate test cases corresponding to the test requirements according to the standard signals corresponding to the equipment test signals; the standard signals are obtained by classifying the equipment signals of the secondary equipment in the substation based on a standard signal model, and are used to represent the signal specifications uniformly followed by some or all different substations and / or some or all different secondary equipment in the substation; the standard signal model is configured to identify the common attributes between equipment signals with different signal specifications to form the standard signals;

[0011] Use the test cases to conduct collaborative testing on the different substations and / or different secondary equipment in the substation to generate test results corresponding to the test requirements.

[0012] The present invention identifies the common attributes of device signals with different signal specifications through a standard signal model, and forms a standard signal that represents the signal specification uniformly followed; furthermore, test cases for collaborative testing between substations with different signal specifications and / or different secondary devices are generated using the standard signal, which can improve the test collaboration between substations and / or secondary devices with different signal specifications. In addition, using the standard signal can ignore the signal differences between different signal specifications, improve the interoperability between substations and / or secondary devices with different signal specifications, and thus improve the test efficiency.

[0013] Furthermore, the present invention also provides a secondary device test apparatus based on a generative large model, and the apparatus includes:

[0014] A test requirement acquisition module, configured to acquire the test requirements of secondary devices in a substation; the test requirements at least include device test signals with different signal specifications between different substations and / or different secondary devices in a substation;

[0015] A test case generation module, configured to generate test cases corresponding to the test requirements according to the standard signal corresponding to the device test signal through a pre-trained test case generation model; the standard signal is obtained by classifying the device signals of the secondary devices in the substation based on a standard signal model, and is used to represent the signal specification uniformly followed between some or all different substations and / or some or all different secondary devices in a substation; the standard signal model is configured to identify the common attributes between device signals with different signal specifications to form the standard signal;

[0016] A collaborative test module, configured to perform collaborative testing on the different substations and / or different secondary devices in a substation using the test cases to generate test results corresponding to the test requirements.

[0017] In the present invention, the common attributes of device signals with different signal specifications are identified through a standard signal model, and a standard signal that represents the signal specification uniformly followed is formed; furthermore, the test case generation module generates test cases for collaborative testing between substations with different signal specifications and / or different secondary devices using the standard signal, which can improve the test collaboration between substations and / or secondary devices with different signal specifications. In addition, using the standard signal can ignore the signal differences between different signal specifications, improve the interoperability between substations and / or secondary devices with different signal specifications, and thus improve the test efficiency.

[0018] Furthermore, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for testing secondary devices based on a generative large model as provided above is implemented.

[0019] The secondary equipment test method, device, and equipment based on a generative large model provided by the embodiments of the present invention have the following beneficial effects compared with the prior art:

[0020] The present invention obtains equipment test signals with different signal specifications between different substations and / or different secondary equipment in a substation; through a pre-trained test case generation model, test cases corresponding to test requirements are generated according to the standard signals corresponding to the equipment test signals; the test cases are used to perform collaborative testing on different substations and / or different secondary equipment in a substation, and test results corresponding to the test requirements are generated. By using a standard signal model to identify the common attributes of equipment signals with different signal specifications, a standard signal representing a uniformly followed signal specification is formed; furthermore, test cases for collaborative testing between substations and / or different secondary equipment with different signal specifications are generated using the standard signal, which can improve the test collaboration between substations and / or secondary equipment with different signal specifications. In addition, using the standard signal can ignore the signal differences between different signal specifications, improve the interoperability between substations and / or secondary equipment with different signal specifications, and thus improve the test efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a schematic flowchart of an embodiment of a secondary equipment test method based on a generative large model provided by the present invention;

[0022] Figure 2 is a schematic structural diagram of an embodiment of a secondary equipment test device based on a generative large model provided by the present invention;

[0023] Reference numerals: 201, test requirement acquisition module; 202, test case generation module; 203, collaborative test module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] The present invention obtains device test signals with different signal specifications between different substations and / or different secondary devices in a substation; through a pre-trained test case generation model, test cases corresponding to test requirements are generated according to the standard signals corresponding to the device test signals; the test cases are used to co-test different substations and / or different secondary devices in a substation to generate test results corresponding to the test requirements. By using a standard signal model to identify the common attributes of device signals with different signal specifications, a standard signal representing the signal specifications uniformly followed is formed; furthermore, on the basis of obtaining device test signals with different signal specifications between different substations and / or different secondary devices in a substation, test cases for co-testing between substations with different signal specifications and / or different secondary devices are generated using the standard signal, which can improve the test coordination between substations and / or secondary devices with different signal specifications. In addition, using the standard signal can ignore the signal differences between different signal specifications, improve the interoperability between substations and / or secondary devices with different signal specifications, and thus improve the test efficiency.

[0026] See Figure 1 , Figure 1 FIG. is a schematic flowchart of an embodiment of a method for testing secondary devices based on a generative large model provided by the present invention. As Figure 1 shown, the method includes S101 - S103, which are specifically as follows:

[0027] S101: Obtain the test requirements of the secondary devices in the substation; the test requirements at least include device test signals with different signal specifications between different substations and / or different secondary devices in the substation;

[0028] S102: Through a pre-trained test case generation model, generate test cases corresponding to the test requirements according to the standard signals corresponding to the device test signals; the standard signals are obtained by classifying the device signals of the secondary devices in the substation using a standard signal model, and are used to represent the signal specifications uniformly followed between some or all different substations and / or between some or all different secondary devices in the substation; the standard signal model is configured to identify the common attributes between device signals with different signal specifications to form the standard signal;

[0029] S103: Use the test cases to co-test the different substations and / or different secondary devices in the substation to generate test results corresponding to the test requirements.

[0030] In order to achieve collaborative testing of different substations and / or different secondary equipment in a substation, first, obtain the test requirements of the substation secondary equipment. Among them, the test requirements at least include equipment test signals with different signal specifications between different substations and / or different secondary equipment in a substation. That is, the equipment test signals of different substations have different signal specifications, and the equipment test signals between different secondary equipment in a substation also have different signal specifications.

[0031] Furthermore, through a pre-trained test case generation model, determine the standard signals corresponding to the equipment test signals. Among them, the standard signals are obtained by classifying the equipment signals of the substation secondary equipment based on a standard signal model, and are used to represent the signal specifications uniformly followed between some or all different substations and / or between some or all different secondary equipment in a substation. And the standard signal model is configured to identify the common attributes between equipment signals with different signal specifications to form the standard signals. That is, the standard signals corresponding to the equipment test signals with different signal specifications between different substations can be identified through the standard signal model, and / or, the standard signals corresponding to the equipment test signals with different signal specifications between some or all different secondary equipment in a substation can be identified.

[0032] Then, test cases corresponding to the test requirements can be generated according to the standard signals corresponding to the equipment test signals. Finally, use the test cases to perform collaborative testing on the different substations and / or different secondary equipment in a substation to generate test results.

[0033] The present invention identifies the common attributes of equipment signals with different signal specifications through a standard signal model to form standard signals representing uniformly followed signal specifications; furthermore, uses the standard signals to generate test cases for collaborative testing between substations and / or different secondary equipment with different signal specifications, which can improve the test collaboration between substations and / or secondary equipment with different signal specifications. In addition, using standard signals can ignore the signal differences between different signal specifications, improve the interoperability between substations and / or secondary equipment with different signal specifications, and thus improve the test efficiency.

[0034] In a further embodiment, the construction process of the standard signal model includes:

[0035] Obtain a first set of equipment signals of the substation secondary equipment; the first set of equipment signals includes standard signals corresponding to equipment signals with different signal specifications between different substations and / or different secondary equipment in a substation and data labels corresponding to each of the standard signals;

[0036] Perform preprocessing on the first set of equipment signals; the preprocessing at least includes data cleaning;

[0037] Dividing the preprocessed first device signal set into at least a training set and a validation set;

[0038] The standard signal model constructed by training with the training set is used to identify the common attributes of equipment signals with different signal specifications between different substations and / or different secondary equipment in the substation to form the standard signal, and the standard signal model is verified with the verification set until the iteration termination condition is met to obtain the trained standard signal model.

[0039] In this embodiment, the whole process operation of substation secondary equipment (e.g., relay protection device) testing is unified through process standardization and intelligent business modeling. Based on artificial intelligence and big data technology, the process visualization and operation standardization are realized by building a standard signal model. The model is dynamically optimized through simulation verification and adaptive adjustment mechanism to improve the consistency and efficiency of the test, while meeting the requirements of multi-scenario and multi-device testing. The continuously optimized standard signal model helps to reduce operational errors and improve test quality and efficiency.

[0040] The standard signal model of the secondary equipment of the substation needs to reflect in detail the various states, actions and communication signals of the equipment under different operating conditions. According to the different stages of equipment operation and the types of equipment failures, the standard signal model should cover the following main signals:

[0041] (1) Normal operation status signal

[0042] System normal status signal: such as "normal operation signal", indicating that the equipment is in a fault-free working state and the protection device is not in operation. Working current and voltage signal: monitor the current and voltage values in the operation of the power grid to ensure that they are within the normal working range.

[0043] (2) Protection action signal

[0044] Trip signal: When the relay protection device identifies a fault and triggers a trip command, the trip signal is activated and the alarm system will alarm in time. Alarm signal: Alarm status triggered by protection signals such as overcurrent, overvoltage, and undercurrent. Protection release signal: After the fault is eliminated, the relay protection device releases the trip and resumes operation, sending a release signal.

[0045] (3) Abnormal / fault status signal

[0046] Fault location signal: For example, in the case of short circuit fault, ground fault, etc., the system will generate a location signal to help locate the fault source. Alarm status signal: For example, in the case of abnormal working conditions such as overload and undervoltage, the system will trigger an alarm signal. Maintenance status signal: When the device enters maintenance or test mode, the system generates a maintenance signal to shield the normal protection action.

[0047] (4) Communication messages

[0048] GOOSE (Generic Object Oriented Substation Event) signals: Used for real-time data exchange between relay protection devices, especially when coordinating actions between relay protection devices and switchgear. SV (Sampled Value) signals: Used to transmit digitized sampled values in the power system, such as numerical signals of current and voltage. MMS (Multimedia Message Service) signals: Used for remote control and data acquisition between devices, especially for remote configuration and management between monitoring systems and relay protection devices.

[0049] The standard signal model is used to uniformly define the signal format and content of relay protection devices and ensure signal interoperability between different devices and manufacturers. Artificial intelligence technologies, especially machine learning and / or deep learning algorithms, can be introduced to automatically learn the model files of secondary equipment in different substations by machines and automatically integrate key information in the model files to achieve automated standard signal modeling.

[0050] Among them, the construction of the standard signal model mainly includes: signal acquisition, signal annotation, signal preprocessing, signal feature extraction, model training, model evaluation and optimization, standard signal model generation, etc.

[0051] Signal acquisition: Obtain the first set of device signals of secondary equipment in the substation; the first set of device signals includes standard signals corresponding to device signals with different signal specifications between different substations and / or different secondary equipment in the substation, and data tags corresponding to each standard signal. First, a large amount of signal data needs to be collected from various relay protection devices, which may include the operating status, action signals, communication signals, etc. of different secondary equipment.

[0052] Specifically, a distributed sensor network and data acquisition terminals can be used to comprehensively collect the first set of device signals from secondary equipment (relay protection devices) in the substation. The first set of device signals covers devices of different manufacturers, models, and operating years, as well as signals under various working conditions such as normal operation, fault, and maintenance, including working current, voltage signals, protection action signals (tripping, alarm, etc.), abnormal / fault status signals (fault location, alarm, etc.), and communication messages (GOOSE, SV, MMS signals). The multi-source data fusion technology is used to integrate data from different communication interfaces and protocols to ensure the integrity and consistency of the data. In addition, the first set of device signals includes data tags corresponding to standard signals of device signals with different signal specifications between different substations and / or different secondary equipment in the substation.

[0053] Exemplarily, among the first device signal set, the device signals of Substation A1 and Substation A2 have different signal specifications, and the device signals with different signal specifications of Substation A1 and Substation A2 have corresponding data tags of the standard signal A. Or, the device signals of secondary device a11 and secondary device a12 in Substation A1 have different signal specifications, and the secondary device signals with different signal specifications of secondary device a11 and secondary device a12 have corresponding data tags of the standard signal a.

[0054] Signal annotation: Organize professionals to annotate the device signals in the collected first device signal set. According to the device operating status and signal characteristics, annotate the category of the standard signal to which the data belongs. For example, normal operating signals are annotated as "normal", and trip signals are annotated as "protection action - trip", etc. For complex fault signals, details such as the fault type and fault occurrence time are annotated to provide accurate label data for subsequent model training.

[0055] Signal preprocessing (data cleaning): Preprocess the first device signal set; the preprocessing includes at least data cleaning. Through data cleaning and preprocessing, artificial intelligence technology identifies and extracts effective signals and eliminates redundant data.

[0056] Specifically, an outlier detection algorithm based on statistics, such as the 3σ criterion, can be used to identify and eliminate abnormal device signals in the first device signal set that significantly deviate from the normal range. For the problem of missing data, according to the time series characteristics of the data, linear interpolation, polynomial interpolation, or the K-nearest neighbor interpolation algorithm based on machine learning is used for filling. At the same time, data smoothing algorithms, such as the moving average method and median filtering method, are used to remove noise interference in the data and improve data quality. Furthermore, the first device signal set after preprocessing (data cleaning) is obtained. The data is standardized to map data with different dimensions to the same numerical interval, such as [0,1] or [-1,1]. Common standardization methods include min-max standardization, Z-score standardization, etc., to improve the model training effect.

[0057] Signal feature extraction: Extract and select features from the device signals in the cleaned first device signal set. For numerical device signals, calculate statistical features, such as mean, variance, standard deviation, maximum value, minimum value, etc.; for time series device signals, methods such as Fourier transform and wavelet transform are used to extract frequency domain features. The correlation analysis algorithm, such as the Pearson correlation coefficient, is used to screen out features closely related to signal modeling, reduce the data dimension, and improve the model training efficiency. For communication message data, features such as message length, message sending frequency, and specific field values are extracted. In addition, some features with physical meanings, such as power factor and impedance, can be constructed in combination with the professional knowledge of the power system.

[0058] In addition, a feature selection algorithm is used to screen out the feature subset that contributes the most to model classification from the numerous extracted features. Common feature selection methods include filtering methods (such as chi-square test, information gain), wrapper methods (such as recursive feature elimination), and embedding methods (such as decision tree-based feature selection). Through feature selection, not only can the data dimension be reduced, the model training time be shortened, but also the impact of redundant information between features on the model performance can be avoided, and the generalization ability of the model can be improved.

[0059] Model training: The preprocessed first device signal set is at least divided into a training set and a validation set; the constructed standard signal model is trained using the training set to identify the common attributes of device signals with different signal specifications between different substations and / or different secondary devices in a substation to form a standard signal, and the validation set is used to validate the standard signal model until the iteration termination condition is met to obtain a trained standard signal model. Machine learning algorithms (such as clustering algorithms, decision trees, etc.) can help identify the signal similarities between different secondary devices and classify and model the signals. Deep learning methods (such as convolutional neural networks, recurrent neural networks, etc.) can be used for more complex signal modeling. Through training on a large amount of historical signal data, a standard signal model for classification and recognition and a standard signal that meets the standard are automatically generated.

[0060] (1) Model training based on machine learning:

[0061] Decision tree model: A standard signal model is constructed using a decision tree algorithm (such as C4.5, CART). According to metrics such as information gain or Gini index of features, the optimal splitting attribute is selected, and the data set is gradually divided into different sub-nodes to form a decision tree structure. During the construction of the standard signal model, by setting appropriate pruning strategies (such as pre-pruning, post-pruning), overfitting of the decision tree is prevented. The decision tree model is trained using the training data set, and the parameters of the model, such as the maximum depth, minimum sample number, etc., are adjusted to obtain the best classification performance.

[0062] Random forest model: A standard signal model of a random forest is constructed based on the decision tree model. Multiple sample subsets are randomly drawn from the training data set with replacement, and a decision tree is constructed for each sample subset, finally forming a forest containing multiple decision trees. During prediction, the prediction results of multiple decision trees are integrated, and the final classification result is determined by voting or averaging, etc. By introducing randomness, the random forest enhances the generalization ability of the model and reduces the risk of overfitting. During the training process, the parameters of the random forest, such as the number of trees, the size of the feature subset, etc., are adjusted to optimize the model performance.

[0063] Support Vector Machine (SVM) model: For linearly separable and non-linearly separable device signals, linear SVM and non-linear SVM (such as using kernel functions, such as radial basis function RBF, polynomial kernel function, etc.) are respectively used for classification to construct a standard signal model. By finding an optimal classification hyperplane to maximize the margin between two types of data, the classification of data is achieved. The SVM model is trained using training data, and the parameters of the model, such as the penalty parameter C, kernel function parameters, etc., are adjusted to improve the classification accuracy of the standard signal model.

[0064] (2) Model training based on deep learning:

[0065] Convolutional Neural Networks (CNN) model: For device signals with certain structures and local features (such as signal data converted into image form after preprocessing), the CNN model is used for classification. The CNN model structure is designed, usually including a convolutional layer, a pooling layer, and a fully connected layer. The convolutional layer slides the convolutional kernel over the data for convolution to extract the local features of the data; the pooling layer is used to reduce the data dimension, reduce the amount of calculation, and at the same time retain important features; the fully connected layer comprehensively classifies the extracted features. The CNN model is trained using the backpropagation algorithm and a stochastic gradient descent optimizer (such as Adagrad, Adadelta, Adam, etc.), and the weights and biases of the model are adjusted to enable the model to accurately identify and classify signal data.

[0066] Recurrent Neural Network (RNN) and its variant models: Considering the temporal characteristics of device signal data, RNN or its variants (such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU)) are used for modeling. Taking LSTM as an example, through the coordinated action of the input gate, forget gate, and output gate, the long-term dependence relationship in the signal is effectively processed. The temporal data of the device signal is input into the LSTM network at each time step. The network learns the changing features of the signal at each time step and passes the information to the next time step. Similarly, the LSTM model is trained using the backpropagation algorithm and a suitable optimizer to enable it to accurately predict and classify the temporal changes of the signal. During the training process, the parameters of the LSTM model, such as the number of hidden layer units, the number of layers, etc., are adjusted to optimize the model performance.

[0067] The above standard signal model obtained through training based on machine learning and / or deep learning can identify the common attributes of device signals with different signal specifications among different substations and / or different secondary devices in a substation during the training process, so as to form standard signals corresponding to device signals with different model specifications. The common attributes of device signals with different signal specifications can be, for example, signal content, signal format, and signal representation form, etc.

[0068] Model evaluation metric selection: Multiple evaluation metrics are used to comprehensively evaluate the trained model. For the classified standard signal model, common evaluation metrics include accuracy, recall, F1-score, precision, etc. Accuracy measures the proportion of samples correctly classified by the model; recall reflects the model's ability to identify positive samples; the F1-score comprehensively considers accuracy and recall and more comprehensively evaluates the model's performance; precision represents the proportion of samples actually being positive samples among those predicted as positive samples by the model. In addition, a confusion matrix can also be used to intuitively display the classification situation of the model in each category.

[0069] Model optimization strategy: Optimize the standard signal model according to the evaluation results. If the standard signal model shows overfitting, regularization techniques (such as L1 and L2 regularization, Dropout, etc.) are used to constrain the complexity of the model and prevent the model from overlearning the noise and details in the training data. For the underfitting standard signal model, increase the complexity of the model, such as increasing the number of layers or neurons in the neural network, adjusting the hyperparameters of the model (such as learning rate, number of iterations, etc.), or trying to use a more complex model structure. At the same time, cross-validation techniques (such as K-fold cross-validation) are adopted. The training dataset is divided into multiple subsets, and one subset is alternately used as the validation set, and the remaining subsets are used as the training set. The standard signal model is trained and evaluated multiple times to ensure the reliability and stability of the model's evaluation results. By continuously optimizing the standard signal model, improve the accuracy and generalization ability of the standard signal model for signal classification modeling.

[0070] Among them, the iteration termination condition can include one or more of the aforementioned accuracy, recall, F1-score, and precision satisfying the corresponding metric thresholds, such as the accuracy threshold or the precision threshold. The iteration termination condition can also include that the number of training iterations of the standard signal model satisfies the preset iteration number threshold.

[0071] Standard signal model generation: Package and serialize a model trained based on machine learning and / or deep learning to generate a standard signal model. The standard signal model should include the model's structural information (such as the number of layers and nodes in a neural network, the structure of a decision tree, etc.), the trained model parameters (weights, biases, etc.), and the model's metadata (such as model name, training time, evaluation metrics, etc.). The format of the standard signal model can be selected from common serialization formats such as Pickle (suitable for machine learning models in Python), HDF5 (suitable for deep learning models), etc., to facilitate model storage, transmission, and subsequent use. The generated standard signal model can be used as a standardized device signal classification modeling tool and applied to the testing and diagnosis of secondary substation equipment to achieve accurate classification and identification of signals under different equipment and operating conditions.

[0072] In the embodiment of the present invention, based on the first device signal set of the secondary substation equipment collected, a machine learning and / or deep learning training can be used to construct the standard signal model, so as to identify the common attributes of device signals with different signal specifications to form standard signals, quickly identify the device signals of secondary substation equipment, classify them to form corresponding standard signals, improve the interoperability and test collaboration between device signals with different signal specifications, and improve the test efficiency.

[0073] In a further embodiment, the method further includes:

[0074] Fuse at least two standard signal models constructed and trained through machine learning and / or deep learning to obtain a fused standard signal model.

[0075] Specifically, use model fusion technology to fuse multiple different standard signal models (such as decision trees, random forests, SVMs, CNNs, LSTMs, etc.) to improve the overall performance of the standard signal model. Common model fusion methods include voting methods (hard voting, soft voting), averaging methods, stacking methods, etc. The voting method is to let multiple models vote and select the category with the most votes as the final prediction result; the averaging method is applicable to regression models and obtains the final predicted value by averaging the prediction results of multiple standard signal models; the stacking method is to use a meta-model to fuse the prediction results of multiple base models. In practical applications, select a suitable fusion method according to the performance and characteristics of different standard signal models to improve the accuracy and robustness of the standard signal model.

[0076] In this embodiment, multiple standard signal models are fused to obtain a fused standard signal model, which can improve the performance and robustness of the standard signal model.

[0077] In a further embodiment, the categories of the standard signal model include: the standard signal model for the device operation stage, the standard signal model for the device failure type, the standard signal model for the device signal nature, and the standard signal model for the device type;

[0078] In S102, generating the test cases corresponding to the test requirements according to the standard signals corresponding to the device test signals includes:

[0079] Generating the test cases corresponding to the test requirements according to at least one category of the standard signals corresponding to the device test signals.

[0080] When constructing the standard signal model, the present invention can hierarchically classify the standard signal model from four key factors and standards of the device operation stage, failure type, signal nature, and device type, improving the systematicness, accuracy, and adaptability of the model.

[0081] Based on the device operation stage: The prior art often does not fully consider the different stages of device operation. The present invention takes the device operation stage as a key factor and further divides the standard signal model into standard signal models for stages such as normal operation, protection action, abnormality / failure, maintenance, or testing. In the normal operation stage, key monitoring is carried out on the normal state signals of the system, working current, and voltage signals to ensure that the device is free of faults and the grid operation parameters are normal; the protection action stage focuses on signals such as tripping, alarming, and protection release to clarify the device state changes during the occurrence and handling of faults; in the abnormality / failure stage, device problems are discovered and located in a timely manner through signals such as fault location and alarm status; in the maintenance or testing stage, the maintenance state signals are used to shield normal protection actions to ensure the safe progress of maintenance and testing work. This hierarchical classification method systematically covers the signal monitoring requirements of the entire life cycle of the device, providing comprehensive data support for testing and differing from the scattered monitoring mode of the prior art.

[0082] According to the device failure type: Hierarchically classifying the standard signal model according to the failure type is another major feature of the present invention. Fault location signals generated for different failure types such as short - circuit faults and ground faults, as well as alarm signals triggered by abnormal states such as over - load and under - voltage, are classified and managed. In this way, during the test process, the signal changes of the device under different failure types can be accurately identified, and the device failure situation can be quickly judged. The prior art may lack such detailed classification monitoring of failure types and it is difficult to accurately locate problems in complex fault scenarios.

[0083] According to the nature of device signals: Based on the signal nature, the present invention classifies signals into categories such as system normal state signals, protection operation signals, abnormal / fault state signals, and communication messages (GOOSE signals, SV signals, MMS signals), etc., to form standard signal models with different signal natures. Signals with different natures perform different functions in the power system. Hierarchical classification of signals with different natures helps to clearly define the uses and scopes of signals. For example, GOOSE signals are used for real-time data exchange and coordinated actions between relay protection devices, SV signals transmit digital sampling values, and MMS signals enable remote control and data acquisition between devices. Through this hierarchical classification, for the standard signal models of different signal natures during testing, targeted monitoring and analysis can be carried out for signals with different natures. However, the prior art may not be able to classify and manage signals so systematically, resulting in chaotic signal analysis during the testing process.

[0084] Based on device types: When constructing the standard signal model, signals are modeled in combination with different device types (such as relay protection devices, measurement and control devices, intelligent terminals, merging units, etc.). Different devices have different functions in the power system and generate signals with their own characteristics. For example, relay protection devices focus on protection operation signals, and measurement and control devices focus on telemetry and telecontrol signals. The present invention realizes precise management of signals from different devices in this way to form standard signal models corresponding to different device types, enabling the test templates to better adapt to different devices and improving the pertinence and accuracy of testing. This is an aspect that has not been fully emphasized in the prior art, and the prior art may adopt a unified test mode, ignoring the differences between devices.

[0085] The present invention classifies and grades the standard signal model through key factors such as the device operation stage, device fault type, device signal nature, and device type, improving the systematicness and adaptability of the standard signal model.

[0086] In a further embodiment, in step S102, generating the test cases corresponding to the test requirements according to the standard signals corresponding to the device test signals by the pre-trained test case generation model includes:

[0087] Extracting the device test signals included in the test requirements according to the test case generation model;

[0088] Determining the standard signals corresponding to the device test signals based on the signal mapping model; the signal mapping model at least includes the mapping rules between the device test signals and the standard signals;

[0089] Generating the initial test cases corresponding to the test requirements in a template configuration manner according to the standard signals by the test case generation model; the initial test cases at least include the standard signals corresponding to the device test signals, the test process, and the test results;

[0090] Instantiate the standard signals in the initial test case into the device test signals to form the instantiated test case.

[0091] When generating a test case, first, extract the device test signals included in the test requirements through a test case generation model. Furthermore, determine the standard signals corresponding to the device test signals based on a signal mapping model. The signal mapping model at least includes the mapping rules between the device test signals and the standard signals, and the standard signals corresponding to the device test signals can be obtained through the signal mapping model based on the mapping rules. Then, after obtaining the standard signals, generate the initial test case corresponding to the test requirements in a template configuration manner. Finally, instantiate the initial test case, instantiate the standard signals into device test signals, and thus obtain the instantiated test case.

[0092] In the embodiment of the present invention, determining the standard signals corresponding to the device test signals through the signal mapping model can improve the efficiency of determining the standard signals; furthermore, generating test cases in a template configuration manner based on the standard signals can improve the flexibility and scalability of the test cases.

[0093] In a further embodiment, the generating, by the test case generation model, the initial test case corresponding to the test requirements in a template configuration manner according to the standard signals includes:

[0094] Through the test case generation model, generate the initial test case corresponding to the test requirements in a template configuration manner according to the standard signals included in at least one of the prompt type, judgment type, pressure plate control type, and overall output fault type.

[0095] Through modular design, the present invention subdivides the test process in the test case into combinable small modules to achieve fast adaptation for multiple devices and multiple scenarios. Utilize an automated template generation tool to generate test scripts based on standard signals, and at the same time support dynamic loading and adjustment of templates to adapt to actual changes. The template system integrates an automated report generation function, and through real-time data filling and version control, realizes the rapid output and unified management of test reports, significantly improving the template configuration efficiency and flexibility.

[0096] Edit the initial test template based on the standard signals defined by the standard signal model to ensure that the generated initial test template has the characteristics of flexible editability and generality, and initial test templates including one-key testing of protection monomers, one-key testing of the overall loop, etc. can be generated through template editing.

[0097] The so-called template configuration technology refers to generating test case templates through flexible editing, rather than solidifying test cases through test instruments. This ensures that the test templates can be applied to different test purposes and scenarios, and can also be made suitable for differentiated requirements through simple template editing. Through complex global information modeling and test case configuration, a whole-station system-level joint automatic debugging solution can be formed, including single-function debugging of relay protection devices, integrated loop debugging of relay protection devices, remote control point matching, recorder acceptance, etc.

[0098] One-key configuration and flexible adjustment: The generation of test templates can be automatically completed through the "one-key" configuration function. Testers only need to provide necessary test requirement parameters, and the system can generate corresponding test templates. At the same time, testers can adjust the template configuration through simple operations to meet the differentiated requirements on-site.

[0099] The specific method is to sort out the device test signals required according to the possible test items and test purposes in the test requirements, specifically including MMS signals and GOOSE signals of various types of relay protection, as well as MMS signals, GOOSE signals of measurement and control, GOOSE signals of intelligent terminals, GOOSE signals and SV signals of merging units, etc. These are uniformly modeled according to the device form, and the above signal sets form a standard signal database with the device as the object.

[0100] According to the test items or test tasks in the test requirements, sort out their test key points. For example, based on a specific integrated test report form, analyze the prerequisite conditions to be met, the signal states to be applied, and the action results to be checked for each specific test sub-item. Then, complete the configuration of the corresponding initial test cases through the standard signals in the standard signal database. The configuration of this initial test case supports configuring test sub-items in a time-sequential manner and combining them into specific test tasks, and finally forms a complete initial test case. This initial test case is generated through template configuration based on the standard signal database, and it is not based on specific SCD file information or a fixed algorithm, ensuring the scalability and universality of the initial test case.

[0101] The process of template configuration is to generate test templates (test cases) through four basic classes, specifically including prompt class, judgment class, pressure plate control class, and integrated output fault class. By performing logical operations on the states or values of signals such as MMS and GOOSE, judgment results are formed, specifically including:

[0102] Steady-state judgment of tele-signals, which requires being able to judge that the state of a certain tele-signal remains 1 or 0;

[0103] Transient judgment of tele-signals, which requires being able to judge that the state of a certain tele-signal changes from 1 to 0 or from 0 to 1;

[0104] For the judgment of remote signals, it is required to be able to judge the steady-state or transient states of certain remote signals that meet the above two requirements.

[0105] For the relative time judgment of remote signal change signals, it is required to be able to judge the result of comparing the relative time of the state change of a certain remote signal with the set time.

[0106] For the magnitude comparison judgment of telemetry, it is required to be able to judge the result of comparing the magnitude of a certain telemetry signal with the set value.

[0107] The prompt type sends prompt information through the man-machine interaction prompt window to prompt the tester to participate in the operations and inspections of external control conditions, inspection conditions, etc. of the test project requirements, so as to achieve the purpose of operation and inspection required for the overall debugging task. The prompt type can not only solve the problem that some control and judgment operations cannot be implemented by the program and need the participation of the tester to complete, but also solve the situation that may occur during the debugging process where the process is interrupted and it is necessary to set up prompts to prompt the tester to conduct inspections before the subsequent debugging work can continue.

[0108] The pressure plate control type is a category that automatically completes the operations of putting in and taking out the pressure plate and control word during the test process to avoid interference in the test system. Since the same fault output may cause different protection components to act, resulting in interference to the test results, during the normal one-key automatic test process, it is necessary to add control operations of the pressure plate control word between different test projects, only put in the target protection function and withdraw other protection functions to ensure the accurate progress of the test project.

[0109] The whole-group output fault type is a project that requires the test system to output sampled values SV or analog quantity faults for specific test tasks to drive the actions of target protection, measurement and control, etc. equipment. The whole-group output fault is preset for specific debugging objects. For example, line protection should at least include core protection function modules such as differential protection test, distance protection test, zero-sequence overcurrent protection test, etc. The test system can accurately simulate the fault analog quantities required for differential action, distance action, and zero-sequence overcurrent action by obtaining the setting information of the protection online and matching the instantiated mapped analog quantity channel information, and simulate normal operating conditions, fault simulation, and post-fault conditions by setting parameters such as pre-fault parameters, fault parameters, and post-fault parameters, so as to achieve the purpose of simulating specific fault types. The whole-group output fault type also includes basic state sequence functions, which are convenient for testers to conduct whole-group tests according to the state sequences calculated by themselves during configuration. The flexible state sequence functions can also be generated into fixed test cases through configuration, greatly enriching the methods of system-level whole-group debugging.

[0110] The template configuration process is actually a process of configuring the standard signals in the standard signal database through the above four basic classes to form a specific preset configuration logic. This configuration (initial test case) includes the necessary content in the system test process such as information prompt, condition check, signal trigger, and result judgment.

[0111] In a further embodiment, the process of instantiating the standard signals in the initial test case into the device test signals to form an instantiated test case includes:

[0112] Determining the standard signal corresponding to the device signal that matches the device test signal from a pre-configured dictionary index using a similarity measurement method; the dictionary index at least includes device signals, standard signals, and the mapping relationship between device signals and standard signals;

[0113] Instantiating the standard signal corresponding to the device signal that matches the device test signal in the initial test case into the device test signal to form an instantiated test case.

[0114] After classifying device signals into standard signals using the standard signal model, it is then necessary to perform instantiation mapping on these standard signals, that is, mapping the abstract standard signals to the device test signals of specific engineering projects.

[0115] In a further embodiment, the process of determining the standard signal corresponding to the device signal that matches the device test signal from a pre-configured dictionary index using a similarity measurement method includes:

[0116] Determining candidate device signals with a similarity exceeding a preset similarity threshold with the device test signal from the dictionary index using a similarity measurement method based on a corpus and / or knowledge base;

[0117] Determining the device signal with the highest similarity with the device test signal among the candidate device signals, and obtaining the standard signal corresponding to the device signal with the highest similarity from the dictionary index as the standard signal corresponding to the device signal that matches the device test signal.

[0118] The mapping process is a matching process of text information, which can also be understood as semantic similarity matching. Semantic similarity calculation mainly includes two categories: knowledge-based and corpus-based. The knowledge-based similarity calculation method quantifies the semantic association degree between two texts by using the information obtained from the knowledge base. WordNet is a method that solves the problem of text similarity calculation through a dictionary. With the idea of WordNet, the automatic mapping of information can be realized by directly establishing the dictionary index of signals and the corresponding dictionary interpretation relationship.

[0119] The rules of the dictionary index can be defined based on the promulgated protection standardization specifications. For the standardized device test signals, through the combination of simple morpheme expressions and the weighted algorithm of each morpheme weight, the object with the highest similarity in the global is calculated as the associated mapping object; for the non-standardized device test signals, by strengthening the unique feature information of the model, parameters, and description, an iterative dictionary index can be established to solve the problem of signal automatic association mapping.

[0120] The establishment of the dictionary index mainly includes: index structure design, index initialization, index update and maintenance, etc.

[0121] Index structure design: Design an iterative dictionary index structure for storing the key features of signals and the corresponding mapping information (such as the corresponding standard signals, mapping rules, etc.). This index structure can be implemented using data structures such as hash tables, tree structures (such as binary search trees, B-trees), etc. The hash table has the advantage of fast searching and is suitable for the fast retrieval of large-scale data; the tree structure is convenient for range queries and sorting operations. In the index, the key features of the signal are used as keys, and the mapping information of the signal is used as values, that is, stored in the form of key-value pairs.

[0122] Index initialization and filling: According to the key features of the extracted device signals, initialize the dictionary index and fill the relevant information of the signals into the index. During the filling process, for each signal, calculate the hash value of its key features or its position in the tree structure, and store the mapping information of the signal in the corresponding position. For signals with similar features, an association relationship can be established in the index for subsequent fast searching and matching.

[0123] Index update and maintenance: As new device signals continuously appear or the signal features change, update and maintain the dictionary index in a timely manner. When a new device signal is added, calculate its key features and insert it into the appropriate position in the dictionary index. If the features of the device signal change, such as the signal name is modified or the data type is changed, update the relevant information in the index accordingly. Optimize the index regularly, such as cleaning up invalid index items and adjusting the index structure to improve the query efficiency.

[0124] The signal mapping of dictionary indexing mainly includes: multi-source data acquisition, data cleaning and denoising, signal classification and marking, feature extraction and analysis, signal mapping, mapping optimization, etc.

[0125] Multi-source data acquisition: Widely collect signal data from various relevant devices, systems, and document materials. This includes not only various signals generated in real time during device operation, such as protection action signals, alarm signals, measurement signals, etc., but also signal-related information mentioned in the device's technical manuals, design documents, maintenance records, etc. Use data acquisition tools and interfaces to ensure comprehensive acquisition of signal data from different sources and in different formats, providing sufficient materials for subsequent processing.

[0126] Data cleaning and denoising: Clean and denoise the collected data. Since the signal data sources are complex, they may contain a large amount of noise, incorrect data, and duplicate information. Through data cleaning algorithms, identify and eliminate obviously incorrect or abnormal data, such as data with signal values outside the reasonable range or incorrect data formats. At the same time, remove duplicate signal records, reduce data redundancy, improve data quality, and lay a foundation for accurate signal mapping.

[0127] Signal classification and marking: Classify the cleaned data according to the nature, function, and source of the signals. For example, classify signals into major categories such as protection signals, measurement signals, control signals, etc., and then further subdivide each major category. For example, protection signals can be further divided into overcurrent protection signals, differential protection signals, etc. Mark each classified signal and assign it a clear category identifier for quick identification and processing in the future.

[0128] Feature extraction and analysis:

[0129] Key feature identification: Identify the key features of the signals. These features include the signal name, description, data type, occurrence frequency, and association relationship with other signals. The signal name and description may contain important information such as device type and signal function; the data type determines the value range and processing method of the signal; the occurrence frequency can reflect the importance and stability of the signal; the association relationship with other signals helps to understand the role and interaction mode of the signal in the system.

[0130] Feature quantization and encoding: Quantize and encode the identified key features so that they can be processed by computer algorithms. For text information such as signal names and descriptions, natural language processing techniques can be used, such as word vector models (such as Word2Vec, GloVe) to convert the text into a numerical vector representation. For numerical features such as data type and occurrence frequency, perform normalization processing and map them to a specific numerical interval, such as [0,1], for easy comparison and analysis.

[0131] Similarity Metric Method Selection: Determine the method used to measure the similarity of signal features. Commonly used similarity metric methods include Euclidean distance, cosine similarity, edit distance, etc. Euclidean distance is used to measure the distance between numerical vectors, cosine similarity is used to measure the directional similarity between vectors, and edit distance is applicable to comparing the differences between text strings. Based on the type and characteristics of the signal features, select an appropriate similarity metric method to accurately calculate the similarity degree between signals.

[0132] Signal Mapping:

[0133] Processing of Signals to be Mapped: For the device test signals that need to be mapped, first perform feature extraction and quantization processing to obtain their key feature vectors. Then, according to the selected similarity metric method, calculate the similarity score between this signal and the existing device signals in the dictionary index.

[0134] Screening of Mapping Objects: Based on the similarity scores, screen out the device signals with relatively high similarity to the device test signals to be mapped from the dictionary index as potential mapping objects. A similarity threshold can be set, and only signals with similarity scores exceeding the threshold are regarded as potential mapping objects. Sort the screened potential mapping objects according to the similarity scores, and select several signals with the highest scores for further analysis.

[0135] Mapping Decision and Verification: According to certain decision rules, select the final mapping object from the potential mapping objects. The decision rules can comprehensively consider factors such as similarity scores, signal correlation relationships, historical mapping records, etc. For example, if a certain potential mapping object not only has a high similarity to the signal to be mapped but is also frequently associated in historical mappings, then the probability of it being selected as the final mapping object is higher. Or directly take the candidate device signal with the highest similarity as the final mapping object. After determining the mapping object, verify the mapping result. It can be checked whether the mapping is accurate and reasonable through actual system tests, expert reviews, etc. If the verification passes, the signal mapping is completed; if the verification fails, reselect the mapping object or adjust the mapping strategy.

[0136] Mapping Optimization:

[0137] Evaluation of Mapping Results: Conduct a comprehensive evaluation of the mapping results, including the accuracy, integrity, and consistency of the mapping. Accuracy evaluation mainly checks whether the mapped signals match the actual requirements and whether they can correctly reflect the functions and meanings of the signals; integrity evaluation focuses on whether all signals that need to be mapped have been properly processed and whether there are any omissions; consistency evaluation ensures the consistency of the mapping rules and results between different signals, avoiding contradictions and conflicts.

[0138] Feedback adjustment mechanism: Based on the evaluation results, a feedback adjustment mechanism is established. If problems are found in the mapping results, such as mapping errors, incompleteness, or inconsistencies, the problems are fed back to the previous processing steps, such as feature extraction, index establishment, or mapping decision-making. According to the feedback information, the corresponding parameters, rules, or algorithms are adjusted, and the signal mapping is performed again. For example, if it is found that the mapping of a certain signal is always incorrect, it is possible to check whether its feature extraction is accurate and whether the similarity measurement method or mapping decision rule needs to be adjusted.

[0139] Knowledge accumulation and reuse: The successful mapping cases and experiences are accumulated to form a knowledge database. In the subsequent signal mapping process, this knowledge can be reused to improve the efficiency and accuracy of mapping. For example, if an accurate mapping result is obtained for a non-normalized signal after multiple adjustments and verifications, its related features, mapping rules, and verification processes can be recorded. When encountering a similar signal, these experiences can be directly referred to for mapping, reducing the repetitive processing process.

[0140] In a further embodiment, the construction process of the signal mapping model includes:

[0141] Pre-training with general data to obtain a mapping pre-training model; the mapping pre-training model includes a machine learning model and / or a deep learning model;

[0142] Obtaining a second device signal set of substation secondary equipment; the second device signal set at least includes data labels characterizing the mapping relationship between device signals and standard signals;

[0143] Preprocessing the second device signal set; the preprocessing at least includes data cleaning;

[0144] Using the preprocessed second device signal set to fine-tune the mapping pre-training model to obtain a trained signal mapping model.

[0145] The present invention realizes automatic mapping by means of artificial intelligence technology, which is completely different from the mapping methods that rely on a large number of manual operations in the prior art. Using natural language processing (NLP) technology in machine learning, the signal naming rules, signal types, etc. of different devices are converted into standard mapping relationships, and the mapping relationships between different devices and signals are automatically learned through training the model, reducing manual intervention. In the mapping process, the neural network in deep learning adaptively adjusts the signal matching rules, trains according to historical data, and optimizes error detection and correction in the mapping process. Artificial intelligence technology plays a key role in this process, which can effectively improve the accuracy and flexibility of the mapping process.

[0146] Among them, the signal mapping model realizes signal mapping mainly including: data collection, mapping relationship annotation, data cleaning preprocessing, model architecture selection, pre-training and fine-tuning, feature extraction and model training, real-time signal mapping, and mapping correction and optimization.

[0147] Data collection: Obtain the second device signal set of the substation secondary equipment.

[0148] Specifically, signal data is widely collected from various types of relay protection devices, measurement and control equipment and other substation secondary equipment. These data cover signals under various working conditions such as normal operation, failure, and maintenance of the equipment, including working current, voltage signals, protection action signals (such as tripping, alarm), abnormal / fault status signals (such as fault location, alarm) and various communication messages (GOOSE, SV, MMS signals). At the same time, detailed description information of each signal is recorded, including signal name, device type, signal meaning, data format, etc., to form a large-scale signal data set, that is, the second device signal set.

[0149] Mapping relationship label: the second device signal set at least includes a data label representing the mapping relationship between the device signal and the standard signal.

[0150] Specifically, organize power experts and NLP professionals to label the device signals in the collected second device signal set. The focus of labeling is to establish a mapping relationship between different device signals and standard signals. For example, label the "overcurrent trip signal" of a manufacturer's relay protection device as the "protection action-overcurrent trip" signal in the corresponding standard signal set, and record this mapping relationship in detail. For complex signals, multi-level labeling may be required, such as first labeling the major category to which the signal belongs (such as protection action signal), and then labeling the specific subcategory (such as overcurrent trip) to ensure the accuracy and consistency of the labeling.

[0151] Data cleaning preprocessing: preprocessing the second device signal set; the preprocessing at least includes data cleaning.

[0152] Specifically, data cleaning technology is used to remove noise and outliers in signal data. Typos and grammatical errors in signal description information are corrected and the data format is unified. Signal names are standardized, such as converting abbreviations and aliases into standard names. Text segmentation technology is used to split the signal description text into individual words or phrases for subsequent analysis. For example, the "busbar differential protection action signal" is segmented into "busbar", "differential protection", and "action signal". At the same time, a stop word list is used to remove meaningless function words (such as "的", "在", etc.) to reduce data redundancy and improve processing efficiency.

[0153] Select the model architecture: The mapping pre-training model includes a machine learning model and / or a deep learning model.

[0154] Specifically, according to the characteristics of the signal data and the requirements of the mapping task, select an appropriate NLP model architecture, that is, the mapping pre-training model. For simple text classification and mapping tasks, traditional machine learning models such as Naive Bayes and Support Vector Machine can be considered. These models are relatively simple to calculate and have a fast training speed. For complex semantic understanding and mapping tasks, deep learning models perform better, such as pre-training models like BERT (Bidirectional Encoder Representations from Transformers) and GPT (Generative Pre-trained Transformer) based on the Transformer architecture. Taking the BERT model as an example, it has strong semantic understanding ability in natural language processing tasks, can capture the context information in the text, understand the meaning of the signal description more accurately, and thus achieve more accurate mapping.

[0155] Feature extraction and model training: For traditional machine learning models, feature engineering is required. Extract features from the signal description text, such as Bag of Words features, where each word that appears in the text is taken as a feature and its occurrence frequency is counted; TF-IDF (Term Frequency-Inverse Document Frequency) features, which not only consider the occurrence frequency of a word in the text but also the rarity of the word in the entire dataset, and can more accurately reflect the importance of the word. In addition, syntactic features and semantic features of the text can also be extracted. Input the extracted features into the machine learning model for training, adjust the hyperparameters of the model (such as the smoothing parameter in the Naive Bayes model, the kernel function type and penalty parameter in the Support Vector Machine model, etc.), and select the optimal model parameters through methods such as cross-validation to improve the accuracy and generalization ability of the model.

[0156] Pre-training and fine-tuning: Use general data for pre-training to obtain the mapping pre-training model, and use the preprocessed second device signal set to fine-tune the mapping pre-training model to obtain the trained signal mapping model.

[0157] Specifically, if a pre-trained model is selected, first, a large-scale general data is used to pre-train the pre-trained model to learn the general features and semantic representations of the language, obtaining a mapped pre-trained model. Then, the labeled power equipment signal data, that is, the second device signal set at least including data labels representing the mapping relationship between the device signal and the standard signal, is used to fine-tune the mapped pre-trained model. During the fine-tuning process, the device signal description text in the second device signal set is used as the input, and the corresponding standard signal annotation is used as the output. The parameters of the mapped pre-trained model are adjusted through the backpropagation algorithm to make the mapped pre-trained model adapt to the signal mapping task in the power field. For example, in the fine-tuning of the BERT model, the power signal description text is input into the BERT model. After being processed by multiple Transformer layers, the semantic representation of the text is obtained. Then, through a fully connected layer, the semantic representation is mapped to the standard signal. The loss function (such as cross-entropy loss) between the prediction result and the annotation result is calculated, and the model parameters are continuously adjusted through an optimizer (such as the Adam optimizer) to minimize the loss function, thereby improving the performance of the model in the signal mapping task. Finally, the signal mapping model after fine-tuning training is obtained.

[0158] Real-time signal mapping: In practical applications, when new device signal data is input, first, preprocessing is performed on the signal description text, such as word segmentation, stop word removal, etc. Then, the preprocessed text is input into the trained NLP-based signal mapping model, and the signal mapping model outputs the corresponding standard signal. For example, when the "zero-sequence overcurrent alarm signal" of a certain device is input, the signal mapping model calculates and infers, and outputs the category of the standard signal "protection action - zero-sequence overcurrent alarm" corresponding in the standard signal database, realizing real-time signal mapping.

[0159] Mapping correction and optimization: Verify the mapping results output by the signal mapping model. The manual review method can be adopted, and experts in the power field check the mapping results to ensure the accuracy of the mapping. If mapping errors are found, analyze the reasons for the errors, which may be insufficient training data of the signal mapping model, unclear signal description, or limitations of the signal mapping model itself, etc. For errors caused by insufficient training data, collect more relevant signal data, re-label the mapping relationship, and re-train the signal mapping model; for the problem of unclear signal description, communicate with the device manufacturer to obtain more accurate signal description information; for the limitations of the signal mapping model itself, try to adjust the architecture or parameters of the signal mapping model, or combine other technologies (such as rule engines) to correct the mapping results and improve the accuracy and reliability of the mapping.

[0160] With the development of the power system and the replacement of equipment, new signals and mapping relationships are constantly emerging. Therefore, it is necessary to continuously collect new signal data and regularly retrain and update the signal mapping model. At the same time, pay attention to the changes in power field standards, and adjust the standard signal database and mapping relationship annotation in a timely manner to ensure that the signal mapping model can always accurately achieve standard mapping. In addition, continuously optimize the performance of the model, such as improving the processing speed of the model and reducing memory consumption, to meet the needs of large-scale signal data processing.

[0161] Automated mapping and anomaly detection: Through the neural network in deep learning, the signal mapping model can adaptively adjust the signal matching rules during the mapping process, train based on historical data, and optimize error detection and correction during the mapping process. The neural network can learn more complex mapping relationships, automatically determine whether the signal is consistent with the target device, and perform anomaly alarm and correction when errors occur.

[0162] In a further embodiment, the method further includes:

[0163] Dynamically adjust the mapping rules of the signal mapping model through a reinforcement learning algorithm.

[0164] Adopting a reinforcement learning algorithm makes the signal mapping process more intelligent. According to the real-time data and status of the equipment at the engineering site, dynamically adjust the signal mapping rules to adapt to different operating environments, greatly improving the accuracy and flexibility of the mapping.

[0165] Specifically, dynamically adjusting the mapping rules based on the reinforcement learning algorithm includes: defining the reinforcement learning environment, initializing the agent, the reinforcement learning training process, and dynamically adjusting the mapping rules.

[0166] I. Define the reinforcement learning environment

[0167] State space definition: The state space needs to comprehensively reflect the relevant information of the current mapping task, including the characteristics of the current signal to be mapped, the established mapping relationships, historical mapping results, and the system operating status, etc. Signal characteristics cover signal name, type, affiliated equipment, etc.; the established mapping relationships include previous successful or failed mapping records; historical mapping results record whether the mapping is accurate and the corresponding feedback; the system operating status includes factors affecting mapping decisions such as equipment load and network communication quality. These information constitute the state vector, which serves as the basis for the decision-making of the reinforcement learning agent.

[0168] Action Space Definition: The action space refers to the set of action adjustments for mapping rules that an intelligent agent can take. It includes adding new mapping rules, such as establishing associations with standard signals based on new features of signals; modifying existing rules, adjusting signal matching conditions or target mappings; deleting unreasonable rules to remove those that cause incorrect mappings; and adjusting rule priorities to change the execution order of different rules according to actual situations to optimize the mapping decision-making process.

[0169] Reward Function Design: The reward function is the key to guiding the intelligent agent to learn the optimal policy. A positive reward is given when the mapping is accurate, such as successfully mapping a certain complex signal correctly to a standard signal, and corresponding rewards are given according to the importance of the signal, with more important signals receiving higher rewards. A negative reward is given for incorrect mappings, and different penalty intensities are set according to the severity of the error, with more severe errors that affect the system operation receiving heavier penalties. In addition, if the mapping process improves the system efficiency or stability, such as reducing the mapping time or lowering the system resource occupancy, an additional reward is also given, and vice versa for penalties, prompting the intelligent agent to improve the overall performance of the system while ensuring mapping accuracy.

[0170] II. Intelligent Agent Initialization

[0171] Select a Reinforcement Learning Algorithm: Algorithms such as Deep Q-Network (DQN), Policy Gradient algorithms (such as A2C, A3C, PPO), or algorithms based on the Actor-Critic architecture (such as DDPG, TD3) can be selected. Taking DQN as an example, it approximates the Q-value function through a neural network, balances exploration and exploitation, and is suitable for solving problems with discrete action spaces, and has good performance in action selection problems such as mapping rule adjustments.

[0172] Initialize Intelligent Agent Parameters: Construct a neural network model as the decision-making model of the intelligent agent. If DQN is used, the network structure includes an input layer, a hidden layer, and an output layer. The input layer receives the state vector, the hidden layer performs feature extraction and processing, and the output layer outputs the Q-values for each action. Randomly initialize the network weights and set hyperparameters such as the learning rate, discount factor, and size of the experience replay buffer. The learning rate controls the step size of weight updates, the discount factor determines the importance of future rewards, and the experience replay buffer is used to store and reuse historical experiences to prevent the intelligent agent from relying too much on current experiences and improve learning stability.

[0173] III. Training Process

[0174] Environment Interaction and Experience Collection: The intelligent agent selects an action (mapping rule adjustment plan) from the action space according to the current state, executes this action in the actual mapping task, observes the mapping result and obtains the new state and reward. Record the state, action, reward, and new state into the experience replay buffer. As the training progresses, a large amount of historical experiences accumulate in the buffer.

[0175] Experience replay and model update: Randomly sample a batch of experience data from the experience replay buffer and input it into the neural network for training. Calculate the Q-value estimate for each action taken in the current state and update the Q-value according to the Q-learning formula. Adjust the neural network weights through backpropagation algorithm to make the Q-value estimate closer to the true value and improve the decision-making ability of the agent.

[0176] Exploration and exploitation balance: In the initial stage of training, since the agent has limited understanding of the environment, a larger exploration probability (such as a larger value in the policy) is adopted to randomly select actions, explore different ways of adjusting mapping rules, and obtain more experience. As the training progresses, gradually reduce the exploration probability and increase the probability of using the existing experience to select the optimal action to improve the mapping efficiency and accuracy.

[0177] IV. Dynamically adjust mapping rules

[0178] Real-time mapping task execution: In the actual signal mapping scenario of secondary substation equipment, the agent continuously monitors the changes in the state space. Once there is a new signal to be mapped, select an appropriate action according to the current state to adjust the mapping rules and complete the mapping task. For example, when it is detected that the new device signal does not match the existing rules, the agent decides to add new rules or adjust the existing rules according to the learned policy.

[0179] Performance evaluation and continuous optimization: Regularly evaluate the performance of the mapping system, and the metrics include mapping accuracy, system response time, resource utilization, etc. Judge whether it is necessary to further optimize the agent's policy according to the evaluation results. If the performance deteriorates, increase the training frequency or adjust the hyperparameters; if the performance improves, try to reduce the exploration probability to make the agent more dependent on the learned optimal policy, ensure that the mapping rules adapt to system changes, and maintain an efficient and accurate mapping effect.

[0180] In a further embodiment, the construction process of the test case generation model includes:

[0181] Obtain a set of training and test cases for secondary substation equipment; the set of training and test cases includes training and test requirements and corresponding training and test cases;

[0182] Fine-tune and train the generative pre-training model for generating test cases using the set of training and test cases to obtain the test case generation model.

[0183] To better meet the intelligent reasoning needs during the testing process, the fine-tuning technology based on the large language model (LLM) is introduced. Through the training of domain knowledge, the LLM has powerful natural language understanding and logical reasoning capabilities and can automatically generate test templates that meet engineering requirements according to user needs.

[0184] Specifically, the process of the test case generation model generating test cases includes:

[0185] I. LLM Adaptation and Fine-tuning

[0186] Domain Data Collection: Obtain a set of training and test cases for secondary equipment in substations; the set of training and test cases includes training and test requirements and corresponding training and test cases.

[0187] Specifically, widely collect training and test cases from the historical records of substation secondary equipment tests, technical documents of various relay protection devices, industry standards and specifications, and actual test cases to form a set of training and test cases. These training and test cases cover information such as test requirements, test steps, and expected results under different equipment types, test scenarios, and fault modes. For example, collect test cases of transformer protection devices produced by different manufacturers under fault scenarios such as overload and short circuit, as well as the corresponding test procedures and expected protection actions.

[0188] Model Selection and Loading: Select a large language model (LLM) with powerful natural language processing capabilities, such as the GPT series, Wenxin Yiyan, DeepSeek, or other open-source pre-trained models. Load the selected LLM pre-trained model into a local computing environment or a cloud platform to ensure that the model can run stably and receive input data for processing.

[0189] Fine-tuning Process: Use the collected substation domain data, that is, a large number of training and test cases for substation secondary equipment, to fine-tune the LLM pre-trained model. During the fine-tuning process, organize the training and test case data in a certain format. For example, use the test requirement description as the input text, and the corresponding test template fragment (test case) or optimization suggestion as the output label. Through the backpropagation algorithm, adjust the parameters of the LLM pre-trained model so that it can better understand and generate content related to substation secondary equipment tests. During the fine-tuning process, transfer learning techniques can be adopted to utilize the language knowledge and semantic understanding capabilities learned by the pre-trained model in general natural language processing tasks to accelerate the learning process in the substation test field. At the same time, set appropriate hyperparameters such as the learning rate and the number of training epochs to balance the training speed and performance of the model and avoid overfitting or underfitting phenomena. Finally, obtain a test case generation model.

[0190] II. Test Task Analysis and Requirement Extraction

[0191] Task Input Parsing: When a new test task is received, first, the test case template generation model parses the task description. The task description may be provided in the form of natural language text, including the purpose of the test, relevant information about the test object (such as device type, model, operating status, etc.), and specific requirements of the test (such as testing a certain fault scenario, verifying a certain functional module, etc.). The test case generation model uses natural language processing techniques, such as word segmentation, part-of-speech tagging, named entity recognition, etc., to decompose the task description into understandable semantic units and extract key information.

[0192] Requirement Understanding and Transformation: Based on the parsed task information, the LLM test case generation model combines the substation test knowledge learned during fine-tuning to understand the specific requirements of the test task. For example, if the task is to conduct a fault simulation test on the relay protection device of a certain transmission line, the test case generation model can identify that the test object is the relay protection device of the transmission line, and the test requirement is to simulate the fault scenario and verify the operation of the protection device. Then, the test case generation model transforms these requirements into an internal representation form for subsequent test template generation and optimization.

[0193] III. Test Template Generation and Optimization

[0194] Initial Template Generation: The test case generation model generates a test case template based on its understanding of the test task requirements, using the knowledge and patterns learned after fine-tuning. The content of the test case template includes the general framework of the test steps, the types of test signals to be applied and the parameter ranges, and the expected test results. For the above test task of the relay protection device of the transmission line, the test case template may include test steps such as setting different types of fault current and voltage signals, observing the tripping time of the protection device and the output of the action signal, as well as the corresponding expected tripping time range and correct action signal.

[0195] Dynamic optimization process: Considering the complexity and variability of the on-site test environment, the test case generation model dynamically optimizes the test case template in the following ways. First, based on the real-time feedback information on-site, such as the real-time operating parameters of the device, the actual results of the previous test steps, etc., the test case template is adjusted. If it is found during the test that the actual operation time of the protection device is faster than expected, the test case generation model can analyze the possible reasons, such as device parameter differences, test signal interference, etc., and accordingly adjust the application time or parameters of the signal in the subsequent test steps. Second, the test case generation model can also optimize the template according to historical test data and experience. If historical data shows that a certain test step is prone to misjudgment under a certain specific device model and operating conditions, the test case generation model can add additional verification steps or adjust the combination method of test signals to improve the accuracy and reliability of the test. In addition, the test case generation model can also interact with the testers, receive the feedback and suggestions from the testers, and further optimize the test template. The testers can point out the unreasonable or difficult-to-operate parts in the template, and the test case generation model adjusts according to these feedbacks to make the test case template more in line with the actual test requirements.

[0196] IV. Template Verification and Application

[0197] Simulation verification: Before actually applying the generated test case template, use simulation tools or historical data to conduct simulation verification on the test case template. Apply the test steps and expected results in the test case template to the simulation environment, simulate the test process, and check whether the test case template can accurately detect device faults and abnormal conditions, and whether the expected results match the actual situation. If problems are found during the simulation verification process, such as the test steps cannot be executed, the expected results do not match the actual situation, etc., the problems are fed back to the test case generation model to optimize the test case template again.

[0198] Actual application and feedback: Apply the optimized test case template to the actual secondary substation equipment test. During the test, record the test data and results in real time, and feed this information back to the test case generation model. The test case generation model continuously optimizes and improves the test case template according to the actual test feedback. If it is found in the actual test that a certain test step shows significant differences on different devices, the test case generation model can further refine the test case template according to these differences so that it can better adapt to the test requirements of different devices. At the same time, record the successful experiences and failure lessons of each test as new training data for further fine-tuning the test case generation model to improve its ability in test case template generation and optimization.

[0199] In a further embodiment, after using the test cases to perform collaborative testing on different substations and / or different secondary equipment in a substation to generate test results corresponding to the test requirements, the method further includes:

[0200] Obtain the real-time device signals of the secondary equipment of the substation;

[0201] Input the real-time device signals into a pre-trained risk warning model, and predict the fault risk of the secondary equipment of the substation through the risk warning model;

[0202] Execute warning actions corresponding to the fault risk.

[0203] The large artificial intelligence model also has the ability to predict fault risks. It can not only analyze the current test results, but also combine information such as the historical performance of the equipment and fault records to predict the possible future fault types or risks, so as to give early warnings in advance. This function is of great significance for preventive maintenance and ensuring equipment safety.

[0204] Specifically, the training process of the risk warning model and the process of predicting fault risks include:

[0205] I. Data collection and collation

[0206] Collect data from various data sources of the secondary equipment of the substation, including but not limited to the operation data of relay protection devices, intelligent terminals, merging units and other equipment, that is, the device signals of the secondary equipment of the substation. These data cover real-time monitored electrical quantity data (such as the amplitude and phase of voltage and current), equipment status information (such as switch position, input and output status of protection devices), communication messages (GOOSE, SV, MMS signals), as well as historical fault records, equipment maintenance records, etc. Clean the collected device signal data, remove duplicates, errors and outliers, unify the data format, and integrate device signals of different devices and different types into a standardized database for convenient subsequent processing and analysis.

[0207] II. Feature engineering

[0208] Analyze the collected device signal data and extract features related to faults or risks. For electrical quantity data, calculate features such as voltage fluctuation amplitude, current harmonic content, power factor change rate, etc.; for equipment status information, pay attention to the number of switch operations, action frequency of protection devices, etc.; extract features such as signal transmission delay and packet loss rate from communication messages. Use statistical analysis, correlation analysis and other methods to screen out key features with high sensitivity and discrimination for fault or risk prediction, remove redundant features, reduce the data dimension, and improve the model training efficiency and prediction accuracy.

[0209] III. Model construction and training

[0210] Select a suitable model for fault or risk warning, such as decision trees, random forests, support vector machines based on machine learning, and recurrent neural networks (RNNs) and their variants, long short-term memory networks (LSTMs), gated recurrent units (GRUs), etc. in deep learning. Use historical data to train the risk warning model, with the feature data as the input and the corresponding fault or risk labels (normal, minor fault risk, severe fault risk, etc.) as the output. During the training process, by adjusting the parameters of the risk warning model, selecting a suitable loss function and optimization algorithm (such as the Adam optimizer), minimize the error between the model prediction result and the actual label, so that the model learns the mapping relationship between the data features and the fault risk. Use cross-validation to evaluate the model performance to ensure that the risk warning model has good generalization ability and avoid overfitting.

[0211] IV. Real-time monitoring and data processing: Obtain the real-time device signals of the secondary equipment in the substation.

[0212] Specifically, during the operation of the substation, collect the real-time device signals of the secondary equipment in the substation.

[0213] V. Fault or risk prediction and warning: Input the real-time device signals into a pre-trained risk warning model, and predict the fault risk of the secondary equipment in the substation through the risk warning model.

[0214] According to the same preprocessing and feature extraction process as the training data, process the real-time device signals to obtain the feature vectors for model prediction. Input these feature vectors into the trained risk warning model in real time. The model predicts the fault risk status of the secondary equipment in the substation based on the input real-time feature vectors, and thus executes the warning actions corresponding to the fault risk. If the prediction result of the risk warning model is that there is a fault risk, different levels of warnings are given according to the severity of the risk. For minor fault risks, such as when it is predicted that the temperature of a certain device is gradually rising but has not reached the danger threshold, it may prompt the operation and maintenance personnel to pay attention to the device status through a pop-up window on the in-station monitoring system, record the relevant data and increase the monitoring frequency; for severe fault risks, such as when the risk warning model predicts that the protection device is about to malfunction, the risk warning model immediately notifies the operation and maintenance personnel through multiple methods such as text messages, emails, and voice alarms, and at the same time issues a strong audible and visual alarm in the monitoring system and provides detailed warning information, including possible fault types, affected ranges, and recommended measures.

[0215] VI. Warning verification and feedback

[0216] After receiving the warning information, the operation and maintenance personnel check and test the secondary equipment of the substation to verify the accuracy of the warning. If the warning is correct, record the warning event and the processing result, and feed it back as new data into the risk warning model training process to further optimize the risk warning model; if the warning is incorrect, analyze the reasons for the error, which may be abnormal data, unreasonable parameter settings of the risk warning model, inaccurate feature selection, etc., make targeted adjustments and improvements, retrain the risk warning model, and improve the warning accuracy of the model. Regularly evaluate the warning performance of the risk warning model, and count indicators such as warning accuracy rate and recall rate to continuously optimize the model to ensure that it can timely and accurately warn of the faults or risks of substation equipment.

[0217] In addition, through the rule engine, the model can process complex test logics and make conditional judgments. Data-driven reasoning depends on the model's historical learning and real-time data input to achieve comprehensive analysis of multi-dimensional information. In this way, the system can not only complete routine test judgments, but also provide accurate fault diagnosis and operation suggestions in abnormal situations.

[0218] I. Rule formulation and sorting

[0219] Organize power industry experts and senior testers to formulate rules applicable to the tests of secondary equipment in substations based on the operating principles of power systems, technical specifications of relay protection devices (such as the regulations on signal transmission and device action logic in the IEC61850 standard), and relevant industry standards, combined with the long-term accumulated on-site test experience. Around the test process, clarify that before conducting a complete set of loop tests, it is necessary to ensure that all devices have completed single-unit commissioning and are in normal state; for signal judgment, stipulate the allowable error range of SV signal sampling values, the upper limit of GOOSE signal transmission delay, etc.; for device action logic, determine the action time and action sequence requirements of the protection device under different fault types. Classify and sort out these rules to form a structured rule set covering different scenarios such as normal operation judgment, fault diagnosis, and abnormal warning.

[0220] II. Digital expression of rules

[0221] Use a rule description language (such as the DRL language of Drools) to convert the sorted rules into a form recognizable by a computer. Assign a unique identifier to each rule, and clearly define the condition part and action part of the rule. For example, for the rule "If the current value detected by the protection device is greater than the overcurrent protection setting value and lasts for more than 50 milliseconds, then it is determined as an overcurrent fault, issue a tripping command and record the fault information", ensure that the digital expression of the rule is accurate and concise, facilitating the parsing and execution of the rule engine.

[0222] III. Rule engine configuration and integration

[0223] Select a suitable rule engine (such as Drools, Jess, etc.) and configure it according to the architecture and requirements of the substation secondary equipment test system. Set the operating parameters of the rule engine, such as memory allocation, thread pool size, etc., to optimize its performance. Integrate the rule engine into the test system and establish interfaces with the test data acquisition module and the device control module. The test data acquisition module obtains the operating data of secondary equipment in real time (such as MMS, GOOSE, SV signals, device status information, etc.) and transmits it to the rule engine; based on the judgment result, the rule engine performs corresponding operations on the device through the device control module (such as sending control instructions and adjusting test parameters).

[0224] IV. Real-time Data Processing and Rule Matching

[0225] During the operation of the test system, the rule engine receives the data transmitted by the test data acquisition module in real time. Preprocess the data, including data cleaning (removing noise data and outliers) and format conversion (unifying data types and units). Match the preprocessed data with the rules in the rule library. Adopt an efficient matching algorithm (such as the Rete algorithm), which stores rule conditions by constructing a node network, reduces repeated calculations, and quickly locates the rules that match the current data. For example, when receiving the current data of a certain protection device, the rule engine quickly filters out the rules related to the current for matching and judgment.

[0226] V. Condition Judgment and Decision Execution

[0227] Once the data successfully matches the condition part of a certain rule, the rule engine immediately triggers the action part of the rule. If it is judged that the device is in a normal operating state, the rule engine can send a normal signal to the monitoring system to maintain the continuation of the test process; if it is determined to be an abnormal or faulty situation, such as detecting that the protection device fails to operate (meeting the rule condition of "a fault occurs and reaches the action time, and the protection device does not send an action signal"), the rule engine performs corresponding actions, such as generating a detailed fault report (including fault type, occurrence time, relevant data), sending an alarm message to the operation and maintenance personnel (by means of text message, email or internal message, etc.), and at the same time controlling the test system to pause the current test task and wait for the operation and maintenance personnel to handle it.

[0228] VI. Result Feedback and Rule Optimization

[0229] After the rule engine makes a decision, it feeds back the results to other modules of the test system. For example, the test report generation module records the judgment results, and the device management module adjusts the device operation status according to the results. Regularly evaluate the operation results of the rule engine and collect feedback data in actual tests. If it is found that the rule judgment is inaccurate (such as misjudgment or missed judgment) or unable to handle newly emerging test scenarios, analyze the reasons in a timely manner. Organize experts to revise, supplement, or optimize the rules, update the rule library, and redeploy it to the rule engine to ensure that the rule engine always adapts to the needs of substation secondary equipment testing and improve the accuracy and reliability of the test system.

[0230] In addition, the core task of the large model is to perform intelligent diagnosis and judgment on the real-time test process. Through the inflow of real-time data, the system can analyze the timing changes of signals based on the pre-established model and detect anomalies by comparing historical patterns. Whenever a signal change or test condition change occurs, the model will immediately analyze it and output a diagnostic result. For example, when the signal of a certain protection device does not change as expected, the model will automatically identify this anomaly and speculate on possible fault causes.

[0231] I. Collection and Arrangement of Historical Test Data

[0232] Comprehensively collect historical test data of substation secondary equipment, covering data of different equipment types, test scenarios, and operation stages. This includes relay protection device action records, such as action time and action type; various signal data, like real-time values and change situations of GOOSE, SV, and MMS signals; test input parameters, such as the magnitude and duration of simulated fault quantities; and test environment information, such as temperature, humidity, and grid load. Obtain data from multiple channels, such as manual test records, automatic test system logs, and equipment operation and maintenance reports, and perform standardized processing to unify the data format, eliminate data noise and error values, and ensure data accuracy and consistency.

[0233] II. Data Classification and Labeling

[0234] Classify historical data according to dimensions such as test equipment type, test items, and fault types. For example, classify data by equipment type into line protection device data, transformer protection device data, etc.; classify data by test items into single-function test data, integrated circuit test data, etc.; classify data by fault types into short-circuit fault data, overcurrent fault data, etc. Add labels to each type of data to clarify normal test results, various abnormal results, and their corresponding fault causes, such as "normal - no fault", "abnormal - protection device refusal to operate - hardware failure", etc., and construct a label system for easy retrieval and analysis.

[0235] III. Construction of Data Analysis Model

[0236] Apply machine learning algorithms such as decision trees, random forests, support vector machines, etc. to model the classified and labeled data. Taking fault type prediction as an example, use the signal features and test conditions in historical test data as inputs and the fault type label as the output to train the model to learn the association patterns between data. Utilize deep learning models, such as convolutional neural networks (CNNs) to process image-based signal data and long short-term memory networks (LSTMs) to analyze test data with temporal characteristics, to mine the deep features and patterns in the data and improve the model's prediction and analysis capabilities.

[0237] IV. Comparison and Analysis of Real-time Test Data

[0238] During the current test process, collect the test data of secondary equipment in real time and compare it with historical test data. Compare key indicators such as signal amplitude, change trend, action time, etc. If the deviation between the real-time data and the historical normal data exceeds the preset threshold, start the abnormal analysis process. Analyze the real-time data through the trained model to predict the possible fault types and development trends. For example, analyze the temporal changes of the action signals of protection devices to predict whether there will be misoperation or refusal to operate of the protection.

[0239] V. Adjustment of Decision-making Mechanism

[0240] If the model predicts an abnormality, adjust the decision-making mechanism based on the processing experience and effect feedback of similar abnormalities in historical data. For abnormalities that occur frequently and for which effective handling measures have been identified, such as signal abnormalities caused by a certain type of communication interference, directly give targeted handling suggestions, such as checking the connection of communication lines and restarting the communication module. For newly emerged or poorly handled abnormalities, combine the characteristics of historical data and the experience of domain experts to make exploratory decisions, such as trying different test parameter adjustments and conducting additional equipment inspection items, and continuously track the implementation effect of the decisions to update historical data and the model.

[0241] VI. Decision Implementation and Effect Evaluation

[0242] Execute operations according to the adjusted decision-making mechanism, such as adjusting the test plan, performing maintenance on equipment, etc., and record the operation process and results. Compare the changes in test data before and after the operation to evaluate the implementation effect of the decision. If the abnormality is resolved, supplement this processing process and results as a successful case to the historical data; if the abnormality is not improved or new problems occur, re-analyze the historical data to further optimize the decision-making mechanism until the problem is solved, continuously improving the accuracy and effectiveness of the decision-making mechanism.

[0243] In addition, the automatic test system software and the acceptance test host complete the functions of issuing test control commands and feedback of test results, and communicate with the relay protection device under test based on the IEC61850 standard using the CMS / MMS communication protocol to achieve the issuance of protection device control commands and the acquisition of device action reports, recordings, remote signal changes and other information. The automatic test system software realizes test task scheduling control and result judgment, and ultimately achieves fully automatic closed-loop testing.

[0244] Based on the existing general test template, the result data of each test item in the test template is obtained through flexible configuration, and a report template in a specific format is generated. During the automatic test process, the test results are automatically filled in the test report in real time until a report in a specific format is automatically generated after the one-click test is completed;

[0245] The configuration method of the test report is flexible and editable. First, based on the debugging report form, the header, test items, and test data table are edited and generated. The results in the table support dragging and selecting the data results in the debugging template. If the above conditions are met, the original debugging report form can be restored to the maximum extent, so that the configuration method generates the entire set of tests performed by the debugging template and does not affect the test report of the original manual test, ensuring high adaptability and availability when the test result data is reported.

[0246] In the process of generating a specific report, first of all, the format of the report is generally in table form. The rows and columns of the table can be generated on a completely blank basis. The text or the test results in the associated test template can be edited at will in the formed row and column cells. Ultimately, the format and content of the original test report can be restored. At the same time, the test results can be automatically filled in according to the judgment results during the test process to generate a debugging report with test results.

[0247] In addition, considering that in actual applications, disaster scenarios such as typhoons have brought severe challenges to substation secondary equipment such as substation relay protection devices. For example, after a typhoon passes and causes equipment abnormalities, the maintenance test of the substation secondary equipment faces a series of outstanding problems: the test process has a low degree of automation, resulting in low efficiency of maintenance tests and difficulty in responding quickly in emergency situations; the system has poor coordination, making it difficult to coordinate tests between different devices, affecting the overall test effect; the test strategy lacks adaptability and cannot be adjusted in time according to the complex equipment conditions after the typhoon disaster. At the same time, existing testing methods are difficult to meet the needs of multi-device collaborative testing, dynamic strategy optimization, and human-computer intelligent interaction in emergency power restoration scenarios, which seriously restricts the improvement of post-disaster repair efficiency and safety assurance capabilities. In order to further improve the application effect of the secondary equipment testing method based on the generative large model proposed in the present invention, the present invention can also address the difficulties in substation secondary equipment testing in disaster scenarios by adopting the following technical means:

[0248] 1) By integrating multi-source maintenance data including real-time monitoring data of equipment operation, historical fault data, maintenance records and other information with the domain knowledge base that integrates power industry standards, professional technical knowledge and expert experience, a large model of intelligent maintenance test for substation relay protection is constructed based on the existing general or industry large model; the model integrates a large amount of data related to relay protection (including equipment operation data, fault cases, test standards, etc.) and conducts in-depth mining and analysis of these data, so that the model can better adapt to relay protection test scenarios and accurately understand and handle complex problems in relay protection tests;

[0249] 2) Based on the integration of AIGC (Artificial Intelligence Generated Content) technology and graph neural network, we build intelligent test scheme generation technology, and use this technology to establish a deep connection between the equipment topology that reflects the connection and layout relationship of the internal equipment of the substation and the test logic that specifies the test process and test method, so as to realize the intelligent construction and dynamic adaptation of test schemes and test templates. It can intelligently generate efficient and adaptive test schemes and test templates according to different equipment status, fault types and test requirements; these templates not only cover comprehensive test steps and parameter settings, but also can be adjusted dynamically in real time according to actual conditions (such as changes in equipment status) to adapt to various complex and changeable test scenarios;

[0250] 3) Based on the multi-objective test strategy optimization framework driven by reinforcement learning, a dynamic adjustment mechanism for test parameters driven by disaster scenarios is constructed. For example, in the emergency power supply scenario after a typhoon passes, the model is allowed to learn and optimize the test strategy in the continuous test process based on the reinforcement learning algorithm, so that the test parameters and processes can be dynamically adjusted according to the different impacts of disasters on the equipment (real-time status feedback of the equipment and test results). These experiences are accumulated to form a differentiated test strategy knowledge base, providing flexible and optimal maintenance test solutions for substation secondary equipment. In actual applications, according to different disaster scenarios, appropriate test strategies can be quickly obtained from the knowledge base to ensure that the test can efficiently and accurately detect potential problems of the equipment, improve the pertinence and effectiveness of the test, and thus improve the reliability of the equipment during emergency power supply.

[0251] 4) Based on digital twin technology, virtual modeling is carried out on substation equipment and the test process, and a visualization interaction interface based on digital twin is constructed. Operators can conveniently communicate and cooperate with the equipment. It can not only intelligently guide the test process according to the operator's instructions and equipment status, provide operation suggestions and risk warnings in real time, but also reflect the actual status of the equipment and the test in real time. Moreover, through interaction with the operator, it can continuously optimize the test process and strategy, realize efficient collaboration between humans and machines and coordinated joint debugging between multiple systems, thereby effectively improving the collaborative working ability and reliability of the entire substation secondary equipment system, providing pioneering auxiliary support for high-efficiency and high-quality maintenance tests of secondary equipment for emergency power transmission after disasters, and significantly enhancing the recovery ability and operation safety of the entire power system after disasters.

[0252] Based on the above technical solution, in special scenarios where substation equipment fails and trips and power outages are caused by disasters such as typhoons, the application value of the secondary equipment test method based on the generative large model provided by the present invention is further improved, and it can effectively meet the needs of grid safety protection equipment such as relay protection to complete maintenance tests efficiently and high-quality before power supply restoration.

[0253] See Figure 2 , Figure 2 is a schematic structural diagram of an embodiment of a secondary equipment test device based on the generative large model provided by the present invention. As Figure 2 shown, the device includes:

[0254] A test requirement acquisition module 201, configured to acquire the test requirements of substation secondary equipment; the test requirements at least include equipment test signals with different signal specifications between different substations and / or different secondary equipment in a substation.

[0255] A test case generation module 202, configured to generate test cases corresponding to the test requirements according to the standard signals corresponding to the equipment test signals through a pre-trained test case generation model; the standard signals are obtained by classifying the equipment signals of substation secondary equipment based on a standard signal model, and are used to represent the signal specifications uniformly followed between some or all different substations and / or between some or all different secondary equipment in a substation; the standard signal model is configured to identify common attributes between equipment signals with different signal specifications to form the standard signals.

[0256] A collaborative test module 203, configured to perform collaborative tests on the different substations and / or different secondary equipment in a substation using the test cases to generate test results corresponding to the test requirements.

[0257] In the present invention, the test case generation module 202 identifies the common attributes of device signals with different signal specifications through a standard signal model to form a standard signal representing the uniformly followed signal specification. Furthermore, the test case generation module 202 uses the standard signal to generate test cases for collaborative testing between substations with different signal specifications and / or different secondary devices, which can improve the test collaboration between substations and / or secondary devices with different signal specifications. Additionally, using the standard signal can ignore the signal differences between different signal specifications, improve the interoperability between substations and / or secondary devices with different signal specifications, and thus improve the test efficiency.

[0258] In a further embodiment, the construction process of the standard signal model includes:

[0259] Obtain a first set of device signals of the secondary devices of the substation; the first set of device signals includes standard signals corresponding to device signals with different signal specifications between different substations and / or different secondary devices in the substation and data tags corresponding to each of the standard signals;

[0260] Preprocess the first set of device signals; the preprocessing includes at least data cleaning;

[0261] Divide the preprocessed first set of device signals into at least a training set and a validation set;

[0262] Used to train the constructed standard signal model with the training set to identify the common attributes of device signals with different signal specifications between different substations and / or different secondary devices in the substation to form the standard signal, and use the validation set to verify the standard signal model until the iteration termination condition is met to obtain a trained standard signal model.

[0263] In a further embodiment, the device further includes:

[0264] A fusion module for fusing at least two standard signal models constructed and trained through machine learning and / or deep learning to obtain a fused standard signal model.

[0265] In a further embodiment, the categories of the standard signal model include: a standard signal model for the device operation stage, a standard signal model for the device failure type, a standard signal model for the device signal nature, and a standard signal model for the device type;

[0266] The test case generation module 202 includes:

[0267] A test case generation unit for generating test cases corresponding to the test requirements according to the standard signals of at least one category corresponding to the device test signals.

[0268] In a further embodiment, the test case generation module 202 includes:

[0269] A signal extraction unit, configured to extract the device test signals included in the test requirements according to the test case generation model.

[0270] A standard signal mapping unit, configured to determine the standard signal corresponding to the device test signal based on a signal mapping model; the signal mapping model at least includes a mapping rule between the device test signal and the standard signal.

[0271] A test case generation unit, configured to generate an initial test case corresponding to the test requirements in a template configuration manner according to the standard signal through the test case generation model; the initial test case at least includes the standard signal corresponding to the device test signal, the test process, and the test result.

[0272] An instantiation unit, configured to instantiate the standard signal in the initial test case into the device test signal to form an instantiated test case.

[0273] In a further embodiment, the construction process of the signal mapping model includes:

[0274] Performing pre-training with general data to obtain a mapping pre-training model; the mapping pre-training model includes a machine learning model and / or a deep learning model;

[0275] Obtaining a second device signal set of the secondary substation equipment; the second device signal set at least includes data tags characterizing the mapping relationship between the device signal and the standard signal;

[0276] Performing preprocessing on the second device signal set; the preprocessing at least includes data cleaning;

[0277] Using the preprocessed second device signal set to perform fine-tuning training on the mapping pre-training model to obtain a trained signal mapping model.

[0278] In a further embodiment, the device further includes:

[0279] A mapping rule adjustment module, configured to dynamically adjust the mapping rule of the signal mapping model through a reinforcement learning algorithm.

[0280] In a further embodiment, the test case generation unit includes:

[0281] A test case generation subunit, configured to generate an initial test case corresponding to the test requirements in a template configuration manner according to the standard signal included in at least one of the prompt item, the judgment item, the pressure plate control item, and the overall output fault item through the test case generation model.

[0282] In a further embodiment, the instantiation unit includes:

[0283] A standard signal index subunit, configured to determine, by using a similarity measurement method, a standard signal corresponding to a device signal that matches the device test signal from a preconfigured dictionary index; the dictionary index includes at least device signals, standard signals, and a mapping relationship between the device signals and the standard signals.

[0284] An instantiation subunit, configured to instantiate the standard signal corresponding to the device signal that matches the device test signal in the initial test case as the device test signal, so as to form an instantiated test case.

[0285] In a further embodiment, the standard signal index subunit includes:

[0286] A similarity index subunit, configured to determine, by using a similarity measurement method based on a corpus and / or a knowledge base, candidate device signals whose similarity to the device test signal exceeds a preset similarity threshold from the dictionary index.

[0287] A standard signal determination subunit, configured to determine a device signal with the highest similarity to the device test signal among the candidate device signals, and obtain, from the dictionary index, the standard signal corresponding to the device signal with the highest similarity as the standard signal corresponding to the device signal that matches the device test signal.

[0288] In a further embodiment, the process of constructing the test case generation model includes:

[0289] Obtaining a training test case set of the secondary substation equipment; the training test case set includes training test requirements and corresponding training test cases;

[0290] Fine-tuning and training a generative pre-training model for generating test cases by using the training test case set to obtain the test case generation model.

[0291] In a further embodiment, the device further includes:

[0292] A risk warning module, configured to obtain real-time device signals of the secondary substation equipment, input the real-time device signals into a pre-trained risk warning model, predict a fault risk of the secondary substation equipment through the risk warning model, and execute a warning action corresponding to the fault risk.

[0293] For the steps executed by each module or unit (and sub-units, etc.) in the above secondary equipment test device based on the generative large model and the functional effects that can be achieved, please refer to the relevant descriptions of each step in the corresponding method embodiment for details, and will not be elaborated here specifically. Each module in the above device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0294] Furthermore, an embodiment of the present invention also provides an electronic device. Among them, the above electronic device includes a server and / or a terminal. Both the terminal and the server can independently execute the secondary equipment test method based on the generative large model provided in the embodiment of the present invention, and the terminal and the server can also cooperate to execute the secondary equipment test method based on the generative large model provided in the embodiment of the present invention. The terminal communicates with the server through a network. The data storage system can store the data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on the cloud or other servers.

[0295] The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc.

[0296] Among them, the server can specifically include: at least one processor, at least one memory, a power supply, a communication interface, an input / output interface, and a communication bus. In this embodiment, the power supply is used to provide working voltage for each hardware device on the server; the communication interface can create a data transmission channel between the server and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present invention, and will not be specifically limited here; the input / output interface is used to obtain external input data or output data to the outside, and the specific interface type can be selected according to specific application needs, and will not be specifically limited here. Generally, the terminal in this embodiment includes a processor and a memory. In some embodiments, the terminal may further include a display screen, an input / output interface, a communication interface, sensors, a power supply, and a communication bus.

[0297] Among them, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor may further include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0298] Among them, the memory is used to store computer programs, and the computer programs are loaded and executed by the processor to implement the relevant steps in the request processing disclosed in any of the foregoing embodiments. As a carrier for resource storage, the memory may be a read-only memory, a random access memory, a disk, or an optical disc, etc. The resources stored thereon include an operating system, computer programs, and data, etc. The storage method may be temporary storage or permanent storage. Among them, the operating system is used to manage and control each hardware device and computer program on the server to enable the processor to perform operations and processing on the data in the memory. It may be Windows Server, Netware, Unix, Linux, etc. In addition to the computer programs that can be used to complete the request processing method disclosed in any of the foregoing embodiments, the computer programs may further include computer programs that can be used to complete other specific tasks. In addition to data such as update information of the application program, the data may further include data such as developer information of the application program.

[0299] In summary, the present invention provides a secondary equipment test method, device and equipment based on a generative large model. By obtaining equipment test signals with different signal specifications between different substations and / or different secondary equipment in a substation; through a pre-trained test case generation model, generating test cases corresponding to test requirements according to the standard signals corresponding to the equipment test signals; using the test cases to perform collaborative testing on different substations and / or different secondary equipment in a substation, and generating test results corresponding to the test requirements. By using a standard signal model to identify the common attributes of equipment signals with different signal specifications, a standard signal representing a uniformly followed signal specification is formed; furthermore, using the standard signal to generate test cases for collaborative testing between substations with different signal specifications and / or different secondary equipment can improve the test collaboration between substations and / or secondary equipment with different signal specifications. In addition, using the standard signal can ignore the signal differences between different signal specifications, improve the interoperability between substations and / or secondary equipment with different signal specifications, and thus improve the test efficiency.

[0300] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards.

[0301] It can be understood that the technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0302] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

Claims

1. A secondary equipment test method based on a generative large model, characterized in that The method includes: Obtaining the test requirements of the secondary equipment in the substation; the test requirements at least include equipment test signals with different signal specifications between different substations and / or different secondary equipment in the substation; Generating test cases corresponding to the test requirements according to the standard signals corresponding to the equipment test signals through a pre-trained test case generation model; the standard signals are obtained by classifying the equipment signals of the secondary equipment in the substation based on a standard signal model, and are used to represent the signal specifications uniformly followed between some or all different substations and / or between some or all different secondary equipment in the substation; the standard signal model is configured to identify the common attributes between the equipment signals with different signal specifications to form the standard signals; the categories of the standard signal model include: the standard signal model for the equipment operation stage, the standard signal model for the equipment fault type, the standard signal model for the equipment signal nature, and the standard signal model for the equipment type; the equipment operation stage includes normal operation, protection action, abnormality / fault, and maintenance / test; the equipment fault types include short-circuit fault, grounding fault, overload, and undervoltage; the equipment signal nature includes system normal state signal, protection action signal, abnormality / fault state signal, and communication message; the equipment types include relay protection devices, measurement and control equipment, intelligent terminals, and merging units; Using the test cases to conduct collaborative testing on the different substations and / or different secondary equipment in the substation to generate test results corresponding to the test requirements; Among them, the test case generation model is obtained by fine-tuning a large language model; the test case generation model parses and converts the test task requirement description to generate corresponding test cases; the test task requirements include test purposes, test object information, and test requirements; the test cases include test step frameworks, types and parameter ranges of test signals to be applied, and expected test results; The step of generating test cases corresponding to the test requirements according to the standard signals corresponding to the equipment test signals through a pre-trained test case generation model includes: Extracting the equipment test signals included in the test requirements according to the test case generation model; Determining the standard signals corresponding to the equipment test signals based on a signal mapping model; the signal mapping model at least includes the mapping rules between the equipment test signals and the standard signals; Generating initial test cases corresponding to the test requirements in a template configuration manner according to the standard signals through the test case generation model; the initial test cases at least include the standard signals corresponding to the equipment test signals, the test process, and the test results; Instantiating the standard signals in the initial test cases into the equipment test signals to form instantiated test cases.

2. The secondary equipment test method based on the generative large model according to claim 1, characterized in that, The construction process of the standard signal model includes: Obtain a first set of device signals of the secondary equipment of the substation; the first set of device signals includes standard signals corresponding to device signals with different signal specifications between different substations and / or different secondary equipment in the substation, and data tags corresponding to each of the standard signals; Preprocess the first set of device signals; the preprocessing includes at least data cleaning; Divide the preprocessed first set of device signals into at least a training set and a validation set; Use the training set to train the constructed standard signal model to identify the common attributes of device signals with different signal specifications between different substations and / or different secondary equipment in the substation to form the standard signals, and use the validation set to verify the standard signal model until the iteration termination condition is met to obtain a trained standard signal model.

3. The secondary equipment test method based on the generative large model according to claim 2, wherein, The method further includes: Fuse at least two standard signal models constructed and trained through machine learning and / or deep learning to obtain a fused standard signal model.

4. The secondary equipment test method based on the generative large model according to claim 1 or 2 or 3, characterized in that Generating the test cases corresponding to the test requirements according to the standard signals corresponding to the device test signals includes: Generating the test cases corresponding to the test requirements according to at least one category of standard signals corresponding to the device test signals.

5. The secondary equipment test method based on the generative large model according to claim 1, wherein, The construction process of the signal mapping model includes: Perform pre-training using general data to obtain a mapping pre-trained model; the mapping pre-trained model includes a machine learning model and / or a deep learning model; Obtain a second set of device signals of the secondary equipment of the substation; the second set of device signals includes at least data tags characterizing the mapping relationship between device signals and standard signals; Preprocess the second set of device signals; the preprocessing includes at least data cleaning; Use the preprocessed second set of device signals to perform fine-tuning training on the mapping pre-trained model to obtain a trained signal mapping model.

6. The secondary equipment test method based on the generative large model according to claim 5, wherein, The method further includes: Dynamically adjust the mapping rules of the signal mapping model through a reinforcement learning algorithm.

7. The secondary equipment test method based on the generative large model according to claim 1, wherein Generating the initial test cases corresponding to the test requirements in a template configuration manner according to the standard signals through the test case generation model includes: Through the test case generation model, generate the initial test cases corresponding to the test requirements in a template configuration manner according to the standard signals included in at least one of the prompt class, judgment class, pressure plate control class, and overall output fault class.

8. The secondary equipment test method based on the generative large model according to claim 1, characterized in that, Instantiating the standard signals in the initial test cases into the device test signals to form instantiated test cases includes: Use a similarity measurement method to determine the standard signals corresponding to the device signals that match the device test signals from a pre-configured dictionary index; the dictionary index includes at least device signals, standard signals, and the mapping relationship between device signals and standard signals; Instantiate the standard signals corresponding to the device signals that match the device test signals in the initial test cases into the device test signals to form instantiated test cases.

9. The method for secondary equipment testing based on a generative large model according to claim 8, wherein, Determining the standard signal corresponding to the device signal that matches the device test signal from a pre-configured dictionary index using a similarity measurement method includes: Using a similarity measurement method based on a corpus and / or knowledge base to determine candidate device signals from the dictionary index whose similarity to the device test signal exceeds a preset similarity threshold; Determining the device signal with the highest similarity to the device test signal among the candidate device signals, and obtaining the standard signal corresponding to the device signal with the highest similarity from the dictionary index as the standard signal corresponding to the device signal that matches the device test signal.

10. The secondary equipment test method based on the generative large model according to claim 1, characterized in that The process of constructing the test case generation model includes: Obtaining a training and test case set for the secondary equipment of the substation; the training and test case set includes training and test requirements and corresponding training and test cases; Fine-tuning and training a generative pre-trained model for generating test cases using the training and test case set to obtain the test case generation model.

11. The method for testing secondary equipment based on a generative large model according to claim 1, wherein After using the test cases to co-test different substations and / or different secondary equipment in a substation to generate the test results corresponding to the test requirements, the method further includes: Obtaining the real-time device signal of the secondary equipment of the substation, inputting the real-time device signal into a pre-trained risk warning model, predicting the fault risk of the secondary equipment of the substation through the risk warning model, and performing a warning action corresponding to the fault risk.

12. A secondary equipment test device based on a generative large model, characterized in that, Applying the secondary equipment test method based on a generative large model as described in claim 1, the device includes: A test requirement acquisition module for acquiring the test requirements of the secondary equipment of the substation; the test requirements at least include device test signals with different signal specifications between different substations and / or different secondary equipment in a substation; A test case generation module for generating the test cases corresponding to the test requirements according to the standard signal corresponding to the device test signal through a pre-trained test case generation model; the standard signal is obtained by classifying the device signals of the secondary equipment of the substation based on a standard signal model, and is used to represent the signal specifications uniformly followed between some or all different substations and / or some or all different secondary equipment in a substation; the standard signal model is configured to identify the common attributes between device signals with different signal specifications to form the standard signal; A co-test module for co-testing different substations and / or different secondary equipment in a substation using the test cases to generate the test results corresponding to the test requirements.

13. The secondary equipment test device based on the generative large model according to claim 12, characterized in that, The device further includes: A risk warning module for obtaining the real-time device signal of the secondary equipment of the substation, inputting the real-time device signal into a pre-trained risk warning model, predicting the fault risk of the secondary equipment of the substation through the risk warning model, and performing a warning action corresponding to the fault risk.

14. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for secondary equipment testing based on a generative large model according to any one of claims 1 to 11.

Images