Generation method, device and equipment of four-remote signal of power system and medium

Abstract

The invention relates to the technical field of data processing of a power system, and discloses a power system four-remote signal generation method, device and equipment and a medium, and the method comprises the steps: obtaining a first signal feature based on a preset feature model, the first signal feature comprises voltage class data, interval type data, primary equipment configuration data and secondary equipment configuration data; based on a preset feature matching model, performing signal template matching according to the first signal feature and a preset signal template library to obtain a signal template matching result; and based on a preset four-remote signal generation model, generating a four-remote signal according to the first signal feature, the signal template matching result and the signal template library, and obtaining a target four-remote signal corresponding to the first signal feature. By automatically generating the four-remote signals, the signal management efficiency is greatly improved, the generated four-remote signals can be ensured to be uniform and accurate, and the problems of signal missing and disorder are effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing of power systems, and in particular to a method, device, equipment and medium for generating four remote signals of a power system. Background Art

[0002] The four remote signals refer to the four functions of telemetry (YC), telesignaling (YX), remote control (YK) and remote adjustment (YT). These functions play a vital role in the power system and are mainly used to monitor and control the operating status of power equipment. However, the signal naming rules of the four remote signals of the equipment of many different manufacturers on the market are very different, resulting in that in actual applications, even the four remote signals of the same physical quantity may be named differently in the equipment of different manufacturers. This inconsistency in signal naming leads to poor signal management efficiency, signal loss and confusion, and lack of adaptability and versatility, which brings great challenges to the signal management, monitoring and maintenance of the power system.

[0003] (1) Inefficient signal management: In the traditional mode, each plant station needs to manually fill in the four remote signals and have them reviewed and unified by the administrator. The process is complicated, time-consuming and inefficient.

[0004] (2) Signal missing and confusion: When manually filling in the four remote signals, signal missing or confusion may occur due to human factors or unclear rules. This not only affects the normal operation of the power system, but may also cause safety accidents.

[0005] (3) Lack of adaptability and versatility: There are many types of equipment in the power system, with different voltage levels and bay types. In the traditional way, different signal management rules need to be formulated for different equipment, bay voltage levels and bay types, which increases management complexity and cost. Summary of the invention

[0006] Based on this, it is necessary to propose a method, device, equipment and medium for generating four remote signals of a power system to address the technical problems that the inconsistent signal naming of the four remote signals in the existing technology leads to poor signal management efficiency, signal missing and confusion, insufficient adaptability and versatility, and brings great challenges to the signal management, monitoring and maintenance of the power system.

[0007] In a first aspect, a method for generating four remote signals of a power system is provided, the method comprising:

[0008] Based on a preset feature model, a first signal feature is obtained, wherein the first signal feature includes: voltage level data, interval type data, primary device configuration data, and secondary device configuration data;

[0009] Based on a preset feature matching model, signal template matching is performed according to the first signal feature and a preset signal template library to obtain a signal template matching result;

[0010] Based on a preset four-remote signal generation model, four-remote signal is generated according to the first signal feature, the signal template matching result and the signal template library, and the target four-remote signal corresponding to the first signal feature is obtained.

[0011] Furthermore, before the step of obtaining the first signal feature based on the preset feature model, the step further includes:

[0012] Get historical four remote signal data;

[0013] Preprocessing the historical four-remote control signal data to obtain four-remote control signal data to be classified;

[0014] Performing signal classification on the four remote signal data to be classified to obtain a signal classification result;

[0015] Perform feature extraction, feature selection and feature transformation according to the four remote signal data to be classified to obtain selected features and transformation results;

[0016] A model is constructed according to the selected features, the transformation results and the signal classification results to obtain the feature model.

[0017] Furthermore, the feature matching model is a model trained based on one or more algorithms of Euclidean distance, cosine similarity, Manhattan distance, and Hamming distance.

[0018] Further, the step of generating four remote signals based on the preset four remote signal generation model according to the first signal feature, the signal template matching result and the signal template library to obtain the target four remote signals corresponding to the first signal feature includes:

[0019] Performing interval analysis according to the first signal feature to obtain an interval analysis result;

[0020] Based on a preset signal naming rule, generating a signal name according to the interval analysis result;

[0021] Based on a preset four-remote signal generation model, four-remote signal is generated according to the signal name, the first signal feature, the signal template matching result and the signal template library to obtain the target four-remote signal.

[0022] Furthermore, the step of generating a signal name according to the interval analysis result based on a preset signal naming rule includes:

[0023] Determining whether a signal generation condition is met according to the interval analysis result and the first signal feature;

[0024] If the signal generation condition is met, the signal name is generated according to the interval analysis result based on a preset signal naming rule.

[0025] Further, the step of generating four remote signals based on the preset four remote signal generation model according to the first signal feature, the signal template matching result and the signal template library to obtain the target four remote signals corresponding to the first signal feature also includes:

[0026] Based on a preset four-remote signal generation model, four remote signals are generated according to the first signal feature, the signal template matching result and the signal template library to obtain data to be analyzed;

[0027] Sending the first signal feature and the data to be analyzed to an audit end;

[0028] Acquire the audit result sent by the audit end according to the first signal feature and the data to be analyzed;

[0029] If the conclusion in the audit result is passed, the four remote signals in the data to be analyzed are used as the target four remote signals;

[0030] If the conclusion in the audit result is failure, the four remote signals in the data to be analyzed are updated according to the correction information in the audit result to obtain the target four remote signals.

[0031] Furthermore, the step of updating the four remote signals in the data to be analyzed according to the correction information in the audit result to obtain the target four remote signals includes:

[0032] According to the correction information in the audit result, the four remote control signals in the data to be analyzed are updated to obtain the four remote control signals to be processed;

[0033] Inputting the four remote control signals to be processed into a pre-trained quality assessment model to predict whether they are qualified, and obtaining a prediction vector;

[0034] Taking the classification category corresponding to the vector element with the largest value in the prediction vector as the target prediction result;

[0035] If the target prediction result is qualified, the to-be-processed four remote control signals are used as the target four remote control signals;

[0036] If the target prediction result is unqualified, the target prediction result and the four remote control signals to be processed are used as the data to be analyzed, and the process jumps to the step of sending the first signal feature and the data to be analyzed to the audit end to continue execution.

[0037] In a second aspect, a device for generating four remote signals of a power system is provided, the device comprising:

[0038] A data acquisition module, configured to acquire first signal features based on a preset feature model, wherein the first signal features include: voltage level data, interval type data, primary device configuration data, and secondary device configuration data;

[0039] A matching module, configured to perform signal template matching according to the first signal feature and a preset signal template library based on a preset feature matching model to obtain a signal template matching result;

[0040] The four-remote signal generation module is used to generate four-remote signals based on a preset four-remote signal generation model, according to the first signal feature, the signal template matching result and the signal template library, and obtain the target four-remote signal corresponding to the first signal feature.

[0041] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for generating four remote control signals of the power system when executing the computer program.

[0042] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for generating four remote control signals of the power system are implemented.

[0043] The method, device, equipment and medium for generating four remote signals of the power system of the present application obtain the first signal feature based on a preset feature model, wherein the first signal feature includes: voltage level data, interval type data, primary equipment configuration data and secondary equipment configuration data; based on a preset feature matching model, signal template matching is performed according to the first signal feature and a preset signal template library to obtain a signal template matching result; based on a preset four-remote signal generation model, four remote signals are generated according to the first signal feature, the signal template matching result and the signal template library to obtain the target four remote signals corresponding to the first signal feature. By automatically generating four remote signals, the signal management efficiency is greatly improved, and at the same time, the generated four remote signals can be guaranteed to be unified and accurate, effectively avoiding the problem of signal missing and confusion. Moreover, different equipment, different interval voltage levels and interval types can be processed, which enhances adaptability and versatility, thereby providing a strong guarantee for signal management, monitoring and maintenance of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] in:

[0046] Figure 1 FIG. 1 is an application environment diagram of a method for generating four remote signals of a power system in one embodiment;

[0047] Figure 2 is a flow chart of a method for generating four remote signals of a power system in one embodiment;

[0048] Figure 3 It is a general simplified schematic diagram of a method for generating four remote signals of a power system in one embodiment;

[0049] Figure 4 for Figure 2 Detailed flow chart of the method for generating four remote signals of the power system;

[0050] Figure 5 for Figure 2 Detailed flow chart of the method for generating four remote signals of the power system;

[0051] Figure 6 for Figure 2 Detailed flow chart of the method for generating four remote signals of the power system;

[0052] Figure 7 for Figure 2 Detailed flow chart of the method for generating four remote signals of the power system;

[0053] Figure 8 for Figure 2 Detailed flow chart of the method for generating four remote signals of the power system;

[0054] Fig. 9 for Figure 2 Detailed flow chart of the method for generating four remote signals of the power system;

[0055] Fig.10 It is a structural block diagram of a device for generating four remote signals of a power system in one embodiment;

[0056] Fig.11 is a structural block diagram of a computer device in one embodiment;

[0057] Fig.12 Another structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] The method for generating four remote signals of a power system provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the client 110 communicates with the server 120 through the network.

[0060] Optionally, the server 120 can obtain the first signal feature through the client 110 based on a preset feature model, and the first signal feature includes: voltage level data, interval type data, primary equipment configuration data and secondary equipment configuration data. The server 120 is used to: based on the preset feature matching model, perform signal template matching according to the first signal feature and the preset signal template library to obtain the signal template matching result; based on the preset four-remote signal generation model, generate four remote signals according to the first signal feature, the signal template matching result and the signal template library, and obtain the target four remote signals corresponding to the first signal feature. By automatically generating four remote signals, the signal management efficiency is greatly improved, and at the same time, the generated four remote signals can be guaranteed to be unified and accurate, effectively avoiding the problem of signal missing and confusion. Moreover, different equipment, different interval voltage levels and interval types can be processed, which enhances adaptability and versatility, thereby providing a strong guarantee for signal management, monitoring and maintenance of the power system.

[0061] Optionally, the client 110 obtains a model from the server 120, and the obtained model is used to implement the method for generating four remote signals of the power system of the present application. The client 110 is used to: based on a preset feature model, obtain a first signal feature, the first signal feature includes: voltage level data, interval type data, primary equipment configuration data and secondary equipment configuration data; based on a preset feature matching model, perform signal template matching according to the first signal feature and a preset signal template library to obtain a signal template matching result; based on a preset four-remote signal generation model, generate four remote signals according to the first signal feature, the signal template matching result and the signal template library, and obtain the target four remote signals corresponding to the first signal feature.

[0062] The client 110 may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server 120 may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0063] See also Figure 2 As shown, Figure 2 A flow chart of a method for generating four remote signals of a power system provided by an embodiment of the present invention includes the following steps:

[0064] S1: Based on a preset feature model, obtain a first signal feature, the first signal feature including: voltage level data, interval type data, primary device configuration data and secondary device configuration data;

[0065] Optionally, a first interface is displayed based on a preset characteristic model, and the user inputs voltage level data and interval type data in the first interface. A second interface is displayed based on the preset characteristic model and the voltage level data and interval type data input by the user, and the user inputs primary device configuration data and secondary device configuration data in the second interface. That is, step S1 is Figure 3 The specific implementation of "entering the primary and secondary equipment data of the plant station".

[0066] The interval type data refers to the type of the interval. The voltage level data refers to the voltage level of the interval.

[0067] The primary device configuration data refers to the configuration data of a primary device.

[0068] Secondary device configuration data refers to the configuration data of secondary devices.

[0069] In the power system, a "bay" is a part of a substation that contains switchgear and control devices associated with the specified circuits contained therein. These devices are used to control and protect a specific part of the power system, ensuring safe and stable power transmission.

[0070] The primary equipment of the power system refers to the equipment that directly produces, transmits, distributes and uses electric energy. They are interconnected to form the main electrical circuit for power generation, transmission and distribution. The primary equipment includes generators, transformers, circuit breakers, disconnectors, automatic switches, contactors, knife switches, busbars, transmission lines, power cables, reactors, motors, etc.

[0071] The secondary equipment of the power system is auxiliary equipment that monitors, measures, controls, regulates and protects the primary equipment of the power system. It is not directly connected to the main power circuit.

[0072] S2: Based on a preset feature matching model, signal template matching is performed according to the first signal feature and a preset signal template library to obtain a signal template matching result;

[0073] Specifically, the first signal feature and the template feature data in the signal template library are input into a preset feature matching model for classification prediction to achieve signal template matching, and the classification category (that is, template identifier) ​​corresponding to the vector element whose value in the predicted vector is greater than the preset value is used as the signal template matching result.

[0074] The template identifier may be data that uniquely identifies a signal template, such as a template name or a template ID.

[0075] Since there are many four-remote signals, not all of them are needed. Therefore, step S2 is used to determine which signals are specifically needed for the first signal feature, and the template identifiers of the needed signals are used as signal template matching results.

[0076] The feature matching model is a pre-trained multi-classification model. The model structure and model training method of the feature matching model can be selected from the existing technology.

[0077] That is, step S2 is Figure 3 The specific implementation of "signal template matching" in .

[0078] S3: Based on a preset four-remote signal generation model, four remote signals are generated according to the first signal feature, the signal template matching result and the signal template library to obtain target four remote signals corresponding to the first signal feature.

[0079] Specifically, according to the signal template matching result, a signal template is obtained from the signal template library as a target template; based on a preset four-remote signal generation model, four-remote signals are generated according to the first signal feature and the target template; all generated four-remote signals are used as target four-remote signals.

[0080] The preset four-remote signal generation model is a pre-trained generation model based on a neural network (for example, a multi-layer perceptron, a convolutional neural network, etc., and a suitable network structure is designed, including the number of layers, the number of neurons, etc.).

[0081] The training process of the four-remote signal generation model includes: (1) Data collection: Collect a large number of data samples including voltage level data, interval type data, primary equipment configuration data, secondary equipment configuration data and the corresponding four-remote signal true values; (2) Data preprocessing: Clean, standardize and normalize the data to improve the data quality and the learning effect of the neural network; (3) Construct a neural network architecture: Select a suitable neural network type, such as multi-layer perceptron, convolutional neural network, etc., and design a suitable network structure, including the number of layers and neurons; (4) Model training: Input the preprocessed data into the neural network, and use optimization methods such as back propagation algorithm to continuously adjust the network weights and biases so that the network output gradually approaches the real four-remote signal; (5) Verification and adjustment: Use the validation set data to verify the trained model, evaluate its accuracy and performance, and further adjust the network structure and training parameters based on the results; (6) Iterative optimization: Repeat the above steps and perform multiple iterative training to continuously improve the performance of the model until satisfactory results are achieved; (7) Testing: Use an independent test set to test the final model to determine its performance on new data.

[0082] That is, step S3 is Figure 3 The specific implementation of the "signal automatic generation model" and "intelligent generation of standardized four remote signals".

[0083] This embodiment greatly improves the signal management efficiency by automatically generating four remote signals, and can also ensure that the generated four remote signals are unified and accurate, effectively avoiding the problem of signal loss and confusion. Moreover, it can process different equipment, different interval voltage levels and interval types, enhancing adaptability and versatility, thereby providing a strong guarantee for signal management, monitoring and maintenance of the power system.

[0084] See also Figure 4 As shown, in one embodiment, before the step of obtaining the first signal feature based on the preset feature model, the step further includes:

[0085] S41: Obtain historical four remote signal data;

[0086] Specifically, the historical four-remote signal data from various plants and different manufacturers are comprehensively collected.

[0087] S42: preprocessing the historical four-remote control signal data to obtain four-remote control signal data to be classified;

[0088] Specifically, the historical four remote signal data are preprocessed, and the preprocessing operations include: one or more combinations of cleaning, noise removal, outlier removal and duplicate data removal, data smoothing, filtering, and interpolation. The historical four remote signal data that have completed the preprocessing are used as the four remote signal data to be classified.

[0089] S43: performing signal classification on the four remote signal data to be classified to obtain a signal classification result;

[0090] Optionally, the four remote signal data to be classified are sent to a classification end, and a staff member classifies the signals input by the classification end for the four remote signal data to be classified; and obtains the signal classification results sent by the classification end.

[0091] Optionally, the four remote signal data to be classified are input into a pre-trained signal classification model for signal classification prediction, and the classification category corresponding to the vector element with the largest value in the predicted vector is taken as the signal classification result.

[0092] The pre-trained signal classification model is a pre-trained multi-classification model. The model structure and model training method of the signal classification model can be selected from the existing technology and will not be described in detail here.

[0093] The optional signal classification result describes the associated data of the three-level classification. The three-level classification includes but is not limited to: first-level classification (such as protection action, alarm, etc.), second-level classification (such as circuit breaker action, protection device alarm, etc.), and third-level classification (such as circuit breaker non-full-phase operation, protection device failure, etc.).

[0094] S44: performing feature extraction, feature selection and feature transformation according to the four remote signal data to be classified to obtain selected features and transformation results;

[0095] Feature extraction includes: extracting key information from the four remote signal data to be classified, which can describe the main characteristics and trends of the data. The features can be numerical, classified or structured data, etc. The method of extracting features depends on the specific application scenario and data type.

[0096] Feature selection includes: selecting the most representative and discriminative features from the features obtained by feature extraction. Feature selection can be achieved through statistical methods, machine learning algorithms or expert experience. Selecting appropriate features can reduce the amount of calculation and improve the performance and accuracy of the model.

[0097] Feature transformation includes: transforming the features selected by feature selection to eliminate redundancy, improve the independence between features or reduce feature dimensions. Common feature transformation methods include principal component analysis (PCA), linear discriminant analysis (LDA), independent component analysis (ICA), etc. Feature transformation helps to simplify the model and improve the generalization ability of the model.

[0098] That is, steps S41 to S44 are Figure 3 The specific implementation of "historical remote signal processing" in .

[0099] S45: constructing a model according to the selected features, the transformation results and the signal classification results to obtain the feature model.

[0100] Specifically, based on one or more of mathematical formulas, statistical models, machine learning models and deep learning models, a model is constructed according to the selected features, the transformation results and the signal classification results, and the constructed model is used as the feature model.

[0101] The specific construction process of the feature model includes: (1) Data preparation: organize the selected features, transformation results and signal classification results into a suitable data format and divide them into training set, validation set and test set; (2) Feature engineering: further process and combine features, which may include operations such as feature scaling and feature crossover; (3) Deep learning model construction: use convolutional neural network to design appropriate convolution layer, pooling layer and fully connected layer structure; (4) Input the processed feature data, perform forward propagation and back propagation training, and adjust the network parameters through optimization algorithms (such as stochastic gradient descent); (5) Machine learning model construction: build a random forest model, input the feature data, and determine the number of trees in the forest and other hyperparameters through training; (6) Model fusion: the output of the deep learning model and the output of the random forest model can be fused in some way, such as weighted averaging or integration through another simple model; (7) Evaluation and adjustment: use the validation set to evaluate the model performance, and adjust the model structure, hyperparameters, etc. according to the evaluation results; (8) Final model determination: verify the generalization ability of the final model through the test set and determine the feature model.

[0102] The feature model should cover all key signal features, such as signal name, type, description, source manufacturer, etc., to ensure that the feature model can fully reflect the characteristics of the signal.

[0103] That is, step S45 is Figure 3 The specific implementation of "Establishing feature model" in .

[0104] This embodiment obtains historical four-remote signal data and preprocesses it to obtain four-remote signal data to be classified, obtains signal classification results after classification, and then performs feature extraction, selection and transformation to obtain selected features and transformation results. A model is constructed based on these, namely the feature model, which can bring technical effects such as improving data quality, refining key features, and improving model accuracy and stability, which is beneficial to signal monitoring, fault diagnosis and automatic control, etc.

[0105] In one embodiment, the feature matching model is a model trained based on one or more algorithms of Euclidean distance, cosine similarity, Manhattan distance, and Hamming distance.

[0106] First, prepare a large number of labeled four-remote signal data samples. Then, for each sample, calculate the Euclidean distance, cosine similarity, Manhattan distance, Hamming distance and other metrics between it and other samples. Then, input these metrics into the model as features and train it in combination with the category labels of the samples. During the training process, by continuously adjusting the parameters of the model, the model can accurately classify and match the samples according to these distance metrics. Some optimization algorithms such as gradient descent may also be used to speed up the training process. At the same time, evaluation methods such as cross-validation will be performed to ensure the generalization ability and accuracy of the model. After repeated training and optimization, a feature matching model trained based on these algorithms is finally obtained.

[0107] The feature matching model described in this embodiment is a model trained based on one or more algorithms of Euclidean distance, cosine similarity, Manhattan distance, and Hamming distance, and the prediction results each time have good consistency.

[0108] See also Figure 5 As shown, in one embodiment, the step of generating four remote signals based on a preset four remote signal generation model according to the first signal feature, the signal template matching result and the signal template library, and obtaining the target four remote signals corresponding to the first signal feature includes:

[0109] S311: performing interval analysis according to the first signal feature to obtain an interval analysis result;

[0110] Specifically, based on the regular expression, the first signal feature is analyzed at intervals, and the voltage level, interval type and circuit breaker number obtained by the analysis are used as interval analysis results.

[0111] S312: Based on a preset signal naming rule, generate a signal name according to the interval analysis result;

[0112] Specifically, based on a preset signal naming rule, a character string is combined according to the interval analysis result, and the combined character string is used as the signal name.

[0113] S313: Based on a preset four-remote signal generation model, four remote signals are generated according to the signal name, the first signal feature, the signal template matching result and the signal template library to obtain the target four remote signals.

[0114] Specifically, according to the signal template matching result, a signal template is obtained from the signal template library as a target template; based on a preset four-remote signal generation model, four-remote signals are generated according to the signal name, the first signal feature and the target template; all generated four-remote signals are used as target four-remote signals.

[0115] This embodiment is based on a preset four-remote signal generation model, and generates four remote signals according to the signal name, the first signal feature, the signal template matching result and the signal template library, so that the signal names of the generated four remote signals are standardized, which is beneficial to the subsequent management and application of the four remote signals.

[0116] See also Figure 6 As shown, in one embodiment, the step of generating a signal name according to the interval analysis result based on a preset signal naming rule includes:

[0117] S3121: Determine whether a signal generation condition is met according to the interval analysis result and the first signal feature;

[0118] When a signal needs to meet the signal generation conditions to be generated, query whether the interval attributes meet the conditions according to the corresponding signal generation conditions (for example: if it needs to be a certain type, query the interval attribute and then compare whether the type meets the requirements; if it needs to have a certain attribute, query whether the interval has this attribute). If it does not meet the signal generation conditions, skip generating the four remote signals.

[0119] Specifically, based on the regular expression, it is determined whether the signal generation condition is met according to the interval analysis result and the first signal feature.

[0120] S3122: If the signal generation condition is met, the signal name is generated according to the interval analysis result based on a preset signal naming rule.

[0121] Specifically, if the signal generation condition is met, it means that four remote signals need to be generated. Therefore, based on the preset signal naming rule, the signal name is generated according to the interval analysis result.

[0122] It is understandable that if the signal generation condition is met, the processing of the current target template is stopped, and step S3121 may be continued to process the next target template.

[0123] This embodiment accurately determines whether the conditions for signal generation are met by judging the interval analysis results and the first signal characteristics. Once the conditions are met, a signal name with specific meaning and specifications can be efficiently generated according to the preset signal naming rules and the interval analysis results, thereby achieving effective control and precise naming of the signal generation process, which is beneficial to subsequent related operations and processing.

[0124] See also Figure 7 As shown, in one embodiment, the step of generating four remote signals based on a preset four remote signal generation model according to the first signal feature, the signal template matching result and the signal template library, and obtaining the target four remote signals corresponding to the first signal feature, further includes:

[0125] S321: Based on a preset four-remote signal generation model, four remote signals are generated according to the first signal feature, the signal template matching result and the signal template library to obtain data to be analyzed;

[0126] Specifically, based on the preset four-remote signal generation model, four-remote signal is generated according to the first signal feature, the signal template matching result and the signal template library, and the generated four-remote signal template is used as the data to be analyzed.

[0127] S322: Sending the first signal feature and the data to be analyzed to a review end;

[0128] Specifically, the first signal feature and the data to be analyzed are sent to the audit end through a communication connection with the audit end.

[0129] The audit end displays the received data to be analyzed, and the auditor audits the displayed data to be analyzed. If the four remote signals in the data to be analyzed meet the requirements, the conclusion of the audit result is determined to be passed. If the four remote signals in the data to be analyzed do not meet the requirements, the conclusion of the audit result is determined to be failed. The auditor modifies the four remote signals in the data to be analyzed and uses the modified information as correction information of the audit result.

[0130] S323: Acquire the audit result sent by the audit end according to the first signal feature and the data to be analyzed;

[0131] Specifically, through the communication connection with the audit end, the audit result sent by the audit end according to the first signal feature and the data to be analyzed is obtained.

[0132] S324: If the conclusion in the audit result is passed, the four remote signals in the data to be analyzed are used as the target four remote signals;

[0133] Specifically, if the conclusion in the audit result is passed, it means that the four remote signals in the data to be analyzed meet the requirements. Therefore, the four remote signals in the data to be analyzed are used as the target four remote signals.

[0134] S325: If the conclusion in the audit result is failure, the four remote signals in the data to be analyzed are updated according to the correction information in the audit result to obtain the target four remote signals.

[0135] If the conclusion in the audit result is failure, it means that the four remote signals in the data to be analyzed meet the requirements. Therefore, according to the correction information in the audit result, the four remote signals in the data to be analyzed are replaced and updated, and the updated four remote signals are used as the target four remote signals.

[0136] This embodiment reviews and corrects unqualified four-remote control signals through the audit end, which not only greatly improves the accuracy of the target four-remote control signals, but also effectively avoids subsequent work errors caused by data errors, providing a solid guarantee for the stable operation of related systems or processes. At the same time, the four-remote control signals that have been reviewed and corrected can better match and interact with other related data, enhance the consistency and compatibility of the data, further optimize the overall data processing efficiency and quality, and lay a more reliable foundation for the smooth development of business and the scientific nature of decision-making.

[0137] See also Figure 8 As shown, in one embodiment, the step of updating the four remote signals in the data to be analyzed according to the correction information in the audit result to obtain the target four remote signals includes:

[0138] S3251: updating the four remote control signals in the data to be analyzed according to the correction information in the audit result to obtain the four remote control signals to be processed;

[0139] Specifically, according to the correction information in the audit result, the four remote control signals in the data to be analyzed are replaced and updated, and the updated four remote control signals are used as the four remote control signals to be processed.

[0140] S3252: Inputting the four remote control signals to be processed into a pre-trained quality assessment model to predict whether they are qualified, and obtaining a prediction vector;

[0141] Specifically, the four remote control signals to be processed are input into a pre-trained quality assessment model to predict whether they are qualified, and the predicted vector is used as a prediction vector.

[0142] The pre-trained quality assessment model is a pre-trained multi-classification model. The model structure and model training method of the quality assessment model can be selected from the existing technology and will not be described in detail here.

[0143] S3253: taking the classification category corresponding to the vector element with the largest value in the prediction vector as the target prediction result;

[0144] Specifically, the vector element with the largest value in the prediction vector is the vector element with the greatest prediction possibility. Therefore, the classification category corresponding to the vector element with the largest value in the prediction vector is used as the target prediction result.

[0145] The value of the target prediction result is either qualified or unqualified.

[0146] S3254: If the target prediction result is qualified, the to-be-processed four remote control signals are used as the target four remote control signals;

[0147] Specifically, if the target prediction result is qualified, it means that the four remote control signals corrected by the audit end meet the requirements. Therefore, the four remote control signals to be processed are used as the target four remote control signals.

[0148] S3255: If the target prediction result is unqualified, the target prediction result and the four remote control signals to be processed are used as the data to be analyzed, and the process jumps to the step of sending the first signal feature and the data to be analyzed to the audit end to continue execution.

[0149] Specifically, if the target prediction result is unqualified, it means that the four remote signals corrected by the audit end do not meet the requirements and need to be re-audited and corrected by the audit end. Therefore, the target prediction result and the four remote signals to be processed are used as the data to be analyzed. After the update of the data to be analyzed is completed, jump to the step of sending the first signal feature and the data to be analyzed to the audit end to continue execution (that is, jump to step S322 to continue execution).

[0150] This embodiment uses a quality assessment model to evaluate the quality of the four remote signals corrected by the audit end, and realizes accurate quantification and scientific analysis of the quality of the four remote signals. This measure can not only timely discover potential quality problems and deviations, but also effectively urge the audit end to further improve the accuracy of correction, thereby effectively improving the accuracy of the four remote signals, ensuring that the data and information in the four remote signals are more reliable and accurate, and providing a solid data foundation for subsequent operations and decisions based on the four remote signals, and effectively ensuring the reliability and stability of data application in related fields such as power systems.

[0151] See also Fig. 9 As shown, in one embodiment, the step of acquiring the first signal feature based on a preset feature model includes:

[0152] S11: Obtain input start signal;

[0153] The input start signal is a signal that starts inputting data.

[0154] Specifically, an input start signal input by a user may be obtained, and an input start signal sent by a third-party application may also be obtained.

[0155] S12: If the input type in the input start signal is the first type, based on a preset feature model, start a first signal acquisition interface, and acquire the first signal feature according to the first signal acquisition interface;

[0156] Specifically, if the input type in the information carried by the input start signal is the first type, it means that the staff only wants to fill in the signal characteristics, so the first signal acquisition interface is started and the first signal characteristics are acquired according to the first signal acquisition interface.

[0157] S13: If the input type in the input start signal is the second type, start the second signal acquisition interface, and acquire the second signal characteristics and the four remote signals to be analyzed according to the second signal acquisition interface;

[0158] Specifically, if the input type in the information carried by the input start signal is the second type, it means that the staff only wants to fill in the signal characteristics and four remote signals. Therefore, the second signal acquisition interface is started, and the second signal characteristics and the four remote signals to be analyzed are obtained according to the second signal acquisition interface.

[0159] S14: Acquire a signal evaluation result according to the second signal feature and the four remote signals to be analyzed;

[0160] Optionally, a signal evaluation result sent by the audit end is obtained based on the second signal characteristics and the four remote signals to be analyzed.

[0161] Optionally, the second signal feature and the four remote signals to be analyzed are spliced ​​and input into a pre-trained four remote signal evaluation model for classification prediction, and the classification category corresponding to the vector element with the largest value in the predicted vector is taken as the signal evaluation result.

[0162] S15: If the signal evaluation result is passed, the four remote control signals to be analyzed are used as the final four remote control signals corresponding to the second signal feature;

[0163] Specifically, if the signal evaluation result is passed, it means that the four remote signals to be analyzed input by the staff meet the requirements. Therefore, the four remote signals to be analyzed are used as the final four remote signals corresponding to the second signal feature.

[0164] S16: If the signal evaluation result is not passed, the second signal acquisition interface is updated according to the signal evaluation result, and the step of acquiring the second signal characteristics and the four remote signals to be analyzed according to the second signal acquisition interface is jumped to continue execution.

[0165] Specifically, if the signal evaluation result is failed, it means that the four remote signals to be analyzed input by the staff do not meet the requirements. Therefore, the second signal acquisition interface is updated according to the signal evaluation result, and the step of acquiring the second signal characteristics and the four remote signals to be analyzed according to the second signal acquisition interface is jumped to continue the execution to re-acquire the second signal characteristics and the four remote signals to be analyzed after the staff.

[0166] This embodiment uses a startup signal to start different interfaces to obtain information, which significantly improves the flexibility of the entire system in terms of information acquisition. The second signal feature and the four remote signals to be analyzed input by the staff are evaluated. When the evaluation result is passed, the four remote signals to be analyzed are used as the target four remote signals corresponding to the second signal feature. When the evaluation result is not passed, the second signal feature and the four remote signals to be analyzed after the staff are re-acquired, which effectively avoids the transmission and use of erroneous data and further improves the rigor and reliability of data processing. This mechanism enables the system to operate more intelligently and efficiently when dealing with various complex situations and different needs, providing strong support for the smooth development of related work, and also enhancing the adaptability and accuracy of the interaction between the staff and the system.

[0167] See also Fig.10 As shown, in one embodiment, a device for generating four remote signals of a power system is provided, the device comprising:

[0168] The data acquisition module 801 is used to acquire a first signal feature based on a preset feature model, wherein the first signal feature includes: voltage level data, interval type data, primary device configuration data, and secondary device configuration data;

[0169] A matching module 802 is used to perform signal template matching according to the first signal feature and a preset signal template library based on a preset feature matching model to obtain a signal template matching result;

[0170] The four-remote signal generation module 803 is used to generate four-remote signals based on a preset four-remote signal generation model, according to the first signal feature, the signal template matching result and the signal template library, and obtain target four-remote signals corresponding to the first signal feature.

[0171] This embodiment greatly improves the signal management efficiency by automatically generating four remote signals, and can also ensure that the generated four remote signals are unified and accurate, effectively avoiding the problem of signal loss and confusion. Moreover, it can process different equipment, different interval voltage levels and interval types, enhancing adaptability and versatility, thereby providing a strong guarantee for signal management, monitoring and maintenance of the power system.

[0172] In one embodiment, the device further comprises: a model building module, wherein the model building module is used to:

[0173] Get historical four remote signal data;

[0174] Preprocessing the historical four-remote control signal data to obtain four-remote control signal data to be classified;

[0175] Performing signal classification on the four remote signal data to be classified to obtain a signal classification result;

[0176] Perform feature extraction, feature selection and feature transformation according to the four remote signal data to be classified to obtain selected features and transformation results;

[0177] A model is constructed according to the selected features, the transformation results and the signal classification results to obtain the feature model.

[0178] In one embodiment, the feature matching model is a model trained based on one or more algorithms of Euclidean distance, cosine similarity, Manhattan distance, and Hamming distance.

[0179] In one embodiment, the step of generating four remote signals based on a preset four remote signal generation model in the four remote signal generation module 803 according to the first signal feature, the signal template matching result and the signal template library to obtain the target four remote signals corresponding to the first signal feature includes:

[0180] Performing interval analysis according to the first signal feature to obtain an interval analysis result;

[0181] Based on a preset signal naming rule, generating a signal name according to the interval analysis result;

[0182] Based on a preset four-remote signal generation model, four-remote signal is generated according to the signal name, the first signal feature, the signal template matching result and the signal template library to obtain the target four-remote signal.

[0183] In one embodiment, the step of generating a signal name based on the preset signal naming rule and the interval analysis result in the four-remote signal generation module 803 includes:

[0184] Determining whether a signal generation condition is met according to the interval analysis result and the first signal feature;

[0185] If the signal generation condition is met, the signal name is generated according to the interval analysis result based on a preset signal naming rule.

[0186] In one embodiment, the step of generating four remote signals based on a preset four remote signal generation model according to the first signal feature, the signal template matching result and the signal template library in the four remote signal generation module 803, and obtaining the target four remote signals corresponding to the first signal feature, further includes:

[0187] Based on a preset four-remote signal generation model, four remote signals are generated according to the first signal feature, the signal template matching result and the signal template library to obtain data to be analyzed;

[0188] Sending the first signal feature and the data to be analyzed to an audit end;

[0189] Acquire the audit result sent by the audit end according to the first signal feature and the data to be analyzed;

[0190] If the conclusion in the audit result is passed, the four remote signals in the data to be analyzed are used as the target four remote signals;

[0191] If the conclusion in the audit result is failure, the four remote signals in the data to be analyzed are updated according to the correction information in the audit result to obtain the target four remote signals.

[0192] In one embodiment, the step of updating the four remote signals in the data to be analyzed according to the correction information in the audit result to obtain the target four remote signals in the four remote signal generation module 803 includes:

[0193] According to the correction information in the audit result, the four remote control signals in the data to be analyzed are updated to obtain the four remote control signals to be processed;

[0194] Inputting the four remote control signals to be processed into a pre-trained quality assessment model to predict whether they are qualified, and obtaining a prediction vector;

[0195] Taking the classification category corresponding to the vector element with the largest value in the prediction vector as the target prediction result;

[0196] If the target prediction result is qualified, the to-be-processed four remote control signals are used as the target four remote control signals;

[0197] If the target prediction result is unqualified, the target prediction result and the four remote control signals to be processed are used as the data to be analyzed, and the process jumps to the step of sending the first signal feature and the data to be analyzed to the audit end to continue execution.

[0198] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.11As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, the functions or steps on the service side of a method for generating four remote signals of a power system are realized.

[0199] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, the functions or steps on the client side of a method for generating four remote signals of a power system are realized.

[0200] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0201] Based on a preset feature model, a first signal feature is obtained, wherein the first signal feature includes: voltage level data, interval type data, primary device configuration data, and secondary device configuration data;

[0202] Based on a preset feature matching model, signal template matching is performed according to the first signal feature and a preset signal template library to obtain a signal template matching result;

[0203] Based on a preset four-remote signal generation model, four-remote signal is generated according to the first signal feature, the signal template matching result and the signal template library, and the target four-remote signal corresponding to the first signal feature is obtained.

[0204] This embodiment greatly improves the signal management efficiency by automatically generating four remote signals, and can also ensure that the generated four remote signals are unified and accurate, effectively avoiding the problem of signal loss and confusion. Moreover, it can process different equipment, different interval voltage levels and interval types, enhancing adaptability and versatility, thereby providing a strong guarantee for signal management, monitoring and maintenance of the power system.

[0205] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0206] Based on a preset feature model, a first signal feature is obtained, wherein the first signal feature includes: voltage level data, interval type data, primary device configuration data, and secondary device configuration data;

[0207] Based on a preset feature matching model, signal template matching is performed according to the first signal feature and a preset signal template library to obtain a signal template matching result;

[0208] Based on a preset four-remote signal generation model, four-remote signal is generated according to the first signal feature, the signal template matching result and the signal template library, and the target four-remote signal corresponding to the first signal feature is obtained.

[0209] This embodiment greatly improves the signal management efficiency by automatically generating four remote signals, and can also ensure that the generated four remote signals are unified and accurate, effectively avoiding the problem of signal loss and confusion. Moreover, it can process different equipment, different interval voltage levels and interval types, enhancing adaptability and versatility, thereby providing a strong guarantee for signal management, monitoring and maintenance of the power system.

[0210] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0211] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0212] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0213] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for generating four remote signals of a power system, characterized in that: The method comprises: Based on a preset feature model, a first signal feature is obtained, wherein the first signal feature includes: voltage level data, interval type data, primary device configuration data, and secondary device configuration data; Based on a preset feature matching model, signal template matching is performed according to the first signal feature and a preset signal template library to obtain a signal template matching result; Based on a preset four-remote signal generation model, four-remote signal is generated according to the first signal feature, the signal template matching result and the signal template library, and the target four-remote signal corresponding to the first signal feature is obtained.

2. The method for generating four remote signals of a power system according to claim 1, characterized in that: Before the step of obtaining the first signal feature based on the preset feature model, the method further includes: Get historical four remote signal data; Preprocessing the historical four-remote control signal data to obtain four-remote control signal data to be classified; Performing signal classification on the four remote signal data to be classified to obtain a signal classification result; Perform feature extraction, feature selection and feature transformation according to the four remote signal data to be classified to obtain selected features and transformation results; A model is constructed according to the selected features, the transformation results and the signal classification results to obtain the feature model.

3. The method for generating four remote signals of a power system according to claim 1, characterized in that: The feature matching model is a model trained based on one or more algorithms of Euclidean distance, cosine similarity, Manhattan distance, and Hamming distance.

4. The method for generating four remote signals of a power system according to claim 1, characterized in that: The step of generating four remote signals based on the preset four remote signal generation model according to the first signal feature, the signal template matching result and the signal template library to obtain the target four remote signals corresponding to the first signal feature includes: Performing interval analysis according to the first signal feature to obtain an interval analysis result; Based on a preset signal naming rule, generating a signal name according to the interval analysis result; Based on a preset four-remote signal generation model, four-remote signal is generated according to the signal name, the first signal feature, the signal template matching result and the signal template library to obtain the target four-remote signal.

5. The method for generating four remote signals of a power system according to claim 4, characterized in that: The step of generating a signal name based on the preset signal naming rule and according to the interval analysis result comprises: Determining whether a signal generation condition is met according to the interval analysis result and the first signal feature; If the signal generation condition is met, the signal name is generated according to the interval analysis result based on a preset signal naming rule.

6. The method for generating four remote signals of a power system according to claim 1, characterized in that: The step of generating four remote signals based on the preset four remote signal generation model according to the first signal feature, the signal template matching result and the signal template library to obtain the target four remote signals corresponding to the first signal feature also includes: Based on a preset four-remote signal generation model, four remote signals are generated according to the first signal feature, the signal template matching result and the signal template library to obtain data to be analyzed; Sending the first signal feature and the data to be analyzed to an audit end; Acquire the audit result sent by the audit end according to the first signal feature and the data to be analyzed; If the conclusion in the audit result is passed, the four remote signals in the data to be analyzed are used as the target four remote signals; If the conclusion in the audit result is failure, the four remote signals in the data to be analyzed are updated according to the correction information in the audit result to obtain the target four remote signals.

7. The method for generating four remote signals of a power system according to claim 6, characterized in that: The step of updating the four remote control signals in the data to be analyzed according to the correction information in the audit result to obtain the target four remote control signals includes: According to the correction information in the audit result, the four remote control signals in the data to be analyzed are updated to obtain the four remote control signals to be processed; Inputting the four remote control signals to be processed into a pre-trained quality assessment model to predict whether they are qualified, and obtaining a prediction vector; Taking the classification category corresponding to the vector element with the largest value in the prediction vector as the target prediction result; If the target prediction result is qualified, the to-be-processed four remote control signals are used as the target four remote control signals; If the target prediction result is unqualified, the target prediction result and the four remote control signals to be processed are used as the data to be analyzed, and the process jumps to the step of sending the first signal feature and the data to be analyzed to the audit end to continue execution.

8. A device for generating four remote signals of a power system, characterized in that: The device comprises: A data acquisition module, configured to acquire first signal features based on a preset feature model, wherein the first signal features include: voltage level data, interval type data, primary device configuration data, and secondary device configuration data; A matching module, configured to perform signal template matching according to the first signal feature and a preset signal template library based on a preset feature matching model to obtain a signal template matching result; The four-remote signal generation module is used to generate four-remote signals based on a preset four-remote signal generation model, according to the first signal feature, the signal template matching result and the signal template library, and obtain the target four-remote signal corresponding to the first signal feature.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for generating four remote signals of the power system as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for generating four remote control signals of a power system as claimed in any one of claims 1 to 7 are implemented.

Images