Intelligent monitoring method and system based on power distribution room

Abstract

The invention provides an intelligent monitoring method and system based on a power distribution room. Identification and early warning of abnormal conditions of the power distribution room are realized by adopting a regional and hierarchical monitoring strategy. The method comprises the following steps: firstly, dividing a power distribution room into a plurality of power distribution areas through power distribution room space distribution data, collecting environment data of each area in a preset sampling time window, and generating area anomaly confidence through a pre-trained area anomaly recognition model; and when the region abnormity confidence exceeds a preset threshold value, marking the region as an abnormal region, and determining a power distribution equipment list in the abnormal region. And then, monitoring each power distribution device in the abnormal area, generating a device abnormity confidence coefficient through a device abnormity identification model, and finally identifying the abnormal power distribution device according to a preset confidence coefficient threshold value. The data processing pressure of all-time and all-equipment monitoring is avoided, the monitoring efficiency is improved, and intelligent early warning guarantee is provided for safe operation of the power distribution room.

Description

Technical Field

[0001] The present application relates to the field of power distribution, and in particular to an intelligent monitoring method and system based on a power distribution room. Background Art

[0002] As a key node in the power system, distribution rooms bear the crucial responsibility of distributing and converting electrical energy. As the scale of the power grid expands and electricity demand grows, the safe and stable operation of distribution rooms has a decisive impact on the reliability of the entire power system. Currently, distribution room monitoring primarily relies on manual inspections, traditional online monitoring, and intelligent monitoring systems.

[0003] Manual inspections are the most traditional monitoring method, with professionals regularly checking the operating status of power distribution equipment. This method is intuitive and based on extensive experience, relying on personnel's expertise to identify potential issues. However, manual inspections are inefficient and cannot provide 24 / 7 monitoring. They suffer from long inspection cycles and discontinuous monitoring, making it easy to miss early signs of equipment failure. Furthermore, human factors can lead to observation bias and recording errors that can compromise monitoring quality. Working in dangerous high-voltage environments poses a high safety risk to personnel, and labor costs continue to rise with rising human resource costs, keeping maintenance and management costs high.

[0004] Traditional online monitoring systems continuously monitor distribution rooms using sensors for temperature, humidity, current, and voltage. While this approach offers continuous monitoring compared to manual inspections, it also has significant drawbacks. Traditional systems often suffer from severe data silos, with each subsystem operating independently. This prevents data sharing and comprehensive analysis, leading to fragmented monitoring information. Equipment status assessments rely too heavily on a single parameter, lacking comprehensive, multi-dimensional judgment capabilities and resulting in a high rate of false alarms. Summary of the Invention

[0005] This application provides an intelligent monitoring method based on a power distribution room, comprising the following steps:

[0006] A1, determining the corresponding power distribution room space distribution data in the preset power distribution room;

[0007] A2, based on the spatial distribution data of the power distribution room, generates multiple power distribution area data;

[0008] A3, collecting corresponding distribution area environmental time window data at corresponding locations in the distribution room according to a preset sampling time window and data of each distribution area;

[0009] A4, generates the corresponding regional anomaly confidence level based on the distribution area environmental time window data through the pre-trained regional anomaly recognition model;

[0010] A5: If the regional anomaly confidence is greater than the preset regional anomaly confidence threshold, the corresponding power distribution area data is defined as abnormal power distribution area data, and the corresponding sampling time window is defined as the abnormal sampling time window;

[0011] A6, determining the corresponding abnormal area power distribution equipment list data based on the abnormal power distribution area data and the preset power distribution equipment installation location data;

[0012] A7, collecting the corresponding distribution equipment time window data of each distribution equipment according to the abnormal sampling time window and the distribution equipment list data in the abnormal area;

[0013] A8, generating corresponding equipment abnormality confidence levels based on the time window data of each power distribution device using a preset equipment abnormality identification model;

[0014] A9: If the device abnormality confidence level is greater than a preset device abnormality confidence level threshold, the corresponding power distribution device is defined as an abnormal power distribution device.

[0015] By adopting the above technical solution, the intelligent monitoring method based on the distribution room can adopt a regional and hierarchical monitoring strategy. First, the distribution room is divided into multiple distribution areas through spatial distribution data, and then the pre-trained regional anomaly recognition model is used to quickly locate the abnormal area. Then, the equipment in the abnormal area is accurately monitored, and finally the specific abnormal distribution equipment is identified. While realizing the monitoring of abnormal distribution equipment, the full-time monitoring of all equipment is avoided, the processing volume of monitoring data is reduced and the monitoring efficiency is improved. At the same time, the dual threshold judgment mechanism is used to effectively reduce the false alarm rate, providing intelligent early warning protection for the safe operation of the distribution room.

[0016] Optionally, step A3 includes the following steps:

[0017] A301, continuously collecting corresponding distribution area temperature data, distribution area humidity data, distribution area magnetic field strength data, distribution area noise intensity data, distribution area ozone concentration data, and distribution area nitrogen oxide concentration data at corresponding locations in the distribution room according to the distribution area data;

[0018] A302, according to the sampling time window, obtains corresponding regional temperature time window data, regional humidity time window data, regional magnetic field intensity time window data, regional noise intensity time window data, regional ozone concentration time window data, and regional nitrogen oxide concentration time window data from the distribution area temperature data, distribution area humidity data, distribution area magnetic field intensity data, and distribution area noise intensity data;

[0019] A303 combines regional temperature time window data, regional humidity time window data, regional magnetic field intensity time window data, regional noise intensity time window data, regional ozone concentration time window data, and regional nitrogen oxide concentration time window data to generate distribution area environmental time window data.

[0020] By adopting the above technical solution, the intelligent monitoring method based on the distribution room can simultaneously collect multi-dimensional environmental data such as temperature, humidity, magnetic field intensity, noise intensity, ozone concentration and nitrogen oxide concentration, and organize them into a structured environmental time window data set according to time windows, providing rich feature information for the regional anomaly recognition model. Multi-parameter fusion can improve the recognition sensitivity and accuracy of abnormal states, and can capture complex fault modes that are difficult to reflect by a single parameter. At the same time, the design of the time window realizes the time series analysis of environmental data, which can effectively identify gradual anomalies and provide a data basis for the preventive maintenance of distribution equipment.

[0021] Optionally, step A4 includes the following steps:

[0022] A401, generating corresponding distribution area environmental feature data using a preset environmental feature extraction algorithm based on the distribution area environmental time window data;

[0023] A402, collecting power distribution external environment time window data corresponding to the external environment of the power distribution room according to the sampling time window;

[0024] A403, generating corresponding power distribution external environment feature data using the environment feature extraction algorithm according to the power distribution external environment time window data;

[0025] A404, generating comprehensive characteristic data of the power distribution environment based on the power distribution area environmental characteristic data and the power distribution external environment characteristic data;

[0026] A405 , generating a corresponding regional anomaly confidence level through the regional anomaly identification model according to the comprehensive characteristic data of the power distribution environment.

[0027] By adopting the above technical solution, the intelligent monitoring method based on the distribution room can simultaneously extract the internal environmental characteristics of the distribution area and the external environmental characteristics of the distribution room, and combine them into comprehensive feature data to input into the regional anomaly recognition model, thereby effectively eliminating the interference of external environmental factors on monitoring and analysis, enabling the system to accurately distinguish between environmental changes caused by equipment anomalies and environmental changes caused by natural factors such as external weather, effectively improving the accuracy and reliability of anomaly detection, and at the same time, performing dimensionality reduction and feature enhancement on the original environmental data through the environmental feature extraction algorithm, which not only reduces the computational complexity, but also enhances the model's sensitivity to minor anomalies, providing data support for early fault warning.

[0028] Optionally, step A7 includes the following steps:

[0029] A701 continuously collects the device current data, device voltage data, device power factor data, and device phase angle data corresponding to each power distribution device in the power distribution device list data of the abnormal area;

[0030] A702 obtains corresponding device current time window data, device voltage time window data, device power factor time window data, and device phase angle time window data from the device current data, device voltage data, device power factor data, and device phase angle data according to the abnormal sampling time window;

[0031] A703 generates distribution equipment time window data based on the equipment current time window data, equipment voltage time window data, equipment power factor time window data, and equipment phase angle time window data.

[0032] By adopting the above technical solution, the intelligent monitoring method based on the distribution room can simultaneously collect multi-dimensional electrical data such as current, voltage, power factor and phase angle, and integrate them into structured distribution equipment time window data according to time windows, providing comprehensive electrical status data for equipment abnormality identification. This multi-parameter fusion monitoring strategy can comprehensively reflect the operating status of the equipment and effectively capture various types of electrical anomalies including overload, short circuit, insulation aging and poor contact. It can not only detect sudden faults, but also identify early signs of gradual degradation of equipment performance, providing a data basis for predictive maintenance and life assessment of distribution equipment.

[0033] Optionally, step A8 includes the following steps:

[0034] A801 generates corresponding device current frequency domain data, device voltage frequency domain data, device power factor frequency domain data, and device phase angle frequency domain data using a preset discrete Fourier transform algorithm based on the device current time window data, device voltage time window data, device power factor time window data, and device phase angle time window data in the power distribution device time window data;

[0035] A802 generates power distribution equipment frequency domain data based on the equipment current frequency domain data, the equipment voltage frequency domain data, the equipment power factor frequency domain data, and the equipment phase angle frequency domain data.

[0036] A803, generating corresponding frequency domain feature data of the power distribution equipment using a preset device feature extraction algorithm based on the frequency domain data of the power distribution equipment;

[0037] A804: Generate corresponding equipment anomaly confidence levels based on the frequency domain feature data of the power distribution equipment using the equipment anomaly identification model.

[0038] By adopting the above technical solution, the intelligent monitoring method based on the distribution room can convert the time domain-based distribution equipment time window data into corresponding frequency domain data through the discrete Fourier transform algorithm, and use the equipment feature extraction algorithm to generate frequency domain feature data as the input of the equipment abnormality recognition model, which can capture complex abnormal modes such as harmonic distortion, subsynchronous oscillation and intermittent faults that are difficult to detect through time domain analysis, and can effectively improve the sensitivity and reliability of abnormality detection; at the same time, by analyzing the spectral characteristics of current, voltage, power factor and phase angle, the system can not only accurately determine whether the equipment is abnormal, but also provide important data basis for fault type identification and root cause analysis.

[0039] Optionally, the intelligent monitoring method based on the power distribution room further includes the following steps:

[0040] B1, obtaining historical power distribution area environment data, historical power distribution external environment data, historical power distribution equipment data, and historical abnormal time of each power distribution equipment and corresponding abnormal cause classification information from a preset historical collection database;

[0041] B2, determine the corresponding historical abnormal time window according to the abnormal time of each historical power distribution equipment and the sampling time window;

[0042] B3, obtaining corresponding historical abnormal power distribution area environment time window data from historical power distribution area environment data according to each historical abnormal time window;

[0043] B4, obtaining corresponding historical abnormal power distribution external environment data from historical power distribution external environment data according to each historical abnormal time window;

[0044] B5, according to each historical abnormal time window, respectively obtain the corresponding historical abnormal power distribution equipment time window data from the historical power distribution equipment data, and generate the corresponding historical abnormal power distribution equipment frequency domain data through a discrete Fourier transform algorithm according to the historical abnormal power distribution equipment time window data;

[0045] B6, generating historical abnormal power distribution comprehensive time window data based on the historical abnormal power distribution area environment time window data, historical abnormal power distribution external environment data, and historical abnormal power distribution equipment frequency domain data corresponding to each historical abnormal time window;

[0046] B7, generating corresponding historical abnormal power distribution comprehensive feature data through a preset comprehensive feature extraction algorithm based on each historical abnormal power distribution comprehensive time window data and converting it into a corresponding historical abnormal power distribution comprehensive feature vector;

[0047] B8, combining the same type of historical abnormal power distribution comprehensive feature vectors according to the abnormal cause classification information to generate a corresponding similar vector set of historical abnormal power distribution comprehensive feature vectors;

[0048] B9, calculate the corresponding central vector according to the same vector set of each historical abnormal power distribution comprehensive feature vector and define the typical feature vector of the historical equipment abnormality category;

[0049] B10, generate an equipment abnormality cause feature comparison dataset based on the combination of all historical equipment abnormality category typical feature vectors and corresponding abnormality cause classification information.

[0050] By adopting the above technical solution, the intelligent monitoring method based on the distribution room can obtain historical abnormal data and extract typical feature vectors to construct a feature comparison data set for the cause of equipment abnormality, which can enhance the intelligent diagnosis capability of equipment abnormality. It can not only accurately identify whether the equipment is abnormal, but also estimate the category of the abnormal cause through feature vector comparison. At the same time, through clustering of similar abnormal data and calculation of central vectors, the system can continuously accumulate and optimize the abnormal feature library, which can further improve the efficiency and accuracy of fault handling.

[0051] Optionally, the intelligent monitoring method based on the power distribution room further includes the following steps:

[0052] C1, generates the current abnormal power distribution comprehensive time window data based on the power distribution area environment time window data corresponding to the abnormal power distribution equipment, the power distribution external environment time window data and the power distribution equipment frequency domain data;

[0053] C2, generating corresponding current abnormal power distribution comprehensive feature data through the comprehensive feature extraction algorithm according to the current abnormal power distribution comprehensive time window data and converting it into the corresponding current abnormal power distribution comprehensive feature vector;

[0054] C3, based on the current abnormal power distribution comprehensive feature vector and the equipment abnormality cause feature comparison data set, the corresponding Euclidean distance is calculated and defined as the feature category distance;

[0055] C4, determining the minimum value among all feature category distances and defining the abnormal cause classification information corresponding to the corresponding historical device abnormality category typical feature vector as the first estimated abnormal cause information;

[0056] C5, based on the current abnormal power distribution comprehensive feature vector and the equipment abnormality cause feature comparison data set, the corresponding cosine similarity is calculated and defined as the feature cosine similarity;

[0057] C6, determining the maximum value among all feature cosine similarities and defining the abnormal cause classification information corresponding to the corresponding historical device abnormality category typical feature vector as the second estimated abnormal cause information;

[0058] C7, generating a current device estimated abnormality cause list based on the first estimated abnormality cause information and the second estimated abnormality cause information.

[0059] By adopting the above technical solution, the intelligent monitoring method based on the distribution room can compare the current abnormal distribution comprehensive feature vector with the typical feature vector of the historical equipment abnormal category by simultaneously using two different measurement methods, Euclidean distance and cosine similarity, thereby realizing a dual matching judgment of the cause of the abnormality. The Euclidean distance can evaluate the difference in the overall amplitude of the feature vector, while the cosine similarity can evaluate the similarity of the feature vector in the direction. The combination of the two can comprehensively capture the subtle differences in the abnormal characteristics, effectively reduce the risk of misjudgment that may be caused by a single algorithm, and improve the accuracy and reliability of the intelligent diagnosis of distribution equipment faults.

[0060] This application also provides an intelligent monitoring system based on a power distribution room, including:

[0061] Power distribution environment data acquisition module;

[0062] Power distribution equipment data acquisition module;

[0063] Data processing module;

[0064] Power distribution anomaly identification model;

[0065] Wherein, the power distribution environment data acquisition module, the power distribution equipment data acquisition module and the power distribution anomaly identification model are respectively data-connected to the data processing module;

[0066] Wherein, the power distribution environment data acquisition module includes a plurality of regional environment data acquisition modules and external environment data acquisition modules, and each of the regional environment data acquisition modules and the external environment data acquisition modules is respectively data-connected to the data processing module;

[0067] The power distribution anomaly identification model includes a regional anomaly identification module and a device anomaly identification module, and the regional anomaly identification module and the device anomaly identification module are respectively data-connected to the data processing module;

[0068] The intelligent monitoring system based on the power distribution room further includes a power distribution abnormality monitoring strategy, including the following steps:

[0069] D1, determining the corresponding distribution room space distribution data in the preset distribution room;

[0070] D2, generates multiple distribution area data based on the distribution room spatial distribution data;

[0071] D3, collecting corresponding distribution area environment time window data through the distribution environment data collection module at corresponding positions in the distribution room according to the preset sampling time window and the data of each distribution area;

[0072] D4, generating a corresponding regional anomaly confidence level in the power distribution anomaly identification module according to the power distribution area environment time window data;

[0073] D5: If the regional anomaly confidence is greater than the preset regional anomaly confidence threshold, the corresponding power distribution area data is defined as abnormal power distribution area data, and the corresponding sampling time window is defined as the abnormal sampling time window;

[0074] D6, determining the corresponding abnormal area power distribution equipment list data based on the abnormal power distribution area data and the preset power distribution equipment installation location data;

[0075] D7, collecting the corresponding power distribution equipment time window data of each power distribution equipment through the power distribution equipment data collection module according to the abnormal sampling time window and the power distribution equipment list data in the abnormal area;

[0076] D8, generating corresponding equipment abnormality confidence levels in the power distribution abnormality identification module according to the time window data of each power distribution device;

[0077] D9: If the device abnormality confidence level is greater than a preset device abnormality confidence level threshold, the corresponding power distribution device is defined as an abnormal power distribution device.

[0078] By adopting the above technical solution, the intelligent monitoring system based on the distribution room can adopt a regional and hierarchical monitoring strategy. First, the distribution room is divided into multiple distribution areas through spatial distribution data, and then the pre-trained regional anomaly recognition model is used to quickly locate the abnormal area. Then, the equipment in the abnormal area is accurately monitored, and finally the specific abnormal distribution equipment is identified. While realizing the monitoring of abnormal distribution equipment, the full-time monitoring of all equipment is avoided, the processing volume of monitoring data is reduced and the monitoring efficiency is improved. At the same time, the dual threshold judgment mechanism is used to effectively reduce the false alarm rate, providing intelligent early warning protection for the safe operation of the distribution room.

[0079] In summary, this application includes at least one of the following beneficial technical effects:

[0080] 1. The intelligent monitoring method based on the distribution room can adopt a regional and hierarchical monitoring strategy. First, the distribution room is divided into multiple distribution areas through spatial distribution data, and then the pre-trained regional anomaly recognition model is used to quickly locate the abnormal area. Then, the equipment in the abnormal area is accurately monitored, and finally the specific abnormal distribution equipment is identified. While realizing the monitoring of abnormal distribution equipment, it avoids the full-time monitoring of all equipment, reduces the processing volume of monitoring data and improves the monitoring efficiency. At the same time, the dual threshold judgment mechanism is used to effectively reduce the false alarm rate, providing intelligent early warning protection for the safe operation of the distribution room.

[0081] 2. The intelligent monitoring method based on the distribution room can simultaneously collect multi-dimensional environmental data such as temperature, humidity, magnetic field intensity, noise intensity, ozone concentration and nitrogen oxide concentration, and organize them into a structured environmental time window data set according to time windows, providing rich feature information for the regional anomaly recognition model. Multi-parameter fusion can improve the recognition sensitivity and accuracy of abnormal states, and can capture complex fault modes that are difficult to reflect with a single parameter. At the same time, the design of the time window realizes the time series analysis of environmental data, which can effectively identify gradual anomalies and provide a data basis for the preventive maintenance of distribution equipment.

[0082] 3. The intelligent monitoring method based on the distribution room can simultaneously extract the internal environmental characteristics of the distribution area and the external environmental characteristics of the distribution room, and combine them into comprehensive feature data to input into the regional anomaly recognition model, effectively eliminating the interference of external environmental factors on monitoring and analysis, enabling the system to accurately distinguish between environmental changes caused by equipment anomalies and environmental changes caused by natural factors such as external weather, effectively improving the accuracy and reliability of anomaly detection. At the same time, the original environmental data is processed by dimensionality reduction and feature enhancement through the environmental feature extraction algorithm, which not only reduces the computational complexity, but also enhances the model's sensitivity to minor anomalies, providing data support for early fault warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 It is a process diagram of an intelligent monitoring method based on a power distribution room of the present invention.

[0084] Figure 2 It is a schematic diagram of the principle of an intelligent monitoring system based on a power distribution room of the present invention. DETAILED DESCRIPTION

[0085] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0086] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0087] refer to Figure 1 The present invention provides an intelligent monitoring method based on a power distribution room, which is used to monitor and discover abnormal conditions of equipment in the power distribution room, including the following steps:

[0088] A1, determining the corresponding power distribution room space distribution data in the preset power distribution room;

[0089] The spatial distribution data of the distribution room is the structural data of the indoor space of the distribution room and can be determined through measurement.

[0090] A2, based on the spatial distribution data of the power distribution room, generates multiple power distribution area data;

[0091] The power distribution area data is the block positioning data of the spatial area corresponding to the spatial distribution data of the power distribution room, and is used to represent each area in the power distribution room;

[0092] The data of each distribution area can be segmented and generated manually or automatically through a specific algorithm.

[0093] A3, collecting corresponding distribution area environmental time window data at corresponding locations in the distribution room according to a preset sampling time window and data of each distribution area;

[0094] The sampling time window is a pre-set time window used to determine the sampling time range of the data, which can be set according to needs or experience;

[0095] The distribution area environmental time window data is the regional environmental data collected in the sampling time window at the location area corresponding to the distribution area data, and may include various environmental variable data such as temperature data, humidity data, noise intensity data, and magnetic field intensity data.

[0096] A4, generates the corresponding regional anomaly confidence level based on the distribution area environmental time window data through the pre-trained regional anomaly recognition model;

[0097] The regional anomaly recognition model is a pre-trained recognition model used to identify whether there are any anomalies in the distribution area environment based on the distribution area environment time window data;

[0098] The regional anomaly confidence is the possibility of anomaly in the distribution area generated by the regional anomaly identification model based on the distribution area environment time window data;

[0099] When power distribution equipment malfunctions, it usually affects the surrounding environment, for example, causing the surrounding temperature to rise, generating noticeable noise or abnormal magnetic field changes. Therefore, it is possible to collect environmental data from the corresponding area to identify and estimate whether there are any abnormalities in the area, and then further investigate the power distribution equipment in the abnormal area.

[0100] A5: If the regional anomaly confidence is greater than the preset regional anomaly confidence threshold, the corresponding power distribution area data is defined as abnormal power distribution area data, and the corresponding sampling time window is defined as the abnormal sampling time window;

[0101] The regional anomaly confidence threshold is a pre-set reference value used to determine the degree of regional anomaly confidence;

[0102] The abnormal power distribution area data is the power distribution area data whose regional abnormality confidence is greater than the regional abnormality confidence threshold, that is, the power distribution area data may contain abnormal power distribution equipment in the area corresponding to the power distribution room;

[0103] The abnormal sampling time window is a sampling time window corresponding to the distribution area environment time window data corresponding to the regional abnormality confidence greater than the regional abnormality confidence threshold.

[0104] A6, determining the corresponding abnormal area power distribution equipment list data based on the abnormal power distribution area data and the preset power distribution equipment installation location data;

[0105] The power distribution equipment installation positioning data is the pre-set installation positioning data of each power distribution equipment in the power distribution room;

[0106] The abnormal area power distribution equipment list data is an information list of all power distribution equipment whose location data is located in the abnormal power distribution area data.

[0107] A7, collecting the corresponding distribution equipment time window data of each distribution equipment according to the abnormal sampling time window and the distribution equipment list data in the abnormal area;

[0108] The distribution equipment time window data is the equipment parameter data of each distribution equipment in the abnormal area distribution equipment list data in the abnormal sampling time window, for example, the current data, voltage data, power factor data, phase angle data, apparent power data, active power data and reactive power data of the distribution equipment and other equipment electrical parameter data.

[0109] A8, generating corresponding equipment abnormality confidence levels based on the time window data of each power distribution device using a preset equipment abnormality identification model;

[0110] The equipment anomaly recognition model is a pre-trained recognition model used to identify whether there are any operating anomalies in the power distribution equipment;

[0111] The equipment anomaly confidence level is the probability of an abnormality in the power distribution equipment generated by the equipment anomaly recognition model based on the time window data of the power distribution equipment.

[0112] A9: If the device abnormality confidence level is greater than a preset device abnormality confidence level threshold, the corresponding power distribution device is defined as an abnormal power distribution device;

[0113] The device abnormality confidence threshold is a pre-set reference value used to determine the degree of confidence in the device abnormality;

[0114] The abnormal power distribution equipment is a power distribution equipment whose corresponding equipment abnormality confidence is greater than the equipment abnormality confidence threshold.

[0115] Through the above steps, the intelligent monitoring method based on the distribution room can adopt a regional and hierarchical monitoring strategy. First, the distribution room is divided into multiple distribution areas through spatial distribution data, and then the pre-trained regional anomaly recognition model is used to quickly locate the abnormal area. Then, the equipment in the abnormal area is accurately monitored, and finally the specific abnormal distribution equipment is identified. While realizing the monitoring of abnormal distribution equipment, the full-time monitoring of all equipment is avoided, the processing volume of monitoring data is reduced and the monitoring efficiency is improved. At the same time, the dual threshold judgment mechanism is used to effectively reduce the false alarm rate, providing intelligent early warning protection for the safe operation of the distribution room.

[0116] Furthermore, the step A3 includes the following steps:

[0117] A301, continuously collecting corresponding distribution area temperature data, distribution area humidity data, distribution area magnetic field strength data, distribution area noise intensity data, distribution area ozone concentration data, and distribution area nitrogen oxide concentration data at corresponding locations in the distribution room according to the distribution area data;

[0118] The distribution area temperature data is the temperature data continuously collected at the corresponding position of the distribution area data;

[0119] The humidity data of the power distribution area is continuously collected at the corresponding position of the power distribution area data;

[0120] The magnetic field strength data of the power distribution area is continuously collected at the corresponding position of the power distribution area data;

[0121] When the power distribution equipment experiences abnormal load operation, it may cause abnormal changes in the surrounding temperature, humidity, and magnetic field;

[0122] The noise intensity data of the power distribution area is continuously collected at the corresponding position of the power distribution area data;

[0123] When the power distribution equipment has structural abnormalities, it may cause abnormal noise to the surrounding area;

[0124] The ozone concentration data in the distribution area is continuously collected at the corresponding position of the distribution area data;

[0125] The nitrogen oxide concentration data of the distribution area is continuously collected at the corresponding position of the distribution area data;

[0126] When abnormal discharge occurs in power distribution equipment, it may cause an abnormal increase in the concentration of ozone or nitrogen oxides around it.

[0127] A302, according to the sampling time window, obtains corresponding regional temperature time window data, regional humidity time window data, regional magnetic field intensity time window data, regional noise intensity time window data, regional ozone concentration time window data, and regional nitrogen oxide concentration time window data from the distribution area temperature data, distribution area humidity data, distribution area magnetic field intensity data, and distribution area noise intensity data;

[0128] The regional temperature time window data is the temperature data of the distribution area within the sampling time window;

[0129] Regional humidity time window data refers to the humidity data of the distribution area within the sampling time window;

[0130] The regional magnetic field strength time window data is the magnetic field strength data of the distribution area within the sampling time window;

[0131] The regional noise intensity time window data is the noise intensity data of the distribution area within the sampling time window;

[0132] The regional ozone concentration time window data is the ozone concentration data of the distribution area noise intensity data within the sampling time window;

[0133] The regional nitrogen oxide concentration time window data is the nitrogen oxide concentration data of the distribution area noise intensity data within the sampling time window.

[0134] A303 combines regional temperature time window data, regional humidity time window data, regional magnetic field intensity time window data, regional noise intensity time window data, regional ozone concentration time window data, and regional nitrogen oxide concentration time window data to generate distribution area environmental time window data;

[0135] The distribution area environmental time window data is a collection of regional temperature time window data, regional humidity time window data, regional magnetic field intensity time window data, regional noise intensity time window data, regional ozone concentration time window data, and regional nitrogen oxide concentration time window data.

[0136] Through the above steps, the intelligent monitoring method based on the distribution room can simultaneously collect multi-dimensional environmental data such as temperature, humidity, magnetic field intensity, noise intensity, ozone concentration and nitrogen oxide concentration, and organize them into a structured environmental time window data set according to time windows, providing rich feature information for the regional anomaly recognition model. Multi-parameter fusion can improve the recognition sensitivity and accuracy of abnormal states, and can capture complex fault modes that are difficult to reflect with a single parameter. At the same time, the time series analysis of environmental data is realized through the design of the time window, which can effectively identify gradual anomalies and provide a data basis for the preventive maintenance of distribution equipment.

[0137] Furthermore, the step A4 includes the following steps:

[0138] A401, generating corresponding distribution area environmental feature data using a preset environmental feature extraction algorithm based on the distribution area environmental time window data;

[0139] The environmental feature extraction algorithm is a pre-set algorithm used to extract feature data from the distribution area environmental time window data;

[0140] The distribution area environment characteristic data is characteristic data corresponding to the distribution area environment time window data.

[0141] A402, collecting power distribution external environment time window data corresponding to the external environment of the power distribution room according to the sampling time window;

[0142] The power distribution external environment time window data is the environmental data of the external environment of the distribution room, such as temperature data, humidity data, wind speed data and other environmental data outside the distribution room. Since the environmental data outside the distribution room may indirectly affect the environmental data inside the distribution room, it is necessary to collect corresponding data for coordinated processing and analysis.

[0143] A403, generating corresponding power distribution external environment feature data using the environment feature extraction algorithm according to the power distribution external environment time window data;

[0144] The power distribution external environment characteristic data is characteristic data corresponding to the power distribution external environment time window data.

[0145] A404, generating comprehensive characteristic data of the power distribution environment based on the power distribution area environmental characteristic data and the power distribution external environment characteristic data;

[0146] The comprehensive characteristic data of the power distribution environment is a collection of the power distribution area environmental characteristic data and the power distribution external environment characteristic data.

[0147] A405, generating a corresponding regional anomaly confidence level using the regional anomaly recognition model based on the comprehensive characteristic data of the power distribution environment;

[0148] The comprehensive characteristic data of the power distribution environment is input into the regional anomaly identification model to obtain the output regional anomaly confidence. Combining the power distribution area environment characteristic data and the power distribution external environment characteristic data can make the regional anomaly confidence output by the regional anomaly identification model have better accuracy.

[0149] Through the above steps, the intelligent monitoring method based on the distribution room can simultaneously extract the internal environmental characteristics of the distribution area and the external environmental characteristics of the distribution room, and combine them into comprehensive feature data to input into the regional anomaly recognition model, thereby effectively eliminating the interference of external environmental factors on monitoring and analysis, enabling the system to accurately distinguish between environmental changes caused by equipment anomalies and environmental changes caused by natural factors such as external weather, effectively improving the accuracy and reliability of anomaly detection, and at the same time, performing dimensionality reduction and feature enhancement on the original environmental data through the environmental feature extraction algorithm, which not only reduces the computational complexity, but also enhances the model's sensitivity to minor anomalies, providing data support for early fault warning.

[0150] Furthermore, the step A7 includes the following steps:

[0151] A701 continuously collects the device current data, device voltage data, device power factor data, and device phase angle data corresponding to each power distribution device in the power distribution device list data of the abnormal area;

[0152] Equipment current data refers to the current data of the power distribution equipment;

[0153] Equipment voltage data refers to the voltage data of the power distribution equipment;

[0154] The equipment power factor data is the power factor data of the power distribution equipment;

[0155] The equipment phase angle data is the phase angle data of the power distribution equipment.

[0156] A702 obtains corresponding device current time window data, device voltage time window data, device power factor time window data, and device phase angle time window data from the device current data, device voltage data, device power factor data, and device phase angle data according to the abnormal sampling time window;

[0157] The device current time window data is the corresponding data of the abnormal sampling time window in the device current data;

[0158] The equipment voltage time window data is the corresponding data of the abnormal sampling time window in the equipment voltage data;

[0159] The equipment power factor time window data is the corresponding data of the abnormal sampling time window in the equipment power factor data;

[0160] The device phase angle time window data is the corresponding data of the abnormal sampling time window in the device phase angle time window data.

[0161] A703 generates distribution equipment time window data based on the equipment current time window data, equipment voltage time window data, equipment power factor time window data, and equipment phase angle time window data.

[0162] The distribution equipment time window data is a collection of equipment current time window data, equipment voltage time window data, equipment power factor time window data, and equipment phase angle time window data.

[0163] Through the above steps, the intelligent monitoring method based on the distribution room can simultaneously collect multi-dimensional electrical data such as current, voltage, power factor and phase angle, and integrate them into structured distribution equipment time window data according to time windows, providing comprehensive electrical status data for equipment abnormality identification. This multi-parameter fusion monitoring strategy can comprehensively reflect the operating status of the equipment and effectively capture various types of electrical anomalies including overload, short circuit, insulation aging and poor contact. It can not only detect sudden faults, but also identify early signs of gradual degradation of equipment performance, providing a data basis for predictive maintenance and life assessment of distribution equipment.

[0164] Furthermore, the step A8 includes the following steps:

[0165] A801 generates corresponding device current frequency domain data, device voltage frequency domain data, device power factor frequency domain data, and device phase angle frequency domain data using a preset discrete Fourier transform algorithm based on the device current time window data, device voltage time window data, device power factor time window data, and device phase angle time window data in the power distribution device time window data;

[0166] The discrete Fourier transform algorithm is a pre-set algorithm used to convert time domain data into frequency domain data;

[0167] The device current frequency domain data is the frequency domain data corresponding to the device current time window data;

[0168] The device voltage frequency domain data is the frequency domain data corresponding to the device voltage time window data;

[0169] The device power factor frequency domain data is the frequency domain data corresponding to the device power factor time window data;

[0170] The device phase angle frequency domain data is the frequency domain data corresponding to the device phase angle time window data.

[0171] A802 generates power distribution equipment frequency domain data based on the equipment current frequency domain data, the equipment voltage frequency domain data, the equipment power factor frequency domain data, and the equipment phase angle frequency domain data.

[0172] The frequency domain data of power distribution equipment is a collection of equipment current frequency domain data, equipment voltage frequency domain data, equipment power factor frequency domain data, and equipment phase angle frequency domain data.

[0173] A803, generating corresponding frequency domain feature data of the power distribution equipment using a preset device feature extraction algorithm based on the frequency domain data of the power distribution equipment;

[0174] The device feature extraction algorithm is a pre-set algorithm used to extract feature data from the frequency domain data of the power distribution equipment;

[0175] The frequency domain characteristic data of the power distribution equipment is characteristic data corresponding to the frequency domain data of the power distribution equipment.

[0176] A804, generating a corresponding equipment abnormality confidence level based on the frequency domain characteristic data of the power distribution equipment through the equipment abnormality identification model;

[0177] The frequency domain characteristic data of the power distribution equipment is input into the equipment abnormality identification model to generate an equipment abnormality confidence level of the output power distribution equipment.

[0178] Through the above steps, the intelligent monitoring method based on the distribution room can convert the time domain-based distribution equipment time window data into corresponding frequency domain data through the discrete Fourier transform algorithm, and use the equipment feature extraction algorithm to generate frequency domain feature data as the input of the equipment abnormality recognition model, which can capture complex abnormal modes such as harmonic distortion, subsynchronous oscillation and intermittent faults that are difficult to detect through time domain analysis, and can effectively improve the sensitivity and reliability of abnormality detection; at the same time, by analyzing the spectral characteristics of current, voltage, power factor and phase angle, the system can not only accurately determine whether the equipment is abnormal, but also provide important data basis for fault type identification and root cause analysis.

[0179] Furthermore, the intelligent monitoring method based on the power distribution room further includes the following steps:

[0180] B1, obtaining historical power distribution area environment data, historical power distribution external environment data, historical power distribution equipment data, and historical abnormal time of each power distribution equipment and corresponding abnormal cause classification information from a preset historical collection database;

[0181] The historical collection database is a database of pre-set distribution room related data, which stores various data collected in the past on the distribution room, including historical distribution environment data, historical external environment data, various electrical data of each distribution equipment, historical abnormal conditions of distribution equipment, etc.

[0182] The historical distribution area environment data is the historical data of the distribution area environment that has been continuously collected in the past;

[0183] The historical power distribution external environment data is the historical data of the power distribution external environment that has been continuously collected in the past;

[0184] The historical power distribution equipment data is the historical electrical status data of the power distribution equipment collected in the past;

[0185] The historical abnormal time of the power distribution equipment is the time when the power distribution equipment has an abnormal working state in the past, which is determined manually or by an algorithm;

[0186] The abnormality cause classification information is the classification of abnormality causes corresponding to abnormal working states of power distribution equipment determined in the past.

[0187] B2, determine the corresponding historical abnormal time window according to the abnormal time of each historical power distribution equipment and the sampling time window;

[0188] The historical abnormal time window is the corresponding time window determined by the abnormal time of each historical distribution equipment combined with the sampling time window. For example, the abnormal time of a historical distribution equipment is 17:23 on March 5, and the sampling time window is set to ±5 minutes. The corresponding historical abnormal time window is from 17:18 on March 5 to 17:28 on March 5.

[0189] B3, obtaining corresponding historical abnormal power distribution area environment time window data from historical power distribution area environment data according to each historical abnormal time window;

[0190] The historical abnormal power distribution area environment time window data is the data of the time period corresponding to the historical abnormal time window in the historical power distribution area environment data.

[0191] B4, obtaining corresponding historical abnormal power distribution external environment data from historical power distribution external environment data according to each historical abnormal time window;

[0192] The historical abnormal power distribution external environment data is the data of the time period corresponding to the historical abnormal time window in the historical power distribution external environment data.

[0193] B5, according to each historical abnormal time window, respectively obtain the corresponding historical abnormal power distribution equipment time window data from the historical power distribution equipment data, and generate the corresponding historical abnormal power distribution equipment frequency domain data through a discrete Fourier transform algorithm according to the historical abnormal power distribution equipment time window data;

[0194] The historical abnormal distribution equipment time window data is the electrical data of various aspects of power distribution during the period corresponding to the historical abnormal time window in the historical distribution equipment data, including current data, voltage data, power factor data, and phase angle data;

[0195] The historical abnormal power distribution equipment frequency domain data is the frequency domain data corresponding to the historical abnormal power distribution equipment time window data.

[0196] B6, generating historical abnormal power distribution comprehensive time window data based on the historical abnormal power distribution area environment time window data, historical abnormal power distribution external environment data, and historical abnormal power distribution equipment frequency domain data corresponding to each historical abnormal time window;

[0197] The comprehensive time window data of historical abnormal power distribution is a collection of historical abnormal power distribution area environment time window data, historical abnormal power distribution external environment data and historical abnormal power distribution equipment frequency domain data.

[0198] B7, generating corresponding historical abnormal power distribution comprehensive feature data through a preset comprehensive feature extraction algorithm based on each historical abnormal power distribution comprehensive time window data and converting it into a corresponding historical abnormal power distribution comprehensive feature vector;

[0199] The comprehensive feature extraction algorithm is a pre-set feature extraction algorithm used to extract feature data from the abnormal power distribution comprehensive time window data that combines multiple data;

[0200] The historical abnormal power distribution comprehensive characteristic data is the characteristic data corresponding to the historical abnormal power distribution comprehensive time window data;

[0201] The comprehensive feature vector of historical abnormal power distribution is a feature vector corresponding to the comprehensive feature data of historical abnormal power distribution.

[0202] B8, combining the same type of historical abnormal power distribution comprehensive feature vectors according to the abnormal cause classification information to generate a corresponding similar vector set of historical abnormal power distribution comprehensive feature vectors;

[0203] The same type vector set of historical abnormal power distribution comprehensive feature vectors is a vector set of historical abnormal power distribution comprehensive feature vectors with the same abnormal cause classification information, that is, the historical abnormal power distribution comprehensive feature vectors corresponding to the historical abnormal time windows with the same abnormal cause classification information are classified into one set.

[0204] B9, calculate the corresponding central vector according to the same vector set of each historical abnormal power distribution comprehensive feature vector and define the typical feature vector of the historical equipment abnormality category;

[0205] The typical feature vector of the historical equipment anomaly category is the center vector of each feature vector in the same category of the historical abnormal power distribution comprehensive feature vector.

[0206] B10, generate a device abnormality cause feature comparison dataset based on the combination of all historical device abnormality category typical feature vectors and corresponding abnormality cause classification information;

[0207] The equipment abnormality cause feature comparison dataset is a paired dataset of typical feature vectors of each historical equipment abnormality category and the corresponding abnormality cause classification information.

[0208] Through the above steps, the intelligent monitoring method based on the distribution room can construct a feature comparison data set of equipment abnormality causes by acquiring historical abnormality data and extracting typical feature vectors, which can enhance the intelligent diagnosis capability of equipment abnormalities. It can not only accurately identify whether the equipment is abnormal, but also estimate the category of abnormality causes through feature vector comparison. At the same time, through clustering of similar abnormal data and calculation of central vectors, the system can continuously accumulate and optimize the abnormality feature library, which can further improve the efficiency and accuracy of fault handling.

[0209] Furthermore, the intelligent monitoring method based on the power distribution room further includes the following steps:

[0210] C1, generates the current abnormal power distribution comprehensive time window data based on the power distribution area environment time window data corresponding to the abnormal power distribution equipment, the power distribution external environment time window data and the power distribution equipment frequency domain data;

[0211] The current abnormal power distribution comprehensive time window data is a collection of the power distribution area environment time window data corresponding to the abnormal power distribution equipment, the power distribution external environment time window data and the power distribution equipment frequency domain data.

[0212] C2, generating corresponding current abnormal power distribution comprehensive feature data through the comprehensive feature extraction algorithm according to the current abnormal power distribution comprehensive time window data and converting it into the corresponding current abnormal power distribution comprehensive feature vector;

[0213] The current abnormal power distribution comprehensive characteristic data is the characteristic data corresponding to the current abnormal power distribution comprehensive time window data;

[0214] The current abnormal power distribution comprehensive feature vector is a feature vector corresponding to the current abnormal power distribution comprehensive feature data.

[0215] C3, based on the current abnormal power distribution comprehensive feature vector and the equipment abnormality cause feature comparison data set, the corresponding Euclidean distance is calculated and defined as the feature category distance;

[0216] The feature category distance is the Euclidean distance between the current abnormal power distribution comprehensive feature vector and the typical feature vector of each historical equipment abnormal category. The smaller the feature category distance, the higher the similarity between the vectors.

[0217] C4, determining the minimum value among all feature category distances and defining the abnormal cause classification information corresponding to the corresponding historical device abnormality category typical feature vector as the first estimated abnormal cause information;

[0218] The first estimated abnormality cause information is the abnormality cause information that may exist in the power distribution equipment determined by matching the minimum value among all feature category distances.

[0219] C5, based on the current abnormal power distribution comprehensive feature vector and the equipment abnormality cause feature comparison data set, the corresponding cosine similarity is calculated and defined as the feature cosine similarity;

[0220] Feature cosine similarity is the cosine similarity between the current abnormal power distribution comprehensive feature vector and the typical feature vectors of each historical equipment abnormality category. The larger the cosine similarity, the higher the similarity between the vectors.

[0221] C6, determining the maximum value among all feature cosine similarities and defining the abnormal cause classification information corresponding to the corresponding historical device abnormality category typical feature vector as the second estimated abnormal cause information;

[0222] The second estimated abnormality cause information is abnormality cause information that may exist in the power distribution equipment determined by matching the maximum value of all feature cosine similarities.

[0223] C7, generating a list of estimated abnormal causes for the current device based on the first estimated abnormal cause information and the second estimated abnormal cause information;

[0224] The current equipment estimated abnormality cause list is a collection of the first estimated abnormality cause information and the second estimated abnormality cause information.

[0225] Through the above steps, the intelligent monitoring method based on the distribution room can compare the current abnormal distribution comprehensive feature vector with the typical feature vector of the historical equipment abnormal category by simultaneously using two different measurement methods, Euclidean distance and cosine similarity, to achieve dual matching judgment of the cause of the abnormality. The Euclidean distance can evaluate the difference in the overall amplitude of the feature vector, while the cosine similarity can evaluate the similarity of the feature vector in the direction. The combination of the two can fully capture the subtle differences in the abnormal characteristics, effectively reduce the risk of misjudgment that may be caused by a single algorithm, and improve the accuracy and reliability of the intelligent diagnosis of distribution equipment faults.

[0226] refer to Figure 2 The present invention also provides an intelligent monitoring system based on a power distribution room, comprising:

[0227] Power distribution environment data acquisition module 10;

[0228] Power distribution equipment data acquisition module 20;

[0229] Data processing module 30;

[0230] Power distribution abnormality identification module 40;

[0231] The power distribution environment data acquisition module 10, the power distribution equipment data acquisition module 20 and the power distribution anomaly identification module 40 are respectively data-connected to the data processing module 30;

[0232] The power distribution environment data acquisition module 10 includes a plurality of regional environment data acquisition modules 11 and an external environment data acquisition module 12, and each of the regional environment data acquisition module 11 and the external environment data acquisition module 12 is respectively data-connected to the data processing module 30;

[0233] The power distribution anomaly identification module 40 includes a regional anomaly identification module 41 and a device anomaly identification module 42, and the regional anomaly identification module 41 and the device anomaly identification module 42 are respectively data-connected to the data processing module 30;

[0234] The power distribution environment data acquisition module 10 is mainly used to collect environmental data inside and outside the power distribution room;

[0235] The regional environmental data acquisition module 11 is mainly used to collect environmental data of each area in the power distribution room;

[0236] The external environment data acquisition module 12 is mainly used to collect environmental data outside the power distribution room.

[0237] The power distribution equipment data acquisition module 20 is mainly used to collect the electrical status data of each power distribution equipment itself.

[0238] The data processing module 30 is mainly used for data collection and analysis.

[0239] The power distribution anomaly identification module 40 is mainly used to identify anomalies based on the data processed by the data processing module 30 .

[0240] The regional anomaly identification module 41 is mainly used to identify and determine whether there is an anomaly in the corresponding area based on the environmental data collected by the power distribution environment data collection module 10.

[0241] The device abnormality identification module 42 is mainly used to determine whether there is an abnormality in the power distribution equipment based on the electrical data collected by the power distribution equipment data collection module 20.

[0242] The intelligent monitoring system based on the power distribution room further includes a power distribution abnormality monitoring strategy, including the following steps:

[0243] D1, determining the corresponding distribution room space distribution data in the preset distribution room;

[0244] D2, generates multiple distribution area data based on the distribution room spatial distribution data;

[0245] D3, collecting corresponding distribution area environment time window data through the distribution environment data collection module 10 at corresponding positions in the distribution room according to the preset sampling time window and the data of each distribution area;

[0246] D4, generating a corresponding regional anomaly confidence level in the power distribution anomaly identification module through the regional anomaly identification module 41 according to the power distribution area environment time window data;

[0247] D5: If the regional anomaly confidence is greater than the preset regional anomaly confidence threshold, the corresponding power distribution area data is defined as abnormal power distribution area data, and the corresponding sampling time window is defined as the abnormal sampling time window;

[0248] D6, determining the corresponding abnormal area power distribution equipment list data based on the abnormal power distribution area data and the preset power distribution equipment installation location data;

[0249] D7, collecting the corresponding power distribution equipment time window data of each power distribution equipment through the power distribution equipment data collection module 20 according to the abnormal sampling time window and the power distribution equipment list data in the abnormal area;

[0250] D8, generating corresponding equipment abnormality confidence levels in the power distribution abnormality identification module through the equipment abnormality identification module 42 according to the time window data of each power distribution device;

[0251] D9: If the device abnormality confidence level is greater than a preset device abnormality confidence level threshold, the corresponding power distribution device is defined as an abnormal power distribution device.

[0252] Through the above technical solution, the intelligent monitoring system based on the distribution room can adopt a regional and hierarchical monitoring strategy. First, the distribution room is divided into multiple distribution areas through spatial distribution data, and then the pre-trained regional anomaly recognition model is used to quickly locate the abnormal area. Then, the equipment in the abnormal area is accurately monitored, and finally the specific abnormal distribution equipment is identified. While realizing the monitoring of abnormal distribution equipment, it avoids the full-time monitoring of all equipment, reduces the processing volume of monitoring data and improves the monitoring efficiency. At the same time, the dual threshold judgment mechanism is used to effectively reduce the false alarm rate, providing intelligent early warning protection for the safe operation of the distribution room.

[0253] The above are all preferred embodiments of the present application and are not intended to limit the scope of protection of this application. Unless otherwise stated, any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features. In other words, unless otherwise stated, each feature is merely an example of a series of equivalent or similar features.

Claims

1. An intelligent monitoring method based on a power distribution room, characterized in that: The following steps are involved: A1, determining the corresponding power distribution room space distribution data in the preset power distribution room; A2, based on the spatial distribution data of the power distribution room, generates multiple power distribution area data; A3, collecting corresponding distribution area environmental time window data at corresponding locations in the distribution room according to a preset sampling time window and data of each distribution area; A4, generates the corresponding regional anomaly confidence level based on the distribution area environmental time window data through the pre-trained regional anomaly recognition model; A5: If the regional anomaly confidence is greater than the preset regional anomaly confidence threshold, the corresponding power distribution area data is defined as abnormal power distribution area data, and the corresponding sampling time window is defined as the abnormal sampling time window; A6, determining the corresponding abnormal area power distribution equipment list data based on the abnormal power distribution area data and the preset power distribution equipment installation location data; A7, collecting the corresponding distribution equipment time window data of each distribution equipment according to the abnormal sampling time window and the distribution equipment list data in the abnormal area; A8, generating corresponding equipment abnormality confidence levels based on the time window data of each power distribution device using a preset equipment abnormality identification model; A9: If the device abnormality confidence level is greater than a preset device abnormality confidence level threshold, the corresponding power distribution device is defined as an abnormal power distribution device.

2. The intelligent monitoring method based on the power distribution room according to claim 1 is characterized in that: Step A3 includes the following steps: A301, continuously collecting corresponding distribution area temperature data, distribution area humidity data, distribution area magnetic field strength data, distribution area noise intensity data, distribution area ozone concentration data, and distribution area nitrogen oxide concentration data at corresponding locations in the distribution room according to the distribution area data; A302, according to the sampling time window, obtains corresponding regional temperature time window data, regional humidity time window data, regional magnetic field intensity time window data, regional noise intensity time window data, regional ozone concentration time window data, and regional nitrogen oxide concentration time window data from the distribution area temperature data, distribution area humidity data, distribution area magnetic field intensity data, and distribution area noise intensity data; A303 combines regional temperature time window data, regional humidity time window data, regional magnetic field intensity time window data, regional noise intensity time window data, regional ozone concentration time window data, and regional nitrogen oxide concentration time window data to generate distribution area environmental time window data.

3. The intelligent monitoring method based on the power distribution room according to claim 2 is characterized in that: Step A4 includes the following steps: A401, generating corresponding distribution area environmental feature data using a preset environmental feature extraction algorithm based on the distribution area environmental time window data; A402, collecting power distribution external environment time window data corresponding to the external environment of the power distribution room according to the sampling time window; A403, generating corresponding power distribution external environment feature data using the environment feature extraction algorithm according to the power distribution external environment time window data; A404, generating comprehensive characteristic data of the power distribution environment based on the power distribution area environmental characteristic data and the power distribution external environment characteristic data; A405 , generating a corresponding regional anomaly confidence level through the regional anomaly identification model according to the comprehensive characteristic data of the power distribution environment.

4. The intelligent monitoring method based on the power distribution room according to claim 3 is characterized in that: Step A7 includes the following steps: A701 continuously collects the device current data, device voltage data, device power factor data, and device phase angle data corresponding to each power distribution device in the power distribution device list data of the abnormal area; A702 obtains corresponding device current time window data, device voltage time window data, device power factor time window data, and device phase angle time window data from the device current data, device voltage data, device power factor data, and device phase angle data according to the abnormal sampling time window; A703 generates distribution equipment time window data based on the equipment current time window data, equipment voltage time window data, equipment power factor time window data, and equipment phase angle time window data.

5. The intelligent monitoring method based on power distribution room according to claim 4 is characterized in that: Step A8 includes the following steps: A801 generates corresponding device current frequency domain data, device voltage frequency domain data, device power factor frequency domain data, and device phase angle frequency domain data using a preset discrete Fourier transform algorithm based on the device current time window data, device voltage time window data, device power factor time window data, and device phase angle time window data in the power distribution device time window data; A802 generates power distribution equipment frequency domain data based on the equipment current frequency domain data, the equipment voltage frequency domain data, the equipment power factor frequency domain data, and the equipment phase angle frequency domain data. A803, generating corresponding frequency domain feature data of the power distribution equipment using a preset device feature extraction algorithm based on the frequency domain data of the power distribution equipment; A804: Generate corresponding equipment anomaly confidence levels based on the frequency domain feature data of the power distribution equipment using the equipment anomaly identification model.

6. The intelligent monitoring method based on power distribution room according to claim 5 is characterized in that: Further comprising the steps of: B1, obtaining historical power distribution area environment data, historical power distribution external environment data, historical power distribution equipment data, and historical abnormal time of each power distribution equipment and corresponding abnormal cause classification information from a preset historical collection database; B2, determine the corresponding historical abnormal time window according to the abnormal time of each historical power distribution equipment and the sampling time window; B3, obtaining corresponding historical abnormal power distribution area environment time window data from historical power distribution area environment data according to each historical abnormal time window; B4, obtaining corresponding historical abnormal power distribution external environment data from historical power distribution external environment data according to each historical abnormal time window; B5, according to each historical abnormal time window, respectively obtain the corresponding historical abnormal power distribution equipment time window data from the historical power distribution equipment data, and generate the corresponding historical abnormal power distribution equipment frequency domain data through a discrete Fourier transform algorithm according to the historical abnormal power distribution equipment time window data; B6, generating historical abnormal power distribution comprehensive time window data based on the historical abnormal power distribution area environment time window data, historical abnormal power distribution external environment data, and historical abnormal power distribution equipment frequency domain data corresponding to each historical abnormal time window; B7, generating corresponding historical abnormal power distribution comprehensive feature data through a preset comprehensive feature extraction algorithm based on each historical abnormal power distribution comprehensive time window data and converting it into a corresponding historical abnormal power distribution comprehensive feature vector; B8, combining the same type of historical abnormal power distribution comprehensive feature vectors according to the abnormal cause classification information to generate a corresponding similar vector set of historical abnormal power distribution comprehensive feature vectors; B9, calculate the corresponding central vector according to the same vector set of each historical abnormal power distribution comprehensive feature vector and define the typical feature vector of the historical equipment abnormality category; B10, generate an equipment abnormality cause feature comparison dataset based on the combination of all historical equipment abnormality category typical feature vectors and corresponding abnormality cause classification information.

7. The intelligent monitoring method based on power distribution room according to claim 6, characterized in that: Further comprising the steps of: C1, generates the current abnormal power distribution comprehensive time window data based on the power distribution area environment time window data corresponding to the abnormal power distribution equipment, the power distribution external environment time window data and the power distribution equipment frequency domain data; C2, generating corresponding current abnormal power distribution comprehensive feature data through the comprehensive feature extraction algorithm according to the current abnormal power distribution comprehensive time window data and converting it into the corresponding current abnormal power distribution comprehensive feature vector; C3, based on the current abnormal power distribution comprehensive feature vector and the equipment abnormality cause feature comparison data set, the corresponding Euclidean distance is calculated and defined as the feature category distance; C4, determining the minimum value among all feature category distances and defining the abnormal cause classification information corresponding to the corresponding historical device abnormality category typical feature vector as the first estimated abnormal cause information; C5, based on the current abnormal power distribution comprehensive feature vector and the equipment abnormality cause feature comparison data set, the corresponding cosine similarity is calculated and defined as the feature cosine similarity; C6, determining the maximum value among all feature cosine similarities and defining the abnormal cause classification information corresponding to the corresponding historical device abnormality category typical feature vector as the second estimated abnormal cause information; C7, generating a current device estimated abnormality cause list based on the first estimated abnormality cause information and the second estimated abnormality cause information.

8. An intelligent monitoring system based on a power distribution room, characterized in that: include: Power distribution environment data acquisition module; Power distribution equipment data acquisition module; Data processing module; Power distribution anomaly identification model; Wherein, the power distribution environment data acquisition module, the power distribution equipment data acquisition module and the power distribution anomaly identification model are respectively data-connected to the data processing module; Wherein, the power distribution environment data acquisition module includes a plurality of regional environment data acquisition modules and external environment data acquisition modules, and each of the regional environment data acquisition modules and the external environment data acquisition modules is respectively data-connected to the data processing module; The power distribution anomaly identification model includes a regional anomaly identification module and a device anomaly identification module, and the regional anomaly identification module and the device anomaly identification module are respectively data-connected to the data processing module; The intelligent monitoring system based on the power distribution room further includes a power distribution abnormality monitoring strategy, including the following steps: D1, determining the corresponding distribution room space distribution data in the preset distribution room; D2, generates multiple distribution area data based on the distribution room spatial distribution data; D3, collecting corresponding distribution area environment time window data through the distribution environment data collection module at corresponding positions in the distribution room according to the preset sampling time window and the data of each distribution area; D4, generating a corresponding regional anomaly confidence level in the power distribution anomaly identification module according to the power distribution area environment time window data; D5, if the regional anomaly confidence is greater than the preset regional anomaly confidence threshold, the corresponding power distribution area data is defined as abnormal power distribution area data, and the corresponding sampling time window is defined as the abnormal sampling time window; D6, determining the corresponding abnormal area power distribution equipment list data based on the abnormal power distribution area data and the preset power distribution equipment installation location data; D7, collecting the corresponding power distribution equipment time window data of each power distribution equipment through the power distribution equipment data collection module according to the abnormal sampling time window and the power distribution equipment list data in the abnormal area; D8, generating corresponding equipment abnormality confidence levels in the power distribution abnormality identification module according to the time window data of each power distribution device; D9: If the device abnormality confidence level is greater than a preset device abnormality confidence level threshold, the corresponding power distribution device is defined as an abnormal power distribution device.

Images