Distribution network equipment abnormity monitoring method and system, electronic equipment and storage medium

Abstract

The invention relates to the technical field of power equipment monitoring, in particular to a distribution network equipment anomaly monitoring method and system, electronic equipment and a storage medium, which can improve the accuracy and timeliness of power equipment anomaly detection and provide powerful guarantee for stable operation of a power system. The method comprises the following steps: collecting operation data information of to-be-detected power equipment in a distribution network; performing data format conversion on the operation data information to obtain an equipment operation historical time sequence matrix; the electric power parameters of the same type in the equipment operation historical time sequence matrix are arranged according to a time sequence, and the electric power parameters with the same timestamp are located in the same row; performing abnormal feature extraction on the equipment operation historical time sequence matrix to obtain an abnormal representation vector of the power equipment; using a pre-constructed equipment operation data reconstruction model to perform data reconstruction on the power equipment anomaly representation vector to obtain an equipment operation reconstruction time sequence matrix; and performing deviation calculation on the equipment operation reconstruction time sequence matrix and the equipment operation historical time sequence matrix.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and in particular to a method, system, electronic equipment and storage medium for monitoring abnormality of distribution network equipment. Background Art

[0002] In the power system, the distribution network serves as a bridge between power sources and end users. Its stability and reliability are directly related to the quality and safety of power supply. However, with the expansion of the scale of the power grid and the increase in the number of power equipment, distribution network equipment will inevitably encounter various faults and abnormal conditions during operation, such as equipment aging, overload operation, short circuit, insulation failure, etc. If these abnormal conditions are not discovered and handled in time, they will not only affect the continuity and stability of power supply, but may also cause more serious power accidents, resulting in economic losses or even personal injury.

[0003] Existing distribution network equipment monitoring methods often extract abnormal features from a single operating parameter collected at different times, and judge whether there is an abnormality in the power equipment based on the extracted abnormal features. Due to the high dimensionality, nonlinearity and complexity of the power equipment operation data, the "single parameter and one-way dimensionality reduction" abnormality judgment method adopted by the existing method is too simple and is often easily affected by factors such as environmental changes and measurement errors, resulting in false alarms or missed alarms. Summary of the invention

[0004] To solve the above technical problems, the present invention provides a distribution network equipment abnormality monitoring method, system, electronic device and storage medium that can improve the accuracy and timeliness of power equipment abnormality detection and provide strong guarantee for the stable operation of the power system.

[0005] In a first aspect, the present invention provides a method for monitoring abnormalities of distribution network equipment, the method comprising: Collect operating data information of the power equipment to be tested in the distribution network; Performing data format conversion on the operation data information to obtain a device operation history time sequence matrix; in the device operation history time sequence matrix, power parameters of the same type are arranged in time sequence, and power parameters with the same timestamp are located in the same row; Extract abnormal features from the equipment operation history time series matrix to obtain the abnormal characterization vector of the power equipment; Using the pre-built equipment operation data reconstruction model, the abnormal characterization vector of the power equipment is reconstructed to obtain the equipment operation reconstruction time series matrix; Calculate the deviation between the equipment operation reconstruction time series matrix and the equipment operation history time series matrix to obtain the power equipment abnormality index; The abnormal index of the electric power equipment is compared with a preset abnormal threshold value, and if the abnormal index of the electric power equipment exceeds the preset abnormal threshold value, the electric power equipment is determined to be abnormal.

[0006] Furthermore, the device operation history timing matrix is: ; in, Indicates n At a point in time m The value of the type power parameter.

[0007] Furthermore, the method for extracting abnormal features from the equipment operation history time series matrix includes: Preprocess the equipment operation history time series matrix, including missing value filling, outlier processing and data normalization; Select a feature extraction method and determine the features to be extracted based on the specific type of power equipment and its common failure modes; Calculate the corresponding eigenvalue for each column in the equipment operation history time series matrix; The various calculated eigenvalues ​​are combined into a power equipment abnormality characterization vector.

[0008] Furthermore, the power equipment abnormality characterization vector is: ; in, Represents the historical timing matrix of slave device operation X Extracted from k Features.

[0009] Furthermore, the calculation formula of the power equipment abnormality index is: ; in, I Indicates the abnormal index of power equipment. Represents the first i The value at each time point; Represents the first i The value at each time point; wi is the weight of the corresponding parameter; N is the number of time points.

[0010] Furthermore, factors influencing the setting of the preset abnormal threshold include historical data analysis, equipment characteristics, environmental factors, measurement errors, data quality and safety margin.

[0011] Furthermore, the method for collecting operation data information of the power equipment to be detected includes: Clarify the monitoring objectives and determine the geographical areas and grid zones to be monitored; Set up data collection points next to power equipment according to equipment type and monitoring requirements; Deploy data collectors at data collection points and use wired and wireless methods to transmit the collected data; Set the frequency and cycle of data collection according to equipment characteristics and monitoring requirements; According to the set data collection frequency and cycle, the operating data information of the power equipment to be tested is collected through the data collector.

[0012] On the other hand, the present application also provides a distribution network equipment abnormality monitoring system, the system comprising: Data acquisition module, collecting operating data information of the power equipment to be tested in the distribution network; A data preprocessing module performs data format conversion on the operation data information to obtain a device operation history time series matrix; in the device operation history time series matrix, power parameters of the same type are arranged in time series, and power parameters with the same timestamp are located in the same row; The abnormal feature extraction module extracts abnormal features from the equipment operation history time series matrix to obtain the abnormal characterization vector of the power equipment; The data reconstruction module uses a pre-built equipment operation data reconstruction model to reconstruct the abnormal characterization vector of the power equipment and obtain the equipment operation reconstruction timing matrix; the equipment operation data reconstruction model is used to reversely reconstruct the ideal original data corresponding to the abnormal characterization vector of the power equipment, that is, the equipment operation reconstruction timing matrix; The deviation calculation module calculates the deviation between the equipment operation reconstruction timing matrix and the equipment operation history timing matrix to obtain the power equipment abnormality index; The abnormality determination module compares the abnormality index of the power equipment with a preset abnormality threshold, and if the abnormality index of the power equipment exceeds the preset abnormality threshold, the power equipment is determined to be abnormal.

[0013] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0014] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0015] Compared with the prior art, the present invention has the following beneficial effects: by collecting and processing the operating data of multiple power parameters to form a device operation history time series matrix, the method can analyze the operating status of power equipment in multiple dimensions; it can more comprehensively capture the abnormal conditions of the equipment and improve the accuracy and reliability of monitoring; The abnormal features are reversely reconstructed using the pre-built data reconstruction model, and the deviation between the reconstructed data and the actual data is compared, which can resist the interference of external factors such as environmental changes and measurement errors to a certain extent; the abnormal index obtained by calculating the deviation is more robust, reducing the possibility of false positives and false negatives; The abnormal feature extraction of the equipment operation history time series matrix not only considers the time series of parameters, but also integrates the correlation between multiple parameters; it can more effectively identify complex abnormal patterns and improve the sensitivity and accuracy of abnormal detection; By adjusting the preset abnormal threshold, it can be flexibly configured according to different monitoring needs and actual conditions; at the same time, the equipment operation data reconstruction model can also be continuously optimized as new data is continuously added, thereby improving the system's adaptability and accuracy; By real-time monitoring and analysis of the operating status of power equipment, this method can promptly detect potential abnormalities and provide sufficient time for taking preventive measures; it helps to reduce power supply interruptions and economic losses caused by equipment failures and improve the overall stability and reliability of the power system; The implementation of this method has promoted the development of power equipment monitoring towards intelligence; through automated data collection, processing and analysis, it can greatly reduce the workload of operation and maintenance personnel and improve operation and maintenance efficiency and quality; at the same time, it also provides strong support for the intelligent management and optimization of power systems; In summary, the distribution network equipment abnormality monitoring method effectively improves the accuracy and timeliness of power equipment abnormality detection through multi-dimensional comprehensive monitoring, complex data processing, data reconstruction and deviation analysis, and provides a strong guarantee for the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the present invention; Figure 2 It is a flow chart of a method for extracting abnormal features from a historical time series matrix of equipment operation; Figure 3 It is a structural diagram of a distribution network equipment abnormality monitoring system. DETAILED DESCRIPTION

[0017] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0018] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0019] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0020] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0021] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0022] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] The present application is described below in conjunction with the drawings in the present application.

[0024] Embodiment 1: Figure 1 to Figure 2 As shown, a distribution network equipment abnormality monitoring method of the present invention specifically includes the following steps: S1. Collecting the operating data information of the power equipment to be tested in the distribution network; The method for collecting operation data information of the power equipment to be detected includes: Identify which power equipment is the target of this monitoring, including transformers, switchgear, lines, capacitor banks and circuit breakers; Determine the geographical areas and grid zones to be monitored to ensure that the monitoring coverage is comprehensive and meets actual needs; According to the equipment type and monitoring requirements, data collection points are set at key parts of the power equipment; ensure that the collection points can truly reflect the operating status of the equipment, while considering the safety and maintainability of data collection; Deploy high-performance data collectors and transmit the collected data to the data center using wired and wireless methods; Set the frequency and period of data collection according to the equipment characteristics and monitoring requirements; for equipment with key parameters or prone to failure, the frequency of data collection should be increased to achieve real-time monitoring; Implement strict quality control measures during data collection, including data verification, outlier removal, data filtering, etc., to ensure data accuracy and reliability; Regularly inspect and maintain the data acquisition system to ensure it is in good working condition; Design data storage architecture and use database to store collected power equipment operation data; Establish a data management system to realize data classification, indexing, compression and encrypted storage to facilitate subsequent data analysis and processing.

[0025] In this step, by clarifying the monitoring targets and geographical areas, we ensure that the monitoring scope is wide and meets actual needs, avoid blind spots in monitoring, and improve the monitoring efficiency of the entire power system; setting data collection points at key locations of power equipment can directly obtain core data reflecting the operating status of the equipment, thereby improving the accuracy and effectiveness of monitoring; setting a reasonable data collection frequency and cycle based on equipment characteristics and monitoring requirements, achieving real-time monitoring of equipment status, and helping to identify potential problems in a timely manner; implementing strict quality control measures during the data collection process, effectively ensuring the accuracy and reliability of the data, and reducing the risk of false alarms and missed reports; and regularly inspecting and maintaining the data collection system. , ensuring the stable operation of the data acquisition system and avoiding data loss or errors caused by system failures; designing a reasonable data storage architecture and establishing a data management system to realize data classification, indexing, compression and encrypted storage, which not only improves the efficiency and security of data storage, but also facilitates subsequent data analysis and processing; high-quality power equipment operation data provides a solid foundation for subsequent abnormal feature extraction, data reconstruction and abnormality judgment, which helps to quickly and accurately identify equipment abnormalities and provide strong support for the stable operation of the power system; step S1 effectively collects the operation data information of the power equipment to be detected in the distribution network, laying a solid foundation for the entire monitoring process.

[0026] S2. Convert the operation data information into a data format to obtain a device operation history time series matrix; in the device operation history time series matrix, power parameters of the same type are arranged in time series, and power parameters with the same timestamp are located in the same row; The method for acquiring the device operation history time series matrix includes: Collecting operation data information from the power equipment to be tested in the distribution network and their corresponding timestamps; The collected data is sorted and organized according to equipment type and monitoring point to ensure that each type of power parameter can be clearly identified and distinguished; Clean the collected data, remove duplicate data, process missing values, and correct outliers to ensure the accuracy and completeness of the data; Convert the cleaned data into a unified format, including data type, timestamp format, and parameter units; this helps with subsequent data processing and analysis; Based on the cleaned and standardized data, a device operation history time series matrix is ​​constructed; each row of the device operation history time series matrix represents the set of all power parameters at a timestamp, and each column represents the value of the same type of power parameter at different timestamps; During the construction process, it is necessary to ensure that the power parameters of the same type are arranged in time sequence, that is, the values ​​in the same column are all measured values ​​of the same type of parameters; at the same time, the power parameters with the same timestamp are located in the same row; Assign a unique index and label to each row and column in the timing matrix to facilitate subsequent data retrieval and analysis; the design of the index and label should be concise and clear, and can intuitively reflect the structure and content of the data; the equipment operation history timing matrix is: ; in, Indicates n At a point in time m The value of the type power parameter.

[0027] In this step, by constructing the equipment operation history time series matrix, the originally scattered and disordered power equipment operation data is organized into a form with a clear structure and easy to analyze; this structured data representation method is not only convenient for subsequent data processing and analysis, but also improves the efficiency and accuracy of data processing; before constructing the time series matrix, the collected data is cleaned and standardized, duplicate data is removed, missing values ​​and outliers are processed, and the accuracy and completeness of the data are ensured; each row of the time series matrix represents the set of all power parameters at a timestamp, and each column represents the value of the same type of power parameter at different timestamps; so that the time dimension and parameter dimension are clearly distinguished in the matrix, which is convenient for time series analysis and parameter comparison analysis; By arranging the same type of power parameters in time series and ensuring that the power parameters with the same timestamp are in the same row, the time series matrix provides strong support for subsequent abnormal feature extraction and anomaly detection; this arrangement makes the performance of abnormal values ​​in the time series more obvious, which helps to timely discover and deal with equipment failures and abnormal conditions; assigning a unique index and tag to each row and column in the time series matrix makes data retrieval and analysis more efficient and convenient, which not only simplifies the process of data operation, but also improves the degree of automation of data processing; step S2 realizes the structuring, cleaning, standardization and orderly processing of power equipment operation data by constructing the equipment operation history time series matrix, laying a solid foundation for subsequent data analysis and anomaly detection.

[0028] S3, extracting abnormal features from the equipment operation history time series matrix to obtain an abnormal characterization vector of the power equipment; The method for extracting abnormal features from a historical time series matrix of equipment operation includes: Preprocess the equipment operation history time series matrix, including missing value filling, outlier processing, and data normalization; ensure that all features are within the same scale range to avoid features with large numerical ranges dominating the learning process; Select appropriate feature extraction methods. Common features include mean, variance, peak, valley, frequency domain features, and time domain features. The selection of features needs to be determined based on the specific type of power equipment and its common failure modes. For transformers, the peak value and frequency component of the current may be of concern; for cables, the changes in temperature and insulation resistance may be of greater concern. Calculate the corresponding eigenvalue for each column in the equipment operation history time series matrix; Combining the calculated various characteristic values ​​into an abnormal characterization vector of the power equipment, the abnormal characterization vector of the power equipment reflects the operation status of the equipment in multiple aspects; The power equipment abnormality characterization vector is: ; in, Represents the historical timing matrix of slave device operation X Extracted from k Features.

[0029] In this step, the integrity and consistency of the data are ensured by performing preprocessing steps such as missing value filling, outlier processing, and data normalization on the equipment operation history time series matrix; this not only improves the accuracy and reliability of subsequent feature extraction, but also avoids misjudgment caused by data quality issues; data normalization places all features in the same scale range, preventing features with a large numerical range from dominating the feature extraction and anomaly detection process; different features are selected to reflect the operating status of the equipment according to the specific type and common failure modes of the power equipment; this enables the anomaly monitoring method to more accurately identify different types of equipment anomalies; and for cables, monitoring changes in temperature and insulation resistance helps to detect problems such as insulation aging or damage. ; Combining the calculated various eigenvalues ​​into an abnormal characterization vector of the power equipment ensures that the abnormal characterization vector can fully reflect the operating status of the equipment in multiple aspects; Improving the sensitivity and accuracy of abnormality detection, so that even if the equipment performs normally in one aspect, abnormalities in other aspects can be discovered in time; By extracting and combining multiple features to form an abnormal characterization vector, the abnormal state of the power equipment can be identified more accurately; And then more comprehensively capture the operating characteristics of the equipment, thereby reducing false alarms and missed alarms; The abnormal feature extraction method in step S3 provides strong support for abnormal monitoring of power equipment through data preprocessing, flexible selection of feature extraction methods, comprehensive combination of eigenvalues, and improving the accuracy of anomaly detection.

[0030] S4. Reconstruct the data of the abnormal characterization vector of the power equipment using a pre-built equipment operation data reconstruction model to obtain an equipment operation reconstruction timing matrix; the equipment operation data reconstruction model is used to reversely reconstruct the ideal original data corresponding to the abnormal characterization vector of the power equipment, that is, the equipment operation reconstruction timing matrix; The abnormal characterization vector of the power equipment is used as input and passed to the trained equipment operation data reconstruction model; After receiving the abnormal characterization vector, the model uses the inherent laws and characteristic representations of normal equipment operation that it has learned to try to reversely reconstruct the idealized equipment operation data corresponding to the abnormal characterization vector. This process is the model trying to "correct" or "repair" the abnormal part of the input data to restore its normal state. The model outputs the reconstructed equipment operation data, namely, the equipment operation reconstruction timing matrix; this matrix is ​​similar in structure to the original equipment operation history timing matrix, but reflects the operation of the equipment under ideal conditions in terms of numerical value; The structure of the equipment operation data reconstruction model includes: Input layer: The power equipment abnormality representation vector is used as input data; it contains multiple key features that can characterize the abnormal state of the equipment; the number of neurons in the input layer matches the dimension of the abnormality representation vector to ensure that the model can receive complete abnormal information; Hidden layers: To handle complex nonlinear relationships, the model contains multiple hidden layers; each hidden layer consists of a certain number of neurons, and nonlinearity is introduced through activation functions, so that complex patterns in the data can be learned; neurons in the hidden layer are connected to neurons in the previous layer through weights and biases, and these parameters are continuously optimized through the training process to learn how to extract high-level features from the input data; The hidden layers also contain dimension reduction and dimension increase operations to more efficiently represent and reconstruct data; Output layer: used to output the device operation reconstruction timing matrix; the dimension and structure of this matrix are the same as the original device operation history timing matrix, but it contains the idealized data that the model reconstructs based on the abnormal characterization vector; The output layer uses an activation function that matches the nature of the data; if the reconstructed data contains continuous values, no activation function is used or a linear activation function is used; if it contains categorical labels, a Softmax activation function is used; however, in most device reconstruction scenarios, since the goal is to restore continuous time series data, the output layer does not use a nonlinear activation function.

[0031] In this step, the idealized equipment operation data corresponding to the abnormal characterization vector can be reversely generated by reconstructing the model. This process not only takes into account the normal mode and internal laws of equipment operation, but also attempts to "correct" or "repair" the abnormal part of the input data, thereby reducing false positives or omissions caused by environmental changes, measurement errors and other factors, and improving the accuracy of anomaly detection. The equipment operation data reconstruction model can resist the influence of external interference and noise to a certain extent by learning and simulating the data characteristics of the equipment under normal operating conditions. This enables the entire monitoring system to maintain high stability and reliability when facing a complex and changeable operating environment. The robustness of the system is enhanced; the reconstructed equipment operation timing matrix not only reflects the operation status of the equipment under ideal conditions, but can also be compared and analyzed with the actual equipment operation history timing matrix; based on the analysis results of the equipment operation reconstruction timing matrix, the health status and operation risks of the equipment can be evaluated more accurately; the equipment operation data reconstruction model is an important part of the intelligent operation and maintenance system; by integrating this model, real-time monitoring, early warning, diagnosis and decision support of power equipment can be realized, and the operation and maintenance work can be promoted to develop in the direction of intelligence and automation; this not only improves the efficiency and quality of operation and maintenance, but also reduces the labor intensity and work risks of operation and maintenance personnel.

[0032] S5. Calculate the deviation between the equipment operation reconstruction timing matrix and the equipment operation history timing matrix to obtain the power equipment abnormality index; For the corresponding parameter value at each time point, the difference between the device operation reconstructed timing matrix and the device operation historical timing matrix is ​​calculated; When calculating the overall deviation, different weights are applied to the deviation of each parameter, taking into account the different importance of different parameters to the health status of the device; the weighted average can help us more accurately reflect the overall health status of the device; Since different parameters have different dimensions and magnitudes, direct comparison will result in the bias of some parameters dominating; therefore, before calculating the overall bias, it is necessary to standardize the parameters so that they are on the same scale; After comprehensively considering the above factors, a comprehensive abnormality index is calculated by the formula. The calculation formula of the power equipment abnormality index is: ; in, I Indicates the abnormal index of power equipment. Represents the first i The value at each time point; Represents the first i The value at each time point; wi is the weight of the corresponding parameter; N is the number of time points; The level of the abnormality index directly reflects the degree of deviation between the equipment status and the ideal status.

[0033] In this step, by calculating the difference between the equipment operation reconstruction time series matrix and the equipment operation history time series matrix at each time point, the difference between the current state of the equipment and the ideal state can be accurately quantified, which can provide reliable data support for subsequent abnormal judgment; by setting different weights for the deviations of each parameter, the health status of the equipment in different aspects can be more accurately reflected; weighted processing makes the calculation of the abnormal index more scientific and reasonable, and improves the accuracy and reliability of abnormal judgment; through standardization processing, each parameter is placed on the same scale, eliminating the influence of dimension and magnitude on the deviation calculation, so that the contribution of each parameter in the calculation of the abnormal index is more balanced; the abnormal index of the power equipment not only reflects the state difference of the equipment at a single time point, but also integrates the information of multiple time points and multiple parameters by weighted average, so as to comprehensively reflect the overall health status of the equipment; the level of the abnormal index directly reflects the degree of deviation between the equipment state and the ideal state, which is an important basis for judging whether the equipment is abnormal; step S5 obtains an abnormal index that can comprehensively reflect the health status of the power equipment through fine deviation calculation and weighted processing; it not only improves the accuracy and reliability of abnormal judgment, but also provides a strong guarantee for the stable operation of the power system.

[0034] S6. Compare the abnormal index of the power equipment with a preset abnormal threshold value. If the abnormal index of the power equipment exceeds the preset abnormal threshold value, the power equipment is determined to be abnormal. The factors affecting the setting of the preset abnormal threshold include: Historical data analysis: By analyzing a large amount of historical normal operation data, determine the parameter fluctuation range of the equipment in a healthy state; the threshold should be set outside this range to ensure that abnormal conditions can be captured; study historical failure cases and analyze the abnormal index changes of the equipment before the failure occurs, so as to determine a threshold that can provide early warning; Equipment characteristics: Different types of power equipment have different operating characteristics and failure modes, so different abnormal thresholds need to be set for different types of equipment; Environmental factors: External conditions such as ambient temperature, humidity, and electromagnetic interference will affect the operation of power equipment. Therefore, when setting thresholds, it is necessary to consider the impact of these environmental factors on equipment parameters. Seasonal changes will also cause fluctuations in equipment parameters, so thresholds need to be adjusted according to the season. Measurement error: The accuracy and stability of the measuring equipment will affect the accuracy of the data, so the impact of measurement error on the data needs to be considered when setting the threshold; Data quality: This may lead to false positives or false negatives, so data quality needs to be improved through data preprocessing and cleaning, and these factors should be considered when setting thresholds; Safety margin: To ensure the safety and stability of the power system, a certain safety margin is added when setting the threshold; this means that the threshold is set at a lower level than the actual abnormality point in order to provide early warning.

[0035] In this step, the abnormal threshold is set by comprehensively considering historical data analysis, equipment characteristics, environmental factors, measurement errors, data quality, safety margin and other factors, which can more accurately reflect the actual operating status of the equipment; multi-dimensional considerations reduce the possibility of false alarms and missed alarms, and improve the accuracy of abnormality detection; the setting of the preset abnormal threshold not only considers the parameter fluctuation range of the equipment in a healthy state, but also studies the changes in the abnormal index before the failure occurred in history; therefore, when the equipment abnormal index approaches or exceeds the threshold, the system can issue a warning signal in advance, providing enough time for the operation and maintenance personnel to take preventive measures to avoid the occurrence or expansion of the failure; By timely discovering and handling abnormal conditions of power equipment, the continuity and stability of the power system can be ensured; it helps to reduce power outages caused by equipment failures, reduce economic losses, and ensure personal safety; the realization of abnormal detection and early warning functions enables operation and maintenance personnel to manage power equipment more efficiently; accurate abnormal detection data provides strong decision-making support for management; step S6 sets the preset abnormal threshold scientifically and reasonably, and compares it with the abnormal index of power equipment, so as to achieve accurate judgment and early warning of the abnormal state of power equipment; it not only improves the accuracy and timeliness of abnormal detection, but also enhances the safety and stability of the power system.

[0036] Embodiment 2: Figure 3 As shown, a distribution network equipment abnormality monitoring system of the present invention specifically includes the following modules; Data acquisition module, collecting operating data information of the power equipment to be tested in the distribution network; A data preprocessing module performs data format conversion on the operation data information to obtain a device operation history time series matrix; in the device operation history time series matrix, power parameters of the same type are arranged in time series, and power parameters with the same timestamp are located in the same row; The abnormal feature extraction module extracts abnormal features from the equipment operation history time series matrix to obtain the abnormal characterization vector of the power equipment; The data reconstruction module uses a pre-built equipment operation data reconstruction model to reconstruct the abnormal characterization vector of the power equipment and obtain the equipment operation reconstruction timing matrix; the equipment operation data reconstruction model is used to reversely reconstruct the ideal original data corresponding to the abnormal characterization vector of the power equipment, that is, the equipment operation reconstruction timing matrix; The deviation calculation module calculates the deviation between the equipment operation reconstruction timing matrix and the equipment operation history timing matrix to obtain the power equipment abnormality index; The abnormality determination module compares the abnormality index of the power equipment with a preset abnormality threshold, and if the abnormality index of the power equipment exceeds the preset abnormality threshold, the power equipment is determined to be abnormal.

[0037] The system not only focuses on a single operating parameter, but also covers multiple related power parameters based on the equipment operation history time series matrix, which can reflect the equipment's operating status more comprehensively and multi-dimensionally, effectively reducing misjudgments or missed judgments caused by single parameter monitoring; In view of the high dimensionality, nonlinearity and complexity of power equipment operation data, the system effectively processes these data through data preprocessing, abnormal feature extraction and other steps, extracts more representative abnormal features, and improves the system's ability to understand and analyze complex data; The data reconstruction module is introduced to use the pre-built equipment operation data reconstruction model to reversely reconstruct the abnormal features and obtain the ideal equipment operation data; by comparing the deviation between the reconstructed data and the original data, the power equipment abnormality index is calculated, which improves the accuracy and robustness of anomaly detection and reduces the impact of environmental changes, measurement errors and other factors on the detection results; The system makes abnormal judgments by presetting abnormal thresholds to adapt to the monitoring needs of different power equipment or different operating environments. In addition, the equipment operation data reconstruction model can also be continuously optimized based on new data and experience to improve the adaptability and accuracy of the system. The system can collect and analyze equipment operation data in real time. Once an abnormality is found, it can quickly make a judgment and issue an alarm, thereby shortening the fault handling time and reducing power supply interruptions and economic losses caused by equipment failures; In summary, the distribution network equipment abnormality monitoring system effectively improves the accuracy and timeliness of power equipment abnormality detection through multi-dimensional comprehensive monitoring, complex data processing, data reconstruction and deviation analysis, providing a strong guarantee for the stable operation of the power system.

[0038] The various variations and specific embodiments of the distribution network equipment abnormality monitoring method in the aforementioned embodiment 1 are also applicable to the distribution network equipment abnormality monitoring system in this embodiment. Through the aforementioned detailed description of the distribution network equipment abnormality monitoring method, those skilled in the art can clearly know the implementation method of the distribution network equipment abnormality monitoring system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0039] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0040] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A distribution network equipment abnormality monitoring method, characterized in that: The method comprises: Collect operating data information of the power equipment to be tested in the distribution network; Performing data format conversion on the operation data information to obtain a device operation history time sequence matrix; in the device operation history time sequence matrix, power parameters of the same type are arranged in time sequence, and power parameters with the same timestamp are located in the same row; Extract abnormal features from the equipment operation history time series matrix to obtain the abnormal characterization vector of the power equipment; Using the pre-built equipment operation data reconstruction model, the abnormal characterization vector of the power equipment is reconstructed to obtain the equipment operation reconstruction time series matrix; Calculate the deviation between the equipment operation reconstruction time series matrix and the equipment operation history time series matrix to obtain the power equipment abnormality index; The abnormal index of the electric power equipment is compared with a preset abnormal threshold value, and if the abnormal index of the electric power equipment exceeds the preset abnormal threshold value, the electric power equipment is determined to be abnormal.

2. A distribution network equipment abnormality monitoring method as claimed in claim 1, characterized in that: The equipment operation history timing matrix is: ； in, Indicates n At a point in time m The value of the type power parameter.

3. A distribution network equipment abnormality monitoring method as claimed in claim 1, characterized in that: The method for extracting abnormal features from a historical time series matrix of equipment operation includes: Preprocess the equipment operation history time series matrix, including missing value filling, outlier processing and data normalization; Select a feature extraction method and determine the features to be extracted based on the specific type of power equipment and its common failure modes; Calculate the corresponding eigenvalue for each column in the equipment operation history time series matrix; The various calculated eigenvalues ​​are combined into a power equipment abnormality characterization vector.

4. A distribution network equipment abnormality monitoring method as claimed in claim 3, characterized in that: The power equipment abnormality characterization vector is: ； in, Represents the historical timing matrix of slave device operation X Extracted from k Features.

5. A distribution network equipment abnormality monitoring method as claimed in claim 1, characterized in that: The calculation formula of power equipment abnormality index is: ； in, I Indicates the abnormal index of power equipment. Represents the first i The value at each time point; Represents the first i The value at each time point; wi is the weight of the corresponding parameter; N is the number of time points.

6. A distribution network equipment abnormality monitoring method as claimed in claim 1, characterized in that: The factors affecting the setting of the preset abnormal threshold include historical data analysis, equipment characteristics, environmental factors, measurement errors, data quality and safety margin.

7. A distribution network equipment abnormality monitoring method as claimed in claim 1, characterized in that: The method for collecting operation data information of the power equipment to be detected includes: Clarify the monitoring objectives and determine the geographical areas and grid zones to be monitored; Set up data collection points next to power equipment according to equipment type and monitoring requirements; Deploy data collectors at data collection points and use wired and wireless methods to transmit the collected data; Set the frequency and cycle of data collection according to equipment characteristics and monitoring requirements; According to the set data collection frequency and cycle, the operating data information of the power equipment to be tested is collected through the data collector.

8. A distribution network equipment abnormality monitoring system, characterized in that: The system comprises: Data acquisition module, collecting operating data information of the power equipment to be tested in the distribution network; A data preprocessing module performs data format conversion on the operation data information to obtain a device operation history time series matrix; in the device operation history time series matrix, power parameters of the same type are arranged in time series, and power parameters with the same timestamp are located in the same row; The abnormal feature extraction module extracts abnormal features from the equipment operation history time series matrix to obtain the abnormal characterization vector of the power equipment; The data reconstruction module uses a pre-built equipment operation data reconstruction model to reconstruct the abnormal characterization vector of the power equipment and obtain the equipment operation reconstruction timing matrix; the equipment operation data reconstruction model is used to reversely reconstruct the ideal original data corresponding to the abnormal characterization vector of the power equipment, that is, the equipment operation reconstruction timing matrix; The deviation calculation module calculates the deviation between the equipment operation reconstruction timing matrix and the equipment operation history timing matrix to obtain the power equipment abnormality index; The abnormality determination module compares the abnormality index of the power equipment with a preset abnormality threshold, and if the abnormality index of the power equipment exceeds the preset abnormality threshold, the power equipment is determined to be abnormal.

9. An electronic device for monitoring abnormalities of distribution network equipment, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. 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 in the method according to any one of claims 1 to 7 are implemented.

Images