A control method and system for distribution automation network access information system

By preprocessing and structuring the historical parameter data of the automatic network access information system of power distribution, combined with improved clustering algorithms and correlation analysis methods, the problems of low data utilization and inaccurate fault mode judgment in traditional systems are solved, and the problem of low data utilization and inaccurate fault mode judgment in traditional systems is realized. Accurate identification and handling of distribution network faults ensures the stable operation of the system.

CN118611057BActive Publication Date: 2024-11-19JIANGSU XINJIEZHI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411067671.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-19
Estimated Expiration
2044-08-06

AI Technical Summary

Technical Problem

The traditional distribution automation network access information system lacks effective preprocessing and structured methods when processing massive historical parameter data, resulting in low data utilization; when judging distribution network failure mode, relying on a single characteristic indicator, ignoring multiple indicators. The correlation of the results of inaccurate judgment results; the lack of effective control strategies for different distribution network failure modes affects the stable operation of the power system.

Method used

A control method for the automatic network access information system of power distribution is proposed. By obtaining historical parameter data of each module for pre-processing, combining with the improved clustering algorithm to obtain the fault mode, data structure is carried out, and whether the second control is performed based on the weighted accuracy is determined. Module access is used to identify and control failure modes using improved correlation analysis method and neural network model.

Benefits of technology

It realizes comprehensive monitoring and management of the automatic network access information system of distribution, improves the accuracy and efficiency of fault handling, ensures the stable operation of the system, and significantly improves the identification and processing effect of distribution network fault modes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118611057B_ABST
    Figure CN118611057B_ABST
Patent Text Reader

Abstract

The present invention discloses a control method and system for a distribution automation access information system, including: historical parameter data acquisition, preprocessing, distribution network fault mode acquisition, second preprocessing, weighted correctness acquisition, and second control module access judgment. The system includes distribution data acquisition, geographic information, management, communication and automation control modules. The distribution network fault mode is acquired by improving the clustering algorithm, and the historical parameter data of the relevant modules are structured preprocessed. Whether to access the second control module is determined according to the weighted correctness. Comprehensive monitoring and management of the distribution automation access information system, as well as accurate identification and processing of the distribution network fault mode are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of control of a distribution automation network access information system, and in particular to a control method and system for a distribution automation network access information system. Background Art

[0002] With the advancement of science and technology and the development of the power industry, distribution automation technology is gradually becoming an indispensable part of the power system. The application of distribution automation network information system provides strong technical support for the stable operation and efficient management of the power system. However, the traditional distribution automation network information system still has some problems to be solved in terms of control.

[0003] First, faced with massive amounts of historical parameter data, traditional distribution automation access information systems often lack effective preprocessing and structuring methods. These data are usually scattered and disordered, lacking unified storage and organization standards, resulting in low data utilization and inability to fully realize the value of the data.

[0004] Secondly, when judging the distribution network fault mode, traditional methods often rely on a single characteristic indicator. This method ignores the correlation between multiple indicators, resulting in inaccurate judgment results and difficulty in adapting to complex and changeable distribution network fault conditions.

[0005] In addition, the traditional distribution automation access information system lacks an effective control strategy for different distribution network fault modes. This results in the system being unable to accurately control the fault when a distribution network fault occurs, affecting the stable operation of the power system. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above existing problems, the present invention is proposed.

[0008] Therefore, the present invention provides a control method and system for a distribution automation network access information system, which can solve the problems mentioned in the background technology.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0010] In a first aspect, the present invention provides a control method for a distribution automation network access information system, comprising:

[0011] Acquire historical parameter data of each module of the distribution automation network access information system, and perform a first preprocessing on the historical parameter data, wherein the distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module, and an automation control module;

[0012] According to the first preprocessing result of the historical parameter data of the power distribution data acquisition module, combined with the improved clustering algorithm, the distribution network fault mode is obtained;

[0013] Performing a second preprocessing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing in combination with the distribution network fault mode, wherein the second preprocessing is used to structure the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing;

[0014] According to the second preprocessing result, the weighted correctness of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes is obtained;

[0015] According to the weighted correctness, it is determined whether to connect a second control module in different distribution network failure modes, and the second control module includes a second control logic.

[0016] As a preferred solution of the control method of the distribution automation network access information system of the present invention, wherein: judging whether to connect the second control module in different distribution network fault modes according to the weighted correctness includes:

[0017] Acquire the real-time parameter data of each module of the distribution automation network access information system, determine the type of current distribution network fault mode according to the real-time parameter data of the distribution data acquisition module, and determine whether to access the second control module according to the type of current distribution network fault mode;

[0018] If it is determined that the second control module is to be connected, the communication module is immediately turned off, and the communication module is turned on again after the second control module is connected. At this time, the connection between the communication module and the power distribution management module is disconnected, and the power distribution equipment geographic information module and the automation control module are directly controlled by the second control module;

[0019] If it is determined that the second control module is not to be connected, the existing module is used to implement the operation of the distribution automation network access information system.

[0020] As a preferred solution of the control method of the distribution automation network access information system of the present invention, wherein: the first preprocessing result of the historical parameter data of the distribution data acquisition module, combined with the improved clustering algorithm, obtains the distribution network fault mode, including:

[0021] The historical parameter data of the power distribution data acquisition module at least includes line current, phase voltage, active power, reactive power, switch status, last operation time, load level, grid frequency, relay action times and fault duration;

[0022] The first preprocessing includes data cleaning, normalization and feature extraction of the historical parameter data of the power distribution data acquisition module, and extracting target features using an improved correlation analysis method;

[0023] According to the target features combined with the improved clustering algorithm, the distribution network fault mode is obtained, and the distribution network fault mode includes an instantaneous short circuit fault mode, a continuous overload fault mode, a single-phase grounding fault mode, a disconnection fault mode and a frequency fluctuation fault mode.

[0024] As a preferred solution of the control method of the distribution automation network access information system described in the present invention, wherein: the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing are subjected to a second preprocessing in combination with the distribution network fault mode, and the second preprocessing is used to structure the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing, including:

[0025] The second preprocessing performs structured processing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing according to the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode and the frequency fluctuation fault mode;

[0026] The historical parameter data of the geographic information module of the power distribution equipment at least includes the location of the fault and the record of the environmental conditions where the fault occurred;

[0027] The historical parameter data of the power distribution management module includes at least feedback on the execution status of management control instructions generated for faults and operator records;

[0028] The historical parameter data of the automation control module at least includes corresponding operations performed in response to the management control instructions generated by the power distribution management module, as well as operation timestamps and performance evaluation indicators of operation results.

[0029] As a preferred solution of the control method of the distribution automation network access information system of the present invention, wherein: the weighted correctness of obtaining the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing under different distribution network fault modes according to the second preprocessing result includes:

[0030] Establish accuracy scoring logic for the power distribution equipment geographic information module, power distribution management module, and automation control module respectively;

[0031] Determine the weights of the power distribution equipment geographic information module, power distribution management module, and automation control module based on historical parameter data, expert experience, and scoring mechanism;

[0032] According to the accuracy scoring logic and weights, a weighted accuracy rate is calculated.

[0033] As a preferred solution of the control method of the distribution automation network access information system of the present invention, wherein: the real-time parameter data of each module of the distribution automation network access information system is obtained, the type of the current distribution network fault mode is determined according to the real-time parameter data of the distribution data acquisition module, and whether to access the second control module according to the type of the current distribution network fault mode is determined, including:

[0034] Establishing a distribution network fault mode recognition model based on a neural network, wherein the input of the distribution network fault mode recognition model is a first preprocessing result of the historical parameter data of the distribution data acquisition module, and the output is a distribution network fault mode probability;

[0035] Obtain the real-time parameter data of each module of the distribution automation network access information system, obtain the real-time parameter data of the module based on the distribution data, and determine the type of the current distribution network fault mode in combination with the distribution network fault mode recognition model;

[0036] If at most two of the weighted correct rates of the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode, and the frequency fluctuation fault mode are lower than the first threshold, the second control module is connected;

[0037] If at least three of the weighted correct rates of the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode and the frequency fluctuation fault mode are higher than the first threshold, the second control module will not be connected.

[0038] As a preferred solution of the control method of the distribution automation network access information system described in the present invention, wherein: the first threshold is calculated according to the user's accuracy requirement.

[0039] In a second aspect, the present invention provides a control system for a distribution automation network access information system, comprising:

[0040] A first overall data acquisition module, used to acquire historical parameter data of each module of the distribution automation network access information system, and perform a first preprocessing on the historical parameter data, wherein the distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module, and an automation control module;

[0041] A mode judgment module, used to obtain a distribution network fault mode according to a first preprocessing result of the historical parameter data of the distribution data acquisition module in combination with an improved clustering algorithm;

[0042] A data processing module, used for performing a second preprocessing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing in combination with the distribution network fault mode, wherein the second preprocessing is used for structuring the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing;

[0043] A weighted accuracy acquisition module, used to acquire the weighted accuracy of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes according to the second preprocessing result;

[0044] The judgment module is used to judge whether to connect the second control module in different distribution network failure modes according to the weighted correctness, and the second control module includes a second control logic.

[0045] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method when executing the computer program.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method described above when executed by a processor.

[0047] Compared with the prior art, the present invention has the following beneficial effects: the present invention proposes a control method and system for a distribution automation network access information system, which obtains historical parameter data of each module of the distribution automation network access information system and performs a first preprocessing on the historical parameter data, wherein the distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module and an automation control module; according to the first preprocessing result of the historical parameter data of the distribution data acquisition module, combined with an improved clustering algorithm, a distribution network fault mode is acquired; in combination with the distribution network fault mode, a second preprocessing is performed on the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing, wherein the second preprocessing is used to structure the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing; according to the second preprocessing result, the weighted correctness of the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing under different distribution network fault modes is obtained; according to the weighted correctness, it is judged whether the second control module is connected to different distribution network fault modes, and the second control module includes a second control logic. It has realized the comprehensive monitoring and management of the distribution automation network access information system, and has achieved remarkable results in the handling of distribution network faults. It has also realized the accurate identification and handling of distribution network fault modes, providing a strong guarantee for the stable operation of the distribution automation network access information system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative labor. Among them:

[0049] Figure 1 A control method for a distribution automation network access information system and a method flow chart of the system are provided for one embodiment of the present invention;

[0050] Figure 2 A control method for a distribution automation network access information system and an internal structure diagram of a computer device of the system are provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention. Example 1

[0052] Reference Figure 1-Figure 2 , is the first embodiment of the present invention, which provides a control method and system for a distribution automation network access information system, including a control method for a distribution automation network access information system and a control system for a distribution automation network access information system, wherein a control method for a distribution automation network access information system includes:

[0053] Before describing the embodiments of the present application in detail, some related concepts are first explained for the sake of clarity.

[0054] Distribution Automation Network Information System: Distribution Automation Network Information System refers to an intelligent management system that integrates computer technology, communication technology and control technology, and is specifically used to monitor and manage the operating status of the distribution network. It is mainly responsible for real-time collection, processing and analysis of various data in the distribution network (such as current, voltage, load, fault information, etc.), and realizes functions such as remote monitoring of power grid equipment, rapid fault location, fault isolation and power supply restoration, and optimization of operation strategies. Through automation means, the system improves the operating efficiency, reliability and service quality of the distribution network, and reduces power outage time and operation and maintenance costs. The "network access" of the network information system means that the system can access a higher-level dispatching or management system to achieve data sharing and collaborative control.

[0055] Clustering algorithm: Clustering algorithm is an unsupervised learning method, mainly used in the field of data mining and machine learning. Its purpose is to divide unlabeled data sets into multiple groups or categories (called clusters), so that the data objects within the cluster have high similarity, while the data objects between different clusters are quite different. Clustering algorithms do not rely on pre-known classification information, but automatically discover hidden structures and patterns through the characteristics of the data itself. Common clustering algorithms include K-means, hierarchical clustering, DBSCAN (density-based clustering algorithm), spectral clustering, etc. These algorithms are widely used in market segmentation, document classification, image segmentation, social network analysis and other scenarios.

[0056] Correlation analysis method: Correlation analysis method is a statistical method used to study the relationship between variables. It aims to explore whether there is a statistically significant association between two or more variables, as well as the nature and strength of this association. The most commonly used is the Pearson correlation coefficient (Pearson's r), which measures the degree of linear correlation. The value range is from -1 to 1. Close to 1 indicates positive correlation, close to -1 indicates negative correlation, and close to 0 indicates no obvious linear relationship. In addition, there is Spearman's rho for correlation analysis of nonlinear data, as well as Kendall's rho, etc. Correlation analysis method is widely used in social sciences, medical research, financial analysis, marketing and other fields to help researchers understand the intrinsic connection between data and provide a basis for decision-making.

[0057] In the related existing technologies, the control and management of the distribution automation network access information system often have some deficiencies. For example, the identification and processing of distribution network fault modes may not be accurate enough, resulting in low fault processing efficiency and even affecting the stable operation of the entire distribution system.

[0058] The present application provides a method for effectively solving the above-mentioned problems. Next, a control method for implementing the distribution automation network access information system will be described in detail in combination with multiple embodiments.

[0059] Figure 1 A control method of a distribution automation network access information system and a method flow chart of the system are shown, including:

[0060] S101, obtaining historical parameter data of each module of the distribution automation network access information system, and performing a first preprocessing on the historical parameter data, the distribution automation network access information system at least comprising a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module and an automation control module;

[0061] In an embodiment of the present application, the power distribution data acquisition module is used to monitor and collect key operating parameters in the power distribution system in real time, such as current, voltage, power, load, frequency, switch status, etc., to provide basic data support for system analysis and fault diagnosis.

[0062] The distribution equipment geographic information module is used to display and manage the physical layout information of the distribution network, including equipment location, line direction, substation distribution, geographical environment, etc., and is combined with real-time data to assist in fault location and resource scheduling.

[0063] The power distribution management module is used for decision-making and execution of control instructions. Based on the results of monitored data analysis, it generates management strategies and control commands for specific situations, such as dispatch instructions, maintenance plans, and load adjustments. It also records operation logs and personnel management information.

[0064] The communication module is used for information exchange and command transmission to ensure smooth data flow between the various components of the distribution system, including real-time data, control signals, alarm information, management decisions, etc., and supports remote monitoring and automated control.

[0065] The automation control module is used to execute control logic, respond to instructions from the distribution management module, and automatically adjust or control equipment operation, such as switch operation, voltage / frequency adjustment, protection action, etc., to achieve rapid fault handling and system optimization operation, and improve efficiency and stability.

[0066] It should be noted that by acquiring and preprocessing historical parameter data, noise and outliers in the data can be eliminated, and the quality and consistency of the data can be improved. This helps to more accurately reflect the operating status and performance of the distribution automation network information system, and provides a reliable basis for subsequent pattern recognition, fault prediction and other analysis work. At the same time, the preprocessed data can also improve the execution efficiency and accuracy of subsequent algorithms and reduce the consumption of computing resources.

[0067] S102, acquiring a distribution network fault mode according to a first preprocessing result of the historical parameter data of the distribution data acquisition module in combination with an improved clustering algorithm;

[0068] Wherein, according to the first preprocessing result of the historical parameter data of the power distribution data acquisition module, in combination with the improved clustering algorithm, obtaining the distribution network fault mode includes: the historical parameter data of the power distribution data acquisition module at least includes line current, phase voltage, active power, reactive power, switch state, last operation time, load level, grid frequency, number of relay actions and fault duration;

[0069] Furthermore, the first preprocessing includes data cleaning, normalization and feature extraction of the historical parameter data of the power distribution data acquisition module, and extracting target features using an improved correlation analysis method;

[0070] Furthermore, the distribution network fault mode is obtained according to the target characteristics combined with the improved clustering algorithm. The distribution network fault mode includes instantaneous short circuit fault mode, continuous overload fault mode, single-phase grounding fault mode, line break fault mode and frequency fluctuation fault mode.

[0071] In the embodiment of the present application, the specific operation of extracting target features using the improved correlation analysis method can be as follows:

[0072] Step 1: Use Pearson's correlation coefficient or Spearman's rank correlation coefficient to measure the linear or nonlinear correlation between each two parameters. This step aims to identify which parameters have strong or weak correlation.

[0073] Step 2: Set a threshold value for the correlation coefficient based on the statistical significance level. Only correlations exceeding this threshold value are considered significant. For example, in this application, this threshold value is set to 75%. In other scenarios, it can be set to 50%, 80%, or 95%. The specific threshold value is determined by the user and is not restricted here.

[0074] Step 3: Create a network diagram of the historical parameter data of the power distribution data acquisition module to improve the correlation analysis method, where the nodes in the network diagram represent various parameters, and the width or color of the edge represents the strength of the correlation. Because the historical parameter data of the power distribution data acquisition module are of many types, a network diagram is designed to replace the original data value judgment by color and width;

[0075] Step 4: Improve the correlation analysis method and use recursive feature elimination combined with a machine learning model to select the most discriminative and independent feature subsets. The target features are those parameters that are most influential in fault identification and have the least information overlap.

[0076] In the embodiment of the present application, the specific steps of using recursive feature elimination combined with a machine learning model to select the most discriminative and mutually independent feature subsets are:

[0077] Set feature set , where n is the number of features, each Indicates a feature;

[0078] Initialize the SVM model and select a suitable kernel function. This application selects a linear kernel. You can also select an RBF kernel and parameters in other scenarios. This application selects the regularization parameter C.

[0079] Use all features F to train the SVM model and calculate the importance scores of the features. In SVM, the importance of a feature can be expressed by the absolute value of the weight. To measure, where j is the feature index, and the feature is weighted by its weight Sort in descending order.

[0080] Select the first k features from the sorted feature list, where k is initialized to n (i.e. all features). Use these k features to retrain the SVM model and use cross-validation to evaluate the model performance. This application chooses to calculate the average accuracy for evaluation. Remove the feature with the lowest weight in the current model, update the feature set, and repeat the above steps until the preset minimum number of features is reached or the performance is no longer significantly improved. The minimum number of features in this application is 2;

[0081] It should be noted that, through the above process, the feature set finally retained is the most discriminative and mutually independent feature subset, which is the most critical for fault identification and has the least information overlap.

[0082] In the embodiment of the present application, the distribution network failure mode is obtained according to the target features combined with the improved clustering algorithm. The specific operations are as follows:

[0083] Step 1: Standardize the most discriminative and independent feature subsets to ensure that the feature values ​​are compared on the same scale;

[0084] Step 2: Build a time series window for each feature. For example, in this application, data points for the past 248 hours are set to form a time series vector. Different time series windows can be set according to different scenario requirements.

[0085] Step 3: When clustering, use DTW distance instead of traditional Euclidean distance to adapt to the nonlinear alignment of time series.

[0086] Step 4: Randomly or heuristically select K samples as the initial cluster centers. For each time series sample, calculate its DTW distance to each cluster center, assign it to the nearest cluster, and recalculate the time series center of each cluster. The median or representative sequence of the sequence can be used. Repeat until the cluster center change is less than the predetermined threshold or the maximum number of iterations is reached.

[0087] Step 5: Analyze the time series pattern of each cluster and identify fault modes such as instantaneous short circuit, overload, grounding, etc. by combining domain knowledge.

[0088] In the embodiment of the present application, the time series pattern of each cluster is analyzed, and the specific steps of identifying the fault mode in combination with domain knowledge are as follows:

[0089] ① Perform statistical analysis on the characteristic values ​​of each cluster. In this application, the median is used to verify the statistical analysis results and determine the characteristic distribution characteristics of each cluster. The mean, extreme value, etc. can also be used for analysis and verification;

[0090] ② Observe common patterns of time series in clusters, such as specific waveforms, frequencies, periodicities, or trends, which can indicate specific types of faults.

[0091] ③ Based on historical failure cases and theoretical knowledge, establish a mapping library between features and failure modes. For example, the mapping library established in this application is based on the following content:

[0092] Short circuit faults are usually accompanied by a surge in current and a sudden drop in voltage.

[0093] An overload fault is manifested as a continuously high current and a load level approaching or exceeding the design value.

[0094] When a ground fault occurs, the three-phase voltages are unbalanced and the grounded phase voltage drops significantly.

[0095] A line break fault may cause a sudden decrease in current and load levels and an increase in voltage on a specific line.

[0096] Frequency fluctuations may be associated with unstable power supply or the connection of a large number of non-synchronous power sources.

[0097] ④Compare the statistical characteristics and time series patterns of the clusters with the feature-pattern library to identify the most matching fault mode.

[0098] In an optional embodiment, domain experts may be invited to review the preliminary judgment, and the experts' experience and knowledge may be used to verify whether the corresponding relationship between the clustering features and the failure modes is reasonable.

[0099] It should be noted that by extracting target features through improved correlation analysis, the feature subset that is most relevant to the distribution network fault mode and has the least information overlap can be more accurately identified. This method not only improves the efficiency of feature selection, but also reduces the complexity of data processing, making subsequent fault identification more accurate and reliable.

[0100] Recursive feature elimination combined with machine learning models is used to select the most discriminative feature subset, further improving the accuracy and stability of feature selection. In a recursive way, features that contribute less to fault identification are gradually eliminated, retaining the most representative feature set, thereby improving the accuracy and robustness of fault identification.

[0101] In addition, by combining domain knowledge and historical failure cases to establish a mapping library between features and failure modes, it provides strong support for the identification of failure modes. This mapping library can help the system quickly match clustered statistical features and time series patterns with known failure modes, thereby achieving automatic identification and classification of failures.

[0102] S103, performing a second preprocessing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing in combination with the distribution network fault mode, wherein the second preprocessing is used to structure the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing;

[0103] Among them, the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing are subjected to a second preprocessing in combination with the distribution network fault mode, and the second preprocessing is used to structure the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing, including: the second preprocessing structures the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing according to the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode and the frequency fluctuation fault mode;

[0104] Furthermore, the historical parameter data of the geographic information module of the power distribution equipment includes at least the location of the fault and the record of the environmental conditions under which the fault occurred;

[0105] Furthermore, the historical parameter data of the power distribution management module includes at least feedback on the execution status of the management control instructions generated for the fault and operator records;

[0106] Furthermore, the historical parameter data of the automation control module at least includes corresponding operations performed in response to the management control instructions generated by the power distribution management module, as well as operation timestamps and performance evaluation indicators of operation results.

[0107] It should be noted that by combining the distribution network failure mode with the second preprocessing of the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module, the data can be further structured, making the subsequent data analysis and mining more efficient and accurate. This step not only takes into account the diversity of distribution network failure modes, but also performs targeted processing on the historical parameter data of each module, thereby better retaining the key information in the data and removing redundant and irrelevant information.

[0108] In the second preprocessing process, the historical parameter data of each module is structured according to the known distribution network fault modes (such as instantaneous short circuit fault mode, continuous overload fault mode, etc.). This includes accurate positioning of the fault location, detailed recording of the environmental conditions where the fault occurs, feedback on the execution status of the management control instructions and the integration of operator records, as well as the extraction of performance evaluation indicators for the corresponding operations, operation timestamps and operation results of the management control instructions in the automation control module. Through such structured processing, the causes, impact range and treatment effects of distribution network faults can be better understood and analyzed, providing strong data support for subsequent fault prediction and early warning.

[0109] S104, according to the second preprocessing result, obtaining the weighted correctness of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes;

[0110] Wherein, according to the second preprocessing result, obtaining the weighted correctness of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes includes: establishing the accuracy scoring logic of the power distribution equipment geographic information module, the power distribution management module and the automation control module respectively;

[0111] Furthermore, the weights of the distribution equipment geographic information module, the distribution management module, and the automation control module are determined based on historical parameter data, expert experience, and a scoring mechanism;

[0112] Furthermore, the weighted accuracy is calculated based on the accuracy scoring logic and weights.

[0113] In the embodiment of the present application, the specific steps for determining the weights of the power distribution equipment geographic information module, the power distribution management module and the automation control module according to the historical parameter data, expert experience and scoring mechanism are as follows:

[0114] A. The contribution of any module fault response is , analyze the response time, processing efficiency and other data of each module in historical fault processing according to historical parameter data to evaluate its direct contribution to system recovery. , , They represent the contribution of geographic information, management, and automation control modules respectively.

[0115] B. The failure prevention effect of any module is The effectiveness of each module in preventing failures is evaluated based on historical parameter data, such as the accuracy of early warnings, the effectiveness of control instructions, etc. Represent the preventive effect of each module respectively.

[0116] C. Record the expert scoring result of any module as , organize industry experts to subjectively score the importance of each module, in this application embodiment, the range is 1 to 10 points, where 10 points means the most important. In this application embodiment, the expert score is ;

[0117] D. Combine historical data analysis and expert scoring to calculate the comprehensive score of each module by weighted average In the present embodiment, it is assumed that the importance ratio of historical data analysis and expert opinions is 7:3, then:

[0118]

[0119] The comprehensive scores are normalized to ensure that the sum of the weights is 1.

[0120]

[0121] It should be noted that according to the above four steps A, B, C, and D, reasonable weights are assigned to each module of the power distribution equipment in combination with objective data and subjective experience. These weights can be directly used to calculate the weighted accuracy, reflecting the overall performance of the system more comprehensively and accurately.

[0122] In the embodiment of the present application, according to the accuracy scoring logic and weights, the specific steps for calculating the weighted accuracy are:

[0123] Specifically, the accuracy scoring steps of the distribution equipment geographic information module are as follows:

[0124] 1. The fault location accuracy score of the distribution equipment geographic information module is Based on the positioning error range, if the positioning error is small, the score is close to 1; if the error is large, the score is reduced. For example, in the embodiment of the present application, less than 10 meters is set as 1 point, and 0.1 points are deducted for every 10 meters of error, until 0 points.

[0125] 2. Record the completeness score of the environmental condition records of the distribution equipment geographic information module as , check whether key environmental factors such as temperature, humidity, weather conditions, etc. are fully recorded. 0.2 points will be deducted for each missing item, with a full score of 1 point.

[0126] The mathematical expression for the accuracy score of the distribution equipment geographic information module is as follows:

[0127]

[0128] in, It indicates that positioning accuracy is slightly more important than environmental condition record. It is a weight factor used to balance the importance of the two parts of the score. In the embodiment of the present application, it is set to 0.6.

[0129] The steps for scoring the accuracy of the power distribution management module are as follows:

[0130] 1. The accuracy of the instruction execution status feedback of the power distribution management module is , the score is based on the success rate of control instruction execution, 100% success is 1 point, and 0.1 point is deducted for every 10% decrease in success rate.

[0131] 2. Record the integrity of operator records in the power distribution management module as , 1 point will be awarded if the recorded operator information (such as name, time, operation details) is complete and correct, and 0.1 point will be deducted for each missing or incorrect item.

[0132] The mathematical expression of the accuracy score of the power distribution management module is as follows:

[0133]

[0134] in, is a weight factor, assuming that the accuracy of instruction execution is more critical, and is set to 0.7 in the embodiment of the present application.

[0135] The steps for grading the accuracy of the automation control module are:

[0136] 1. Record the automation control module operation response time score as If the response time is within the preset time, the full score will be awarded. After the time limit, the score will be reduced proportionally. For example, 0.1 point will be deducted for every 10% of the time exceeding the specified time.

[0137] 2. The performance evaluation index of the automation control module operation result is , including operational efficiency, resource utilization, etc., and full marks are given within the set standard range. Points will be deducted in proportion if the performance exceeds or falls below the standard range. Specific standards need to be formulated based on actual needs.

[0138] The mathematical expression of the automation control module accuracy score is as follows:

[0139]

[0140] in, is a weight factor. Assuming that response time is particularly important for automated control, it is set to 0.5 in the embodiment of the present application.

[0141] The calculation formula of weighted accuracy is as follows:

[0142]

[0143] in, The accuracy scores are respectively given to the distribution equipment geographic information module, distribution management module, and automation control module. are the weights of these three modules respectively, and satisfy .

[0144] It should be noted that the comprehensive score of each module is calculated by weighted average. The advantage of this approach is that it takes into account the advantages of historical data analysis and expert scoring, making the module weight distribution more scientific and reasonable. Historical data provides objective and quantitative information, reflecting the performance of each module in actual operation; while expert scoring incorporates the experience and knowledge of industry experts and conducts a subjective assessment of the importance of the module.

[0145] S105, judging whether to connect a second control module according to different distribution network failure modes according to the weighted correctness, where the second control module includes a second control logic.

[0146] Among them, judging whether to connect the second control module for different distribution network fault modes according to the weighted correctness includes: obtaining real-time parameter data of each module of the distribution automation network access information system, judging the type of the current distribution network fault mode according to the real-time parameter data of the distribution data acquisition module, and judging whether to connect the second control module according to the type of the current distribution network fault mode;

[0147] Furthermore, if it is determined that the second control module is to be connected, the communication module is immediately turned off, and the communication module is turned on again after the second control module is connected, and the connection between the communication module and the power distribution management module is disconnected at this time, and the power distribution equipment geographic information module and the automation control module are directly controlled by the second control module;

[0148] Furthermore, if it is determined that the second control module is not to be connected, the existing module is used to implement the operation of the distribution automation network access information system.

[0149] Furthermore, obtaining real-time parameter data of each module of the distribution automation network access information system, judging the type of current distribution network fault mode according to the real-time parameter data of the distribution data acquisition module, and judging whether to access the second control module according to the type of current distribution network fault mode includes: establishing a distribution network fault mode recognition model based on a neural network, the input of the distribution network fault mode recognition model is a first preprocessing result of the historical parameter data of the distribution data acquisition module, and the output is a distribution network fault mode probability;

[0150] Obtain the real-time parameter data of each module of the distribution automation network access information system, obtain the real-time parameter data of the module based on the distribution data, and determine the type of the current distribution network fault mode in combination with the distribution network fault mode recognition model;

[0151] If at most two of the weighted correct rates of the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode, and the frequency fluctuation fault mode are lower than the first threshold, the second control module is connected;

[0152] If at least three of the weighted correct rates of the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode and the frequency fluctuation fault mode are higher than the first threshold, the second control module will not be connected.

[0153] The first threshold is calculated according to the user's accuracy requirement.

[0154] In the embodiment of the present application, the loss function used to establish the distribution network fault mode recognition model based on the neural network is:

[0155]

[0156] in, is the one-hot encoding of the true label, is the probability of failure mode i predicted by the model, and 3 represents the number of modules.

[0157] In the embodiment of the present application, the relationship between the weighted correctness of the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode and the frequency fluctuation fault mode and the first threshold is determined, that is, In relationship with the first threshold, if at most two of the weighted correct rates of the instantaneous short circuit fault mode, continuous overload fault mode, single-phase grounding fault mode, disconnection fault mode and frequency fluctuation fault mode are lower than the first threshold, the second control module is connected; if at least three of the weighted correct rates of the instantaneous short circuit fault mode, continuous overload fault mode, single-phase grounding fault mode, disconnection fault mode and frequency fluctuation fault mode are higher than the first threshold, the second control module is not connected.

[0158] In an embodiment of the present application, when the user accuracy is higher than 90%, the first threshold is 0.85; when the user accuracy is not higher than 90% and not lower than 80%, the first threshold is 0.78; when the user accuracy is lower than 80%, the first threshold is 0.72, wherein the first thresholds are obtained through the adjustment curve obtained through experiments.

[0159] In the embodiment of the present application, the second control module is connected to the distribution automation network access information system before processing the fault mainly relying on the existing basic module collaboration, the process is as follows:

[0160] Before the second control module is connected, first, the module collects key parameters such as current, voltage, load, switch status, fault indication, etc. of the power grid in real time through sensors and monitoring equipment to monitor preliminary fault signs. Combined with the fault location system, once an abnormality is detected, the specific location of the fault is immediately determined, including longitude and latitude, line, equipment number, etc., to provide precise guidance for subsequent actions. According to the feedback from the geographic information module, the distribution management module generates control instructions, such as isolating the fault area, switching lines, adjusting loads, etc., and records the operator and the execution status of the instructions to ensure orderly operation. After receiving the instructions from the management module, the automation control module immediately executes, such as remote control switch operation, and records the operation timestamp and performance evaluation to evaluate whether the operation is successful and its efficiency. Throughout the process, the communication module ensures the smooth transmission of information between modules. Whether it is real-time data, control instructions or feedback information, they are all interacted in real time through the communication network to ensure the immediate response of the system.

[0161] After the second control module is connected, it means the introduction of a higher level of control or a more sophisticated processing mechanism. The processing flow includes: the second control module first strengthens data acquisition and analysis, uses more complex algorithms to identify potential fault modes in advance, and improves early warning capabilities. After the connection, the second control module directly participates in guiding the decision-making process, intelligently generates more optimized control strategies based on the current system status and fault mode, and conducts autonomous intervention. In terms of automated control, the second control module performs more detailed regulation, such as precise load transfer, voltage regulation, and fault isolation strategies to reduce the impact range and recovery time. Between the original system modules, the second control module optimizes the overall response process through closer linkage. For example, it can instantly adjust the positioning accuracy of the geographic information module, or guide the automation module to take preventive measures. The second control module may also have a learning function, which optimizes its own algorithms and strategies based on the processing results and fault handling experience, and continuously improves the efficiency and accuracy of the system in responding to faults.

[0162] In an embodiment of the present application, after the second control module is connected, it can also receive and integrate all real-time data collected from the basic monitoring module, use advanced data analysis and machine learning algorithms to perform preliminary analysis, and identify abnormal trends and potential faults. The second control module can quickly identify possible precursors to faults, predict the probability and scope of fault occurrence, and promptly alert the power distribution management system. The second control module shares prediction information with other modules through a high-speed communication interface (such as the IEC 61850 standard communication protocol) to trigger an early warning mechanism. The control instructions optimized by the second control module are sent to the corresponding automation control modules and field equipment (such as RTU, DTU) through the communication network. The automation control module executes the instructions and feeds back the execution status and effect to the second control module through the communication loop to achieve closed-loop control.

[0163] In an optional embodiment, after the fault is eliminated, the system gradually resumes normal operation, and the second control module can also monitor the recovery process to ensure that there are no residual problems and update the system status.

[0164] In an optional embodiment, a second control module may be configured to post-evaluate the processing process, analyze key indicators such as processing efficiency and response time, and continuously optimize the prediction model and control strategy using machine learning technology.

[0165] In an optional embodiment, the second control module may also promote system parameter adjustment or strategy improvement based on the learning results to enhance the adaptability and fault response capabilities of the overall system.

[0166] In summary, the present invention proposes a control method for a distribution automation network access information system, which obtains historical parameter data of each module of the distribution automation network access information system and performs a first preprocessing on the historical parameter data, wherein the distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module and an automation control module; according to the first preprocessing result of the historical parameter data of the distribution data acquisition module, combined with an improved clustering algorithm, a distribution network fault mode is obtained; in combination with the distribution network fault mode, a second preprocessing is performed on the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing, wherein the second preprocessing is used to structure the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing; according to the second preprocessing result, the weighted correctness of the historical parameter data of the distribution equipment geographic information module, the distribution management module and the automation control module after the first preprocessing under different distribution network fault modes is obtained; according to the weighted correctness, it is judged whether to connect the second control module in different distribution network fault modes, and the second control module includes a second control logic. It has realized the comprehensive monitoring and management of the distribution automation network access information system, and has achieved remarkable results in the handling of distribution network faults. It has also realized the accurate identification and handling of distribution network fault modes, providing a strong guarantee for the stable operation of the distribution automation network access information system.

[0167] This embodiment also provides a control system for a distribution automation network access information system, including:

[0168] A first overall data acquisition module is used to acquire historical parameter data of each module of the distribution automation network access information system and perform a first preprocessing on the historical parameter data. The distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module and an automation control module;

[0169] A mode judgment module, used to obtain a distribution network fault mode according to a first preprocessing result of the historical parameter data of the distribution data acquisition module in combination with an improved clustering algorithm;

[0170] A data processing module, used for performing a second preprocessing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing in combination with the distribution network fault mode, wherein the second preprocessing is used for structuring the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing;

[0171] A weighted accuracy acquisition module, used to acquire the weighted accuracy of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes according to the second preprocessing result;

[0172] The judgment module is used to judge whether to connect the second control module according to the weighted correctness rate in different distribution network failure modes, and the second control module includes a second control logic.

[0173] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0174] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2 As shown. The computer device includes a processor, a memory, a communication 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 communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a control method for a distribution automation network access information system is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0175] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0176] Obtain historical parameter data of each module of the distribution automation network access information system, and perform a first preprocessing on the historical parameter data, the distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module and an automation control module;

[0177] According to the first preprocessing result of the historical parameter data of the power distribution data acquisition module, combined with the improved clustering algorithm, the distribution network fault mode is obtained;

[0178] Performing a second preprocessing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing in combination with the distribution network fault mode, wherein the second preprocessing is used to structure the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing;

[0179] According to the second preprocessing result, the weighted correctness of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes is obtained;

[0180] According to the weighted correctness, it is determined whether to connect the second control module in different distribution network failure modes, and the second control module includes a second control logic. Example 2

[0181] Reference Figure 1-Figure 2 , which is an embodiment of the present invention, provides a control method and system for a distribution automation network access information system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0182] First, in order to verify the effectiveness of the control method of the distribution automation network access information system of the present invention, an actual distribution automation network access information system was selected as the experimental object. The system includes multiple modules such as a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module, and an automation control module. According to the steps in Example 1, the historical parameter data of these modules were processed and analyzed.

[0183] In the experiment, the historical parameter data of each module of the distribution automation access information system were first obtained, and the data were preprocessed in the first place. Then, the distribution network fault mode was obtained based on the first preprocessing results of the historical parameter data of the distribution data acquisition module using the improved clustering algorithm. Then, combined with the distribution network fault mode, the historical parameter data of the distribution equipment geographic information module, the distribution management module, and the automation control module were preprocessed in the second place to structure them for subsequent analysis and processing.

[0184] According to the second preprocessing result, the weighted correctness of each module under different distribution network fault modes is calculated. By comparing the weighted correctness under different fault modes, it can be determined which fault modes require the access of the second control module to improve the stability and reliability of the system.

[0185]

[0186] The experimental results show that by applying the control method of the distribution automation network access information system of the present invention, it is possible to achieve comprehensive monitoring and management of the distribution automation network access information system, improve the stability and reliability of the system. At the same time, it is also possible to accurately identify and process the distribution network fault mode, and improve the efficiency and accuracy of fault processing.

[0187] In order to further verify the beneficial effects of the present invention, a comparative experiment was conducted in which a conventional control method of a distribution automation network access information system was used and compared with the control method of the present invention.

[0188]

[0189] Experimental results show that, compared with traditional control methods, the control method of the present invention achieves better results in distribution network fault processing and improves the accuracy and efficiency of fault processing.

[0190] In addition, the performance of the computer device and computer-readable storage medium provided by the present invention is verified. By deploying the control method of the present invention on a computer device and storing it in a computer-readable storage medium, its feasibility and effectiveness in practical applications are verified. The experimental results show that the computer device and computer-readable storage medium can stably run the control method of the present invention and realize comprehensive monitoring and management of the distribution automation network access information system.

[0191] In summary, the control method and system of the distribution automation network access information system of the present invention realizes accurate identification and processing of distribution network fault modes by improving the application of clustering algorithm and calculation of weighted accuracy, and improves the stability and reliability of the distribution automation network access information system. At the same time, by being deployed to a computer device and stored in a computer-readable storage medium, the method also has practical application value and feasibility.

[0192] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0193] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present application may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0194] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0195] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0196] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0197] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0198] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A control method for a distribution automation network access information system, characterized in that: include: Acquire historical parameter data of each module of the distribution automation network access information system, and perform a first preprocessing on the historical parameter data, wherein the distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module, and an automation control module; According to the first preprocessing result of the historical parameter data of the power distribution data acquisition module, combined with the improved clustering algorithm, the distribution network fault mode is obtained, including: The historical parameter data of the power distribution data acquisition module at least includes line current, phase voltage, active power, reactive power, switch status, last operation time, load level, grid frequency, relay action times and fault duration; The first preprocessing includes data cleaning, normalization and feature extraction of the historical parameter data of the power distribution data acquisition module, and extracting target features using an improved correlation analysis method; According to the target features combined with the improved clustering algorithm, a distribution network fault mode is obtained, wherein the distribution network fault mode includes an instantaneous short circuit fault mode, a continuous overload fault mode, a single-phase grounding fault mode, a disconnection fault mode, and a frequency fluctuation fault mode; The target feature combined with the improved clustering algorithm includes: Standardize the most discriminative and independent feature subsets to ensure that feature values ​​are compared on the same scale; Construct time series windows for each feature; When clustering, DTW distance is used to accommodate the nonlinear alignment of time series; Randomly or heuristically select K samples as the initial cluster centers. For each time series sample, calculate its DTW distance with each cluster center, assign it to the nearest cluster, recalculate the time series center of each cluster, use the median or representative sequence of the sequence, and repeat until the change of the cluster center is less than the predetermined threshold or the maximum number of iterations is reached; Analyze the time series pattern of each cluster and identify the failure mode by combining domain knowledge; In combination with the distribution network fault mode, the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing are subjected to a second preprocessing, wherein the second preprocessing is used to structure the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing, including: The second preprocessing performs structured processing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing according to the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode and the frequency fluctuation fault mode; the historical parameter data of the power distribution equipment geographic information module at least includes the positioning of the fault location and the record of the environmental conditions where the fault occurs; The historical parameter data of the power distribution management module includes at least feedback on the execution status of management control instructions generated for faults and operator records; The historical parameter data of the automation control module at least includes the corresponding operation performed for the management control instruction generated by the power distribution management module, as well as the operation timestamp and the performance evaluation index of the operation result; According to the second preprocessing result, the weighted correctness of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes is obtained; According to the weighted correctness, it is determined whether to connect a second control module in different distribution network failure modes, and the second control module includes a second control logic.

2. The control method of the distribution automation network access information system according to claim 1, characterized in that: The determining, according to the weighted correctness, whether to perform access to the second control module in different distribution network failure modes includes: Acquire the real-time parameter data of each module of the distribution automation network access information system, determine the type of current distribution network fault mode according to the real-time parameter data of the distribution data acquisition module, and determine whether to access the second control module according to the type of current distribution network fault mode; If it is determined that the second control module is to be connected, the communication module is immediately turned off, and the communication module is turned on again after the second control module is connected. At this time, the connection between the communication module and the power distribution management module is disconnected, and the power distribution equipment geographic information module and the automation control module are directly controlled by the second control module; If it is determined that the second control module is not to be connected, the existing module is used to implement the operation of the distribution automation network access information system.

3. The control method of the distribution automation network access information system according to claim 2, characterized in that: The method of obtaining the weighted correctness of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes according to the second preprocessing result includes: Establish accuracy scoring logic for the power distribution equipment geographic information module, power distribution management module, and automation control module respectively; Determine the weights of the power distribution equipment geographic information module, power distribution management module, and automation control module based on historical parameter data, expert experience, and scoring mechanism; According to the accuracy scoring logic and weights, a weighted accuracy rate is calculated.

4. The control method of the distribution automation network access information system according to claim 3, characterized in that: The acquiring of real-time parameter data of each module of the distribution automation network access information system, judging the type of current distribution network fault mode according to the real-time parameter data of the distribution data acquisition module, and judging whether to access the second control module according to the type of current distribution network fault mode includes: Establishing a distribution network fault mode recognition model based on a neural network, wherein the input of the distribution network fault mode recognition model is a first preprocessing result of the historical parameter data of the distribution data acquisition module, and the output is a distribution network fault mode probability; Obtain the real-time parameter data of each module of the distribution automation network access information system, obtain the real-time parameter data of the module based on the distribution data, and determine the type of the current distribution network fault mode in combination with the distribution network fault mode recognition model; If at most two of the weighted correct rates of the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode, and the frequency fluctuation fault mode are lower than the first threshold, the second control module is connected; If at least three of the weighted correct rates of the instantaneous short circuit fault mode, the continuous overload fault mode, the single-phase grounding fault mode, the disconnection fault mode and the frequency fluctuation fault mode are higher than the first threshold, the second control module will not be connected.

5. The control method of the distribution automation network access information system according to claim 4, characterized in that: The first threshold is calculated according to the user's accuracy requirement.

6. A system using the control method of the distribution automation network access information system according to claim 1, characterized in that: include: A first overall data acquisition module, used to acquire historical parameter data of each module of the distribution automation network access information system and perform a first preprocessing on the historical parameter data, wherein the distribution automation network access information system at least includes a distribution data acquisition module, a distribution equipment geographic information module, a distribution management module, a communication module and an automation control module; A mode judgment module, used to obtain a distribution network fault mode according to a first preprocessing result of the historical parameter data of the distribution data acquisition module in combination with an improved clustering algorithm; A data processing module, used for performing a second preprocessing on the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing in combination with the distribution network fault mode, wherein the second preprocessing is used for structuring the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing; A weighted accuracy acquisition module, used to acquire the weighted accuracy of the historical parameter data of the power distribution equipment geographic information module, the power distribution management module and the automation control module after the first preprocessing under different distribution network fault modes according to the second preprocessing result; The judgment module is used to judge whether to connect the second control module in different distribution network failure modes according to the weighted correctness, and the second control module includes a second control logic.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.