Method, system and equipment for monitoring power distribution station house and medium

Abstract

The invention relates to the technical field of power distribution station monitoring, and discloses a method, a system, equipment and a medium for monitoring a power distribution station room, and the method comprises the steps: constructing a partial discharge diagnosis waveform graph and a partial discharge diagnosis auxiliary text through real-time partial discharge monitoring data and real-time environment monitoring data of a high-voltage switch cabinet in the power distribution station room; inputting the partial discharge type of the high-voltage switch cabinet into a pre-constructed image-text multi-mode partial discharge classification model for processing to obtain a first classification result of the partial discharge type to which the high-voltage switch cabinet belongs; determining a plurality of partial discharge mechanism model characteristic values of the partial discharge diagnosis waveform graph, matching the partial discharge mechanism model characteristic values with a pre-constructed partial discharge mechanism model, and determining a second classification result according to a matching result; the target partial discharge type of the high-voltage switch cabinet is determined based on the first classification result and the second classification result, and then the abnormal reason of the high-voltage switch cabinet is determined, so that the power distribution station room is monitored, the accuracy of distinguishing the partial discharge type of the switch cabinet and the monitoring efficiency of the power distribution station room are improved, and accurate maintenance of the high-voltage switch cabinet is facilitated.

Description

Technical Field

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

[0002] As a place for receiving, distributing, controlling and protecting electric energy, distribution stations are key nodes in the power system, and their safe operation is directly related to the reliable power supply of residents and enterprises. Since distribution stations are usually located in remote areas, they are mostly monitored by manual inspections, which is inefficient and cannot process monitoring data in real time, making it impossible to achieve accurate management of distribution stations.

[0003] It can be seen that how to improve the monitoring efficiency of power distribution stations has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0004] The present invention provides a method, system, equipment and medium for monitoring a power distribution station, which solve the problem of how to improve the monitoring efficiency of the power distribution station.

[0005] In order to solve the above technical problems, the first aspect of the present invention provides a method for monitoring a power distribution station, comprising: Acquire real-time partial discharge monitoring data and real-time environmental monitoring data of the high-voltage switchgear in the power distribution station, and construct a partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data; Inputting the partial discharge diagnosis waveform graph and the partial discharge diagnosis auxiliary text into a pre-constructed graphic and text multi-modal partial discharge classification model for processing, to obtain a first classification result of the partial discharge type corresponding to the high-voltage switchgear; Determine multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnostic waveform spectrum to match them with a pre-constructed partial discharge mechanism model, and determine a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result; The target partial discharge type of the high-voltage switchgear is determined based on the first classification result and the second classification result, and the abnormal cause of the high-voltage switchgear is determined according to the target partial discharge type to realize monitoring of the distribution station.

[0006] As one of the preferred solutions, the construction of a partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data includes: The partial discharge diagnostic waveform spectrum is constructed according to the real-time partial discharge monitoring data, and the mechanism characteristics of the real-time partial discharge monitoring data are extracted to obtain a plurality of partial discharge mechanism characteristic components; the partial discharge mechanism characteristic components include amplitude dispersion, phase aggregation, polarity effect, flight diagram characteristics, pulse balance, 50 Hz frequency component and 100 Hz frequency component; Quantifying the correlation between the real-time partial discharge monitoring data and the real-time environmental monitoring data, and generating a partial discharge external influencing factor according to the correlation quantification result; The partial discharge mechanism characteristic components and the partial discharge external influencing factors are subjected to data discretization and text escape processing, and the processing results are represented in a key-value pair manner to obtain the partial discharge diagnosis auxiliary text.

[0007] As one preferred solution, the real-time environmental monitoring data includes real-time temperature data and real-time humidity data; wherein, The quantifying the correlation between the real-time partial discharge monitoring data and the real-time environmental monitoring data, and generating a partial discharge external influencing factor according to the correlation quantification result, comprises: Performing Pearson correlation analysis and calculation on the real-time partial discharge monitoring data and the real-time temperature data in the same time period to obtain a partial discharge-temperature correlation coefficient; Performing Pearson correlation analysis and calculation on the real-time partial discharge monitoring data and the real-time humidity data in the same time period to obtain a partial discharge-humidity correlation coefficient; The partial discharge temperature correlation coefficient and the partial discharge humidity correlation coefficient are weighted according to a preset ratio to obtain the partial discharge external influencing factor.

[0008] As one of the preferred solutions, the image-text multimodal partial discharge classification model includes an image encoder, a text encoder, an image-text multimodal encoder and an image-text multimodal decoder; wherein, The inputting of the partial discharge diagnosis waveform graph and the partial discharge diagnosis auxiliary text into a pre-built graphic and text multi-modal partial discharge classification model for processing to obtain a first classification result of the partial discharge type corresponding to the high-voltage switchgear includes: Encoding the partial discharge diagnosis waveform spectrum through the image encoder to obtain a partial discharge spectrum feature vector, and encoding the partial discharge diagnosis auxiliary text based on the text encoder to obtain a partial discharge text feature vector; Based on the cross-modal feature alignment loss function and the image-text matching loss function, the partial discharge spectrum feature vector and the partial discharge text feature vector are input into the image-text multimodal encoder for processing to obtain an image-text encoding result; The image-text encoding result is input into the image-text multimodal decoder for processing, and a first classification result of the partial discharge type corresponding to the high-voltage switch cabinet is output.

[0009] As one of the preferred solutions, the method of determining multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnostic waveform spectrum to match them with a pre-built partial discharge mechanism model, and determining a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result, includes: Quantifying multiple partial discharge mechanism model characteristic values ​​of the partial discharge diagnostic waveform spectrum; the partial discharge mechanism model characteristic values ​​include amplitude, number of discharges, discharge time interval, 50Hz and 100Hz frequency component comparison, positive and negative semi-axis symmetry, single peak or double peak characteristics, classification diagram, ultrasonic detection probability and PRPS characteristics; The characteristic values ​​of the multiple partial discharge mechanism models are matched with the partial discharge mechanism models corresponding to the multiple pre-constructed partial discharge types to obtain a plurality of matching degrees, and the partial discharge type corresponding to the partial discharge mechanism model with the highest matching degree is taken as the second classification result.

[0010] As one preferred solution, the first classification result includes the partial discharge type and its corresponding probability value; The determining a target partial discharge type of the high-voltage switchgear based on the first classification result and the second classification result includes: Determine a first weight value of the first classification result according to the probability value, and determine a second weight value of the second classification result based on the matching degree; The first weight value and the second weight value are normalized to obtain a normalized weight value, and a target partial discharge type of the high-voltage switchgear is determined according to the normalized weight value, the first classification result, and the second classification result.

[0011] As one of the preferred solutions, after determining the abnormal cause of the high-voltage switchgear according to the target partial discharge type, the method further includes: Constructing a hidden danger feature set of the high-voltage switch cabinet; the hidden danger feature set includes excessive humidity in the station room, equipment aging and family defects; Acquire equipment information of the high-voltage switch cabinet, and when it is determined that the high-voltage switch cabinet meets the hidden danger feature set according to the equipment information and the real-time environmental monitoring data, determine the occurrence probability of each hidden danger feature to generate a risk identification list; Early warning information of the power distribution station is generated according to the risk identification list to achieve early warning of the power distribution station.

[0012] A second aspect of the present invention provides a monitoring system for a power distribution station, comprising: A partial discharge information acquisition module is used to acquire real-time partial discharge monitoring data and real-time environmental monitoring data of the high-voltage switchgear in the power distribution station, and to construct a partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data; A first result generating module is used to input the partial discharge diagnosis waveform spectrum and the partial discharge diagnosis auxiliary text into a pre-built graphic and text multi-modal partial discharge classification model for processing, so as to obtain a first classification result of the partial discharge type corresponding to the high-voltage switchgear; A second result generating module is used to determine multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnostic waveform spectrum, so as to match them with a pre-constructed partial discharge mechanism model, and determine a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result; An abnormality cause determination module is used to determine a target partial discharge type of the high-voltage switchgear based on the first classification result and the second classification result, and determine the abnormality cause of the high-voltage switchgear according to the target partial discharge type to realize monitoring of the distribution station.

[0013] A third aspect of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for monitoring a distribution station room as described above when executing the computer program.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the monitoring method for the distribution station room as described above is implemented.

[0015] Compared with the prior art, the embodiments of the present invention have the following advantages: (1) By combining the graphic multi-modal partial discharge classification model and the partial discharge mechanism model, the partial discharge type of the high-voltage switchgear and its abnormal cause can be judged more accurately; real-time collection and processing of monitoring data can be carried out to timely discover and warn of potential faults and improve operation and maintenance efficiency; through automated monitoring and diagnosis, the cost of manual inspections can be reduced, while improving the accuracy and timeliness of operation and maintenance; (2) Through the comprehensive use of real-time monitoring, data analysis, model matching and other technical means, accurate monitoring and diagnosis of high-voltage switchgear in distribution stations is achieved, which is of great significance for improving the safety and reliability of power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of a method for monitoring a power distribution station provided by a certain embodiment of the present invention; Figure 2 It is a diagram of the training process of a graphic multimodal partial discharge classification model provided by a certain embodiment of the present invention; Figure 3 It is a structural diagram of a monitoring system for a power distribution station provided by a certain embodiment of the present invention; Figure 4 It is a structural diagram of an electronic device provided by a certain embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0020] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two components. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are for illustrative purposes only, and do not indicate or imply that the system or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0021] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0022] In one embodiment, if Figure 1 As shown, the first aspect of the present invention provides a method for monitoring a power distribution station, comprising: S1. Acquire real-time partial discharge monitoring data and real-time environmental monitoring data of the high-voltage switchgear in the power distribution station, and construct a partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data; Specifically, the present invention adopts a cloud-edge collaborative approach to set up the cloud, edge and end sides to obtain monitoring data for the distribution station; wherein, the cloud-edge collaborative computing platform is an intelligent computing architecture developed to meet the new challenges brought by the development of the Internet of Things (IoT). To manage digital cloud computing, the platform can sink computing power from the centralized cloud to the edge nodes close to the data source, optimize data processing capabilities through a distributed computing model, and the cloud-edge collaborative computing model not only extends the cloud native capabilities, but also deploys edge nodes to enable data processing, business applications and artificial intelligence (AI) models to be executed at the edge end close to the data source, solving the problems of real-time response, data privacy, and maintenance convenience encountered by the Internet of Things when it is implemented. It significantly improves data processing efficiency and system response speed in practical applications in multiple industries, realizes diversified intelligent applications, and helps the digital transformation of various industries. The cloud, edge and end sides together constitute a digital intelligent management and control system for distribution stations. The system deploys a variety of intelligent sensors in distribution stations in remote areas to achieve insulation perception of high-voltage switch cabinets, environmental status monitoring, and active alarms for fire and security anomalies.

[0023] The digital management and control system of distribution substations adopts a three-layer architecture of cloud side, edge side and terminal side. The cloud side includes the distribution network cloud master station for managing the distribution substation, which can be deployed on the distribution automation platform and is responsible for the status overview, data display, data storage and alarm push of the distribution substation; the distribution network cloud master station can be deployed on one or more computing devices to realize monitoring and early warning of the distribution substation; the edge side includes distribution digital access node equipment, which can realize the unified data collection of main equipment sensing equipment, dynamic environment sensors, security sensors, and fire protection sensors through the power transmission and transformation Internet of Things protocol, and can access the distribution network cloud master station through 4G or 5G private network; the terminal side includes various intelligent sensors, which are responsible for collecting comprehensive status information of distribution substations and realizing abnormal monitoring of the main equipment of distribution substations; by deploying intelligent sensors and distribution digital access node equipment in distribution substations, collecting and aggregating station monitoring data, and deploying digital distribution network cloud master stations on the cloud side, comprehensive, real-time and continuous monitoring of multiple distribution substations can be realized.

[0024] Various intelligent sensors included in the end side can be deployed in the distribution station, including main equipment sensing equipment, dynamic environment sensors, security sensors and fire protection sensors; among them, the main equipment sensing equipment includes partial discharge sensors, and the partial discharge sensors include ultrasonic partial discharge sensors and dual ultrasonic transient ground voltage partial discharge sensors. One or more high-voltage switch cabinets are usually deployed in the distribution station. The partial discharge sensor can be deployed on the high-voltage switch cabinet to realize the detection of the partial discharge ultrasonic parameters of the high-voltage switch cabinet, and enhance the local insulation abnormality monitoring capability of the high-voltage switch cabinet. The deployment of ultrasonic partial discharge sensors can improve the perception capability of the main equipment (such as high-voltage switch cabinet) in the distribution station; specifically, 6 ultrasonic partial discharge sensors can be deployed in the distribution station, 5 of which are deployed in the incoming and outgoing line intervals or high-voltage switch cabinets, and 1 is used as a background noise sensor, which is deployed on the cabinet side of the high-voltage switch cabinet to collect background noise in the station.

[0025] The operation levels of distribution substations include conventional operation and maintenance substations and key operation and maintenance substations. Conventional operation and maintenance substations usually deploy one or more ultrasonic partial discharge sensors, smoke detectors, water immersion sensors, temperature and humidity sensors, SF6 and O2 sensors, and access control sensors; key operation and maintenance substations usually deploy one or more dual ultrasonic transient ground voltage partial discharge sensors, smoke detectors, water immersion sensors, temperature and humidity sensors, SF6 and O2 sensors, and access control sensors; among them, a dual ultrasonic transient ground voltage partial discharge sensor can be set as a background noise sensor, which is battery-powered and can collect 20kHz~100kHz ultrasonic partial discharge signals and 3MHz~100MHz transient ground voltages generated by partial discharge of electrical equipment. It can identify partial discharge and interference through partial discharge identification algorithms combined with node equipment and system applications, and can also improve the dimension of discharge signal monitoring and improve the accuracy of discharge signal monitoring. It also has the dual collection capabilities of ultrasonic partial discharge and transient ground voltage, strengthens the insulation damage monitoring capability, and thus collects the background noise of the distribution substation.

[0026] In addition, six dual ultrasonic transient ground voltage partial discharge sensors can be deployed in the distribution station, which can be deployed in the incoming and outgoing line intervals or high-voltage switch cabinets. The outward ultrasonic probe of one dual ultrasonic transient ground voltage partial discharge sensor is the source of background noise values, and the dual ultrasonic transient ground voltage partial discharge sensor is used as a background noise sensor.

[0027] Security sensors include access control sensors, which are installed on one side of the station door of the distribution station, above the wall of the entrance door, or installed on the door frame using a magnetic control strip. They can also be installed on the lintel of the main door using a permanent magnet to collect the station door status in real time, strengthen the alarm capability for illegal intrusion into the distribution station, and thus improve the security capability of the distribution station.

[0028] Dynamic environment sensors include water immersion sensors, temperature and humidity sensors, SF6 and O2 sensors, etc.; among them, water immersion sensors can be installed in the cable trench of the distribution station, close to the gap of the top cable cover, or installed at a height of 15 cm from the bottom of the cable trench with the detection electrode, to monitor abnormal water levels in the station to achieve flood warning capabilities.

[0029] The temperature and humidity sensor can be installed next to the high-voltage switchgear in the distribution station or in the measured environment. It can be installed at a suitable position on the wall or magnetically attached to the side of the high-voltage switchgear to monitor the temperature and humidity in real time and improve the perception of the impact of abnormal temperature and humidity on the main equipment. The monitoring data adopts the power transmission and transformation Internet of Things protocol and is sent to the corresponding distribution digital access node device through wireless LoRa communication. The distribution digital access node device then transmits the monitoring data to the upper-level monitoring system through Ethernet or RS485 / RS232 and other communication methods to realize remote monitoring and early warning of temperature and humidity.

[0030] SF6 and O2 sensors can be installed on the cabinet surface of the high-voltage switchgear, or on the wall inside the station near the power socket, the maintenance power box, or directly below the distribution digital access node equipment, 30 cm above the ground, to improve the air tightness monitoring capability of the switch and reduce the risk of suffocation for operation and maintenance personnel. Since the circuit breaker components in the high-voltage switchgear are insulated with SF6, monitoring its content to determine whether there is a leak can prevent people from inhaling harmful gases. The installation of dynamic environment sensors can enhance the environmental perception capability of the distribution station.

[0031] Fire sensors include smoke detectors, etc. Smoke detectors can be installed at high places in the distribution station building and deployed at the center of the top of the station building to monitor the smoke concentration in the station, improve fire warning and emergency response capabilities, and thereby enhance the fire-fighting capabilities of the distribution station building.

[0032] In the distribution station room, multiple sensors are set up in the above-mentioned way to collect the real-time environmental monitoring data and real-time partial discharge monitoring data of the high-voltage switch cabinet through collaborative cooperation; among which, the real-time environmental monitoring data includes temperature, humidity, etc.; the real-time partial discharge monitoring data includes the partial discharge data inside the cabinet, the partial discharge data outside the cabinet and the transient ground voltage data, which are divided into structured data and unstructured data. Partial discharge (hereinafter referred to as partial discharge) is one of the main hidden dangers in the operation and maintenance of power equipment. Partial discharge will cause the insulation of the equipment to deteriorate, and in severe cases, it will cause equipment operation failure. Timely discovery and disposal of partial discharge hazards have a significant impact on the safe and stable operation of power equipment. The partial discharge data inside the cabinet and the partial discharge data outside the cabinet are structured data, including the highest peak value of partial discharge, the average value of partial discharge, the number of pulses of partial discharge, etc. The structured data is used for threshold judgment. According to the partial discharge data of the switch cabinet, it can be determined whether the attention interval, the serious interval and the maintenance interval are reached. The present invention can be arranged that when the partial discharge data of the switch cabinet is above 8dBμV and below 20dBμV, it reaches the attention interval; when the partial discharge data of the switch cabinet is above 20dBμV and below 30dBμV, it reaches the serious interval; when the partial discharge data of the switch cabinet is above 30dBμV, it reaches the maintenance required interval. When the partial discharge data of the switch cabinet is monitored to reach the above intervals, general alarm, serious alarm and crisis alarm alarm information can be generated respectively to prompt the operation and maintenance personnel.

[0033] The alarm level can be determined through structured data, and different alarm levels can explain the severity of the partial discharge abnormality of the high-voltage switch cabinet to the operation and maintenance personnel. However, the cause of the partial discharge abnormality of the switch cabinet cannot be further determined based on the structured data, nor can the partial discharge data be analyzed when the partial discharge data of the switch cabinet does not reach the abnormal level, and then the possible type of partial discharge abnormality can be determined to eliminate the relevant causes. Therefore, the present invention collects unstructured data of the high-voltage switch cabinet through a partial discharge sensor, which includes a partial discharge pulse signal, and a partial discharge map of the partial discharge data of the switch cabinet can be drawn according to the partial discharge pulse signal. After obtaining these real-time data, pre-processing operations such as data cleaning are performed on them, such as deleting duplicate data, filling missing values, etc., to improve the accuracy of the data.

[0034] In one embodiment, constructing a partial discharge diagnosis waveform graph and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data includes: The partial discharge diagnostic waveform spectrum is constructed according to the real-time partial discharge monitoring data, and the mechanism characteristics of the real-time partial discharge monitoring data are extracted to obtain a plurality of partial discharge mechanism characteristic components; the partial discharge mechanism characteristic components include amplitude dispersion, phase aggregation, polarity effect, flight diagram characteristics, pulse balance, 50 Hz frequency component and 100 Hz frequency component; Quantifying the correlation between the real-time partial discharge monitoring data and the real-time environmental monitoring data, and generating a partial discharge external influencing factor according to the correlation quantification result; The partial discharge mechanism characteristic components and the partial discharge external influencing factors are subjected to data discretization and text escape processing, and the processing results are represented in a key-value pair manner to obtain the partial discharge diagnosis auxiliary text.

[0035] Specifically, the present invention constructs a partial discharge diagnostic waveform spectrum, namely, a partial discharge phase distribution spectrum (PRPD), according to real-time partial discharge monitoring data; then, the mechanism characteristics of the real-time partial discharge monitoring data are extracted to generate partial discharge mechanism characteristic components, namely, for the partial discharge sampling data, based on the partial discharge signal generation mechanism, seven types of partial discharge mechanism characteristic components are calculated, namely, partial discharge signal amplitude dispersion (Tamp), phase aggregation (Tphase), polarity effect (Tpole), flight pattern characteristics (Tfly), pulse balance (Tpulse), 50Hz frequency component (Tf50), 100Hz (Tf100) frequency component, etc.

[0036] In one embodiment, the real-time environmental monitoring data includes real-time temperature data and real-time humidity data; wherein, The quantifying the correlation between the real-time partial discharge monitoring data and the real-time environmental monitoring data, and generating a partial discharge external influencing factor according to the correlation quantification result, comprises: Performing Pearson correlation analysis and calculation on the real-time partial discharge monitoring data and the real-time temperature data in the same time period to obtain a partial discharge-temperature correlation coefficient; Performing Pearson correlation analysis and calculation on the real-time partial discharge monitoring data and the real-time humidity data in the same time period to obtain a partial discharge-humidity correlation coefficient; The partial discharge temperature correlation coefficient and the partial discharge humidity correlation coefficient are weighted according to a preset ratio to obtain the partial discharge external influencing factor.

[0037] The present invention performs Pearso correlation calculation on the real-time partial discharge monitoring data, the real-time temperature data, and the real-time humidity data in the same period, respectively, to obtain the partial discharge temperature and humidity correlation coefficient, and divides it into three levels according to [0, 0.3), [0.3, 0.7), and [0.7, 1], so as to obtain the partial discharge external influencing factor. The present invention quantifies the correlation between the real-time monitoring data and the environmental monitoring data, and generates the partial discharge external influencing factor, which helps to identify the influence of environmental factors on partial discharge behavior, thereby enhancing environmental adaptability.

[0038] After each partial discharge mechanism characteristic component and partial discharge external influencing factor are correspondingly translated into the text "L, M, H", data discretization and text translation are performed on them, and a partial discharge diagnosis auxiliary text S is generated in a key-value pair mode of name and value "key_value", such as: "Tamp_H, Tphase_L, Tpole_M, Tfly_L, Tpulse_H, Tf50_M, Tf100_L,Xtemp_H, Xhumid_L". By extracting multiple partial discharge mechanism characteristic components, the present invention can more comprehensively understand the characteristics of partial discharge, thereby improving the accuracy and reliability of fault diagnosis; the data discretization and text translation processing make the diagnosis result more intuitive and easy to understand, and easy to understand and explain; the generated partial discharge diagnosis auxiliary text can be used as the input of subsequent automated and intelligent diagnostic systems to support higher-level fault warning and diagnostic decisions.

[0039] S2. Inputting the partial discharge diagnosis waveform spectrum and the partial discharge diagnosis auxiliary text into a pre-constructed graphic-text multimodal partial discharge classification model for processing, and obtaining a first classification result of the partial discharge type corresponding to the high-voltage switchgear; wherein the graphic-text multimodal partial discharge classification model includes an image encoder, a text encoder, a graphic-text multimodal encoder, and a graphic-text multimodal decoder; In one embodiment, step S2 includes: Encoding the partial discharge diagnosis waveform spectrum through the image encoder to obtain a partial discharge spectrum feature vector, and encoding the partial discharge diagnosis auxiliary text based on the text encoder to obtain a partial discharge text feature vector; Based on the cross-modal feature alignment loss function and the image-text matching loss function, the partial discharge spectrum feature vector and the partial discharge text feature vector are input into the image-text multimodal encoder for processing to obtain an image-text encoding result; The image-text encoding result is input into the image-text multimodal decoder for processing, and a first classification result of the partial discharge type corresponding to the high-voltage switch cabinet is output.

[0040] Specifically, due to the complexity of partial discharge phenomena in switch cabinets in distribution stations, only traditional methods are used to classify and identify partial discharge maps, such as PRPD map images, using CNN convolutional neural networks. This has limitations and seriously affects the accuracy of partial discharge diagnosis, namely: the on-site signals in distribution stations are complex and easily affected by internal and external interference, and their PRPD waveform maps vary widely, which affects the accuracy of classification based on image recognition; the PRPD map image is generated based on phase superposition of pulse sampling signal sequence data sampled once, reflecting the phase and amplitude distribution relationship of partial discharge pulses within one power frequency cycle; information loss will occur in the process of generating PRPD map images, such as the inability to express the time interval between adjacent pulses and the inability to express the amplitude of frequency domain components, which limits the accurate diagnosis of partial discharge types. Based on this, the present invention proposes a graphic multimodal partial discharge classification model, and its training process is as follows: Figure 2 As shown in the figure, not only partial discharge maps, such as PRPD map images, are used to classify partial discharge types, but also partial discharge mechanism characteristic components are extracted from partial discharge monitoring data to assist in classification, and external influencing parameters related to partial discharge are incorporated into the diagnosis model, which is conducive to the accurate diagnosis of partial discharge. In addition to partial discharge caused by insulation degradation of the equipment itself, when the temperature or humidity in the distribution station is too high, the probability of partial discharge in the switch cabinet will also increase. Therefore, taking external influencing parameters into account can improve the accuracy of partial discharge diagnosis.

[0041] Due to the different temperatures and humidity in the distribution station, the types of partial discharge in the switch cabinet will be different, or the probability of different types of partial discharge will be different. For example, different parts of the switch cabinet will produce different types of partial discharge under different temperatures and humidity. Therefore, the temperature and humidity are trained together with the partial discharge data to improve the accuracy of the graphic multimodal partial discharge classification model in determining the partial discharge type.

[0042] When training the graphic multimodal partial discharge classification model, the historical partial discharge sampling data of the switch cabinet is obtained based on the partial discharge sensor deployed in the distribution station, and the historical partial discharge sampling data includes sampling data of multiple partial discharge signals, for example, a signal sampling every 0.27ms within a total sampling time of 1s, and a total of 3600 ultrasonic partial discharge sampling pulse amplitudes; the present invention also obtains the distribution station environment data at each signal sampling, and the distribution station environment data includes temperature data and humidity data; then, according to each sampling data, the corresponding historical partial discharge map and historical auxiliary text are generated in the above manner, that is, based on the picture-text data pairs generated for each historical partial discharge sampling, manual annotation work is carried out, and the annotation types include 6 categories: no partial discharge, surface discharge, corona discharge, particle discharge, suspended discharge and air gap discharge, and based on the Transformer model, the annotated data is used to realize the training of the graphic multimodal partial discharge classification model, and the specific training process is similar to the classification process of the real-time data, and only the data acted on is different.

[0043] The classification process of the image-text multimodal partial discharge classification model for real-time data includes: encoding the partial discharge diagnosis waveform spectrum through an image encoder (such as CNN, ViT, etc.), and based on the self-attention mechanism and feedforward propagation function, to form a partial discharge spectrum feature vector, which can capture key information in the waveform spectrum, such as discharge intensity, discharge mode, etc.; that is, using ViT to apply the Transformer architecture to the field of image processing, by dividing the image into a series of small patches, and converting these small patches into embedded vectors, and then encoding them through the Encoder part of the Transformer, so as to extract the partial discharge spectrum feature vector; The encoding of the auxiliary text for partial discharge diagnosis is realized through a text encoder (such as Transformer architecture, RNN, LSTM, GRU, etc.), and based on the self-attention mechanism and feedforward propagation function, a partial discharge text feature vector is formed. This vector can capture the semantic information in the text, such as descriptions of discharge type and discharge location. Similar to the Vision Transformer in the image encoder, the text encoder also adopts the Transformer architecture, and converts the input text into a hidden representation through the self-attention mechanism and feedforward neural network. With the advantages of Transformer in processing long sequences and capturing global dependencies, the text is converted into a high-dimensional hidden representation. The two types of vectors are imported into the image-text multimodal encoder, which can learn the association information between images and texts, and optimize based on the cross-modal feature alignment loss function and the image-text matching loss function to obtain the image-text encoding result, which integrates the information of the image and text and provides rich feature representation for subsequent decoding and classification; that is, by introducing the attention mechanism, the image-text multimodal encoder can dynamically focus on the key information in the image and text, and capture the association between them, which is achieved by calculating the similarity score between the image and text features, using a shared Transformer layer and further fusion and encoding through the self-attention mechanism and feedforward neural network, so that the model can learn the deep association between images and texts; Finally, the image-text encoding result is output through the image-text multimodal decoder to obtain the classification result, that is, a Transformer-based decoder is used, and the Decoder part of the Transformer is used to generate the corresponding output according to the encoding result, that is, the partial discharge type classification result of the high-voltage switchgear; an example of the classification result is as follows: the probability of surface discharge is 80%, the probability of suspension discharge is 3%, the probability of air gap discharge is 5%, the probability of corona discharge is 1%, and the probability of particle discharge is 11%; finally, the partial discharge type with the highest probability value is taken as the first classification result; for example, when the classifier layer outputs the probability of surface discharge as 80%, the surface discharge is taken as the first classification result.

[0044] The overall architecture of the image-text multimodal partial discharge classification model includes: input layer: receiving image and text data respectively, and performing preprocessing (such as image scaling, text segmentation, etc.); image encoder and text encoder: processing image and text data respectively, and extracting their respective feature representations; image-text multimodal encoder: fusing the feature representations of the image and text, and extracting cross-modal correlation information; classification layer (also known as image-text multimodal decoder): based on the fused feature representation, using a fully connected layer or other classifiers for partial discharge classification.

[0045] The present invention combines image and text information to more comprehensively capture the partial discharge characteristics of high-voltage switchgear, thereby improving the accuracy of classification; since image and text information have different characteristics and advantages, the scheme can resist the noise and interference of a single information source to a certain extent and enhance the robustness of the model; the scheme promotes cross-modal learning between images and texts through cross-modal feature alignment and image-text matching loss functions, providing a basis for subsequent image-text fusion and joint analysis; in addition, the image-text multimodal partial discharge classification model uses partial discharge spectra to extract characteristic components of partial discharge mechanisms, and combines with partial discharge external influencing factor data to give full play to the advantages of joint diagnosis of partial discharge multi-faceted characterization data, avoid the problem of insufficient information represented by single data, and achieve accurate judgment of the type of partial discharge in the switchgear.

[0046] S3, determining multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnostic waveform spectrum to match them with a pre-constructed partial discharge mechanism model, and determining a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result; In one embodiment, step S3 includes: Quantifying multiple partial discharge mechanism model characteristic values ​​of the partial discharge diagnostic waveform spectrum; the partial discharge mechanism model characteristic values ​​include amplitude, number of discharges, discharge time interval, 50Hz and 100Hz frequency component comparison, positive and negative semi-axis symmetry, single peak or double peak characteristics, classification diagram, ultrasonic detection probability and PRPS characteristics; The characteristic values ​​of the multiple partial discharge mechanism models are matched with the partial discharge mechanism models corresponding to the multiple pre-constructed partial discharge types to obtain a plurality of matching degrees, and the partial discharge type corresponding to the partial discharge mechanism model with the highest matching degree is taken as the second classification result.

[0047] Specifically, the present invention pre-constructs a partial discharge mechanism model corresponding to each partial discharge type, including a surface discharge mechanism model, a suspended discharge mechanism model, a corona discharge mechanism model, an air gap discharge mechanism model and a particle discharge mechanism model. Each partial discharge mechanism model is determined according to the partial discharge spectrum corresponding to the partial discharge type, including extracting the characteristic value of each partial discharge spectrum as the characteristic value of the partial discharge mechanism model of the corresponding partial discharge type. For example, if the characteristic value corresponding to the amplitude dispersion of the surface discharge partial discharge spectrum is larger, the larger value is used as the characteristic value of the amplitude dispersion feature in the surface discharge mechanism model; wherein, the characteristic value of the partial discharge mechanism model includes one or more features of amplitude height, amplitude dispersion, discharge times, discharge time interval, 50Hz frequency component, 100Hz frequency component, 50Hz and 100Hz frequency component comparison, positive and negative semi-axis symmetry, single peak or double peak feature, polarity effect, classification diagram, ultrasonic detection probability and PRPS feature, and the characteristic value of the partial discharge mechanism model of each partial discharge mechanism model includes characteristic values ​​of multiple partial discharge mechanism model features; wherein, examples of characteristic values ​​of each mechanism model are shown in Table 1: Table 1 Example table of characteristic values ​​of each mechanism model The "low", "large" and "high" in the amplitude can be classified as follows: the highest value of the amplitude in all training samples of the text-image multimodal partial discharge classification model is used as the amplitude standard value, and the amplitude standard value is divided into four equal parts to obtain four increasing value intervals. From the first to the fourth value intervals, the amplitude in the first value interval is "low", the amplitude in the third value interval is "large", and the amplitude in the fourth value interval is "high". In the amplitude dispersion, "large" means that the amplitude covers more than 60% of all acquisition phases, "small" means that the amplitude covers less than 30% of all acquisition phases, and "very large" means that the amplitude covers more than 80% of all acquisition phases. The "few" and "more" in the number of discharges can also be classified as follows: the quartiles of all the discharges in all training samples of the text-image multimodal partial discharge classification model are determined to obtain the positions of the first to fourth quartiles, and the number of discharges less than the lower quartile is regarded as "few", and the number of discharges greater than the second quartile is regarded as "more". Similarly, "obvious", "not obvious", "none or very small" in the 50Hz frequency component can also be classified as follows: the highest value of the amplitude in all training samples of the text-image multimodal partial discharge classification model is used as the amplitude standard value, and the amplitude standard value is divided into four equal parts to obtain four successively increasing value intervals, the first to fourth value intervals, the amplitude in the first value interval is "none or very small"; the amplitude in the second value interval is "not obvious", and the amplitude in the third and fourth value intervals is "obvious". In this way, the present invention can perform feature extraction based on the drawn partial discharge spectrum, determine the characteristic values ​​of one or more partial discharge mechanism model features, so as to match the partial discharge mechanism model, and there is no restriction on the specific method of extracting features based on the partial discharge spectrum, such as extraction through image recognition algorithms and the like.

[0048] When determining the matching degree between multiple partial discharge mechanism model characteristic values ​​and the partial discharge mechanism model corresponding to each partial discharge type, each partial discharge mechanism model characteristic value can be compared with the partial discharge mechanism model characteristic value of the corresponding partial discharge mechanism model feature in the partial discharge mechanism model. If the partial discharge mechanism model characteristic values ​​are the same, the partial discharge mechanism model feature matches; if they are different, the partial discharge mechanism model feature does not match, and then it is determined whether the next partial discharge mechanism model characteristic value is the same, until all partial discharge mechanism model characteristic values ​​are compared, and the partial discharge mechanism model with the same partial discharge mechanism model characteristic value is calculated. The ratio of the number of partial discharge mechanism model features to the total number of all partial discharge mechanism model features of the partial discharge mechanism model is used as the matching degree. The corresponding weight can also be set for each partial discharge mechanism model feature, and the matching degree is calculated according to the partial discharge mechanism model features that can be matched and the corresponding set weights. The weight set for each partial discharge mechanism model feature can be determined according to the importance of the partial discharge mechanism model feature or the empirical value after multiple tests. The present invention does not limit the weight value and setting method corresponding to each partial discharge mechanism model feature. Finally, the partial discharge type corresponding to the partial discharge mechanism model with the highest matching degree is taken as the second classification result.

[0049] The present invention can more comprehensively reflect the essence of the discharge phenomenon by quantifying and matching multiple partial discharge mechanism model characteristic values, thereby improving the accuracy of diagnosis; realize the automation of partial discharge diagnosis, reduce manual intervention, and improve work efficiency; consider multiple partial discharge mechanism model characteristic values ​​to adapt to different types of partial discharge phenomena, and has strong versatility and adaptability; through the quantification and matching of the partial discharge mechanism model characteristic values, it can provide strong support for the fault diagnosis of power equipment, and help to timely discover and deal with potential fault hazards.

[0050] S4. Determine a target partial discharge type of the high-voltage switchgear based on the first classification result and the second classification result, and determine an abnormal cause of the high-voltage switchgear according to the target partial discharge type, so as to monitor the distribution station; In one embodiment, the first classification result includes the partial discharge type and its corresponding probability value; The determining a target partial discharge type of the high-voltage switchgear based on the first classification result and the second classification result includes: Determine a first weight value of the first classification result according to the probability value, and determine a second weight value of the second classification result based on the matching degree; The first weight value and the second weight value are normalized to obtain a normalized weight value, and a target partial discharge type of the high-voltage switchgear is determined according to the normalized weight value, the first classification result, and the second classification result.

[0051] Specifically, the present invention normalizes the probability value in the first classification result and the second classification result together with the matching degree of the corresponding partial discharge mechanism model, and uses them as the first weight value and the second weight value respectively; wherein, the maximum values ​​of the first weight value and the second weight value are both 50%. For example, when the probability value is 80%, the first weight value obtained after normalization is 40%; when the matching degree is 70%, the second weight value obtained after normalization is 35%. Then, according to the first weight value, the second weight value, the first classification result and the second classification result, it is determined which classification result has a higher score, and it is used as the target partial discharge type corresponding to the switch cabinet partial discharge data. When the first classification result and the second classification result are the same, the partial discharge type pointed to by the same classification result can be directly used as the target partial discharge type corresponding to the switch cabinet partial discharge data.

[0052] Each type of partial discharge may correspond to one or more partial discharge abnormal causes, and the partial discharge abnormal causes corresponding to each type of partial discharge may be collected based on the historical operation and maintenance experience and troubleshooting experience of the high-voltage switchgear, so as to predict the partial discharge abnormal causes. The partial discharge abnormal causes corresponding to the extended surface discharge may include: the surface degradation of the insulating medium, such as the rupture of the cable insulation layer, etc.; the partial discharge abnormal causes corresponding to the suspended discharge may include the cracking of the fuse, etc.; the partial discharge abnormal causes corresponding to the corona discharge may include the insulation abnormality of the components in the high-voltage switchgear, resulting in tip discharge; the partial discharge abnormal causes corresponding to the air gap discharge include the hollowing of the insulating medium, the quality defects, etc.; the partial discharge abnormal causes corresponding to the particle discharge include the accumulation of a lot of dust inside the high-voltage switchgear, causing the dust to float and be charged in the high-voltage switchgear, etc. The present invention does not limit the specific partial discharge abnormal causes corresponding to each type of partial discharge, and can be added as needed. After the partial discharge type is determined, the pre-stored partial discharge abnormal cause corresponding to the partial discharge type can be obtained and used as the predicted partial discharge abnormal cause; in addition, the abnormal cause can be analyzed and determined according to the classified target partial discharge type, combined with the structural characteristics, operating environment and historical fault data of the high-voltage switch cabinet, and the specific process is not described in detail here. By combining the weights of the two classification methods, the present invention can make full use of their respective advantages, reduce the errors that may be caused by a single classification method, and thus improve the accuracy of classification.

[0053] In one embodiment, after determining the abnormal cause of the high-voltage switchgear according to the target partial discharge type, the method further includes: Constructing a hidden danger feature set of the high-voltage switch cabinet; the hidden danger feature set includes excessive humidity in the station room, equipment aging and family defects; Acquire equipment information of the high-voltage switch cabinet, and when it is determined that the high-voltage switch cabinet meets the hidden danger feature set according to the equipment information and the real-time environmental monitoring data, determine the occurrence probability of each hidden danger feature to generate a risk identification list; Early warning information of the power distribution station is generated according to the risk identification list to achieve early warning of the power distribution station.

[0054] Since the influence of ambient humidity on the partial discharge of the switch cabinet is positively correlated, and when the humidity of the station room reaches more than 50%, the partial discharge signal is significantly enhanced. Therefore, the present invention can set the preset humidity threshold to 50%, that is, when the humidity of the station room reaches the preset humidity threshold of 50%, the excessive humidity of the station room is used as the influencing factor of the abnormal partial discharge of the high-voltage switch cabinet, indicating that the abnormal partial discharge of the high-voltage switch cabinet is caused by the excessive humidity of the station room.

[0055] The present invention collects the equipment information of the high-voltage switchgear in each power distribution station in advance, including the operation time and operation duration of the high-voltage switchgear, and obtains the time of the historical partial discharge abnormality of each high-voltage switchgear, and associates and stores the time of the historical partial discharge abnormality of each high-voltage switchgear with the operation duration, and determines the operation duration of each high-voltage switchgear when the historical partial discharge abnormality occurs; then, the information of the partial discharge abnormality and the operation duration of the high-voltage switchgear is counted, and the connection between the partial discharge abnormality of the high-voltage switchgear and the operation duration is established, as well as the fitting function between the probability of the partial discharge abnormality of the high-voltage switchgear and the operation duration, and the operation duration when the partial discharge abnormality of the switchgear is greater than the preset probability threshold is determined according to the fitting function, such as the preset probability threshold is set to 50%, and the operation duration when the probability of the partial discharge abnormality of the switchgear is greater than 50% is 13-14 years. As the operation duration of the high-voltage switchgear increases, the probability of the occurrence of partial discharge abnormality and other faults increases accordingly, and the operation duration threshold can be determined according to the operation duration when the probability of the partial discharge abnormality of the switchgear is greater than the preset probability threshold, such as taking 13 years as the operation duration threshold. Then, by obtaining the operation time of the high-voltage switchgear, if the operation time is greater than the preset operation time threshold, the aging of the high-voltage switchgear equipment can be used as an influencing factor of the partial discharge abnormality of the high-voltage switchgear.

[0056] In addition, the equipment information also includes the manufacturer information, brand information and model information of the high-voltage switchgear, and also counts the family defects of the high-voltage switchgear. The family defects include the high-voltage switchgear corresponding to the manufacturer information, brand information and model information. According to the live detection data of the equipment, it is shown that the number of partial discharge abnormalities and other faults of a certain component is large. According to the family defects, the high-voltage switchgear with the same manufacturer information, brand information and model information in all distribution stations is marked. When the high-voltage switchgear has a partial discharge abnormality, it is determined whether the high-voltage switchgear is marked. If the high-voltage switchgear is marked, the family defect is used as the influencing factor of the partial discharge abnormality of the high-voltage switchgear.

[0057] Based on this, the present invention constructs excessive humidity in the station room, aging of equipment and family defects as a hidden danger feature set of high-voltage switchgear; and uses excessive humidity in the station room as a hidden danger feature for early warning, so as to deal with the excessive humidity in the station room and avoid abnormal partial discharge of the switchgear and more serious faults; uses aging of high-voltage switchgear equipment as a hidden danger feature for early warning, so as to increase the maintenance frequency of high-voltage switchgear with aging equipment and avoid abnormal partial discharge of the switchgear and more serious faults; uses family defects as hidden danger features for early warning, so as to increase the maintenance frequency of marked high-voltage switchgear, or replace components that are prone to problems, so as to avoid abnormal partial discharge of the switchgear and more serious faults.

[0058] The present invention obtains the equipment information of the high-voltage switch cabinet, and when it is determined that the high-voltage switch cabinet meets the hidden danger characteristics in the hidden danger characteristic set according to the equipment information and the real-time environmental monitoring data, that is, when it is determined according to the equipment information that the high-voltage switch cabinet is marked, it is determined that the high-voltage switch cabinet in the distribution station has the hidden danger characteristics of family defects, and the probability of occurrence of family defects is determined according to the probability value of partial discharge abnormalities and other faults of the high-voltage switch cabinet corresponding to the manufacturer information, brand information and signal information, and added to the risk identification list; when it is determined according to the equipment information that the high-voltage switch cabinet reaches the commissioning time threshold, it is determined that the high-voltage switch cabinet in the distribution station has the hidden danger characteristics of high-voltage switch cabinet equipment aging, and according to the fitting function of the partial discharge abnormality of the high-voltage switch cabinet and the commissioning time, the probability of partial discharge abnormality of the high-voltage switch cabinet under the commissioning time is determined, and used as the probability of occurrence of high-voltage switch cabinet equipment aging; when it is determined that the station room humidity is greater than the preset humidity threshold according to the station room humidity uploaded by the temperature and humidity sensor, it is determined that the high-voltage switch cabinet in the distribution station has the hidden danger characteristics of excessive humidity in the station room, and the higher the station room temperature, the higher the probability of occurrence of the hidden danger characteristics, and added to the risk identification list. The probability of excessive humidity in the station building can be determined based on the probability and frequency of partial discharge anomalies and other faults caused by humidity in the historical station building. The present invention does not limit the specific method for determining the probability of excessive humidity in the station building.

[0059] Finally, early warning information for the distribution substation is generated based on the risk identification list. The early warning information includes multiple hidden danger features listed in the risk identification list and the probability of occurrence of each hidden danger feature. The early warning information can sort the hidden danger features according to the probability of occurrence of the hidden danger features, so that the operation and maintenance personnel can deal with one or more hidden danger features with the highest risk and realize early warning of the distribution substation.

[0060] Through real-time monitoring and data analysis, the present invention can discover potential hidden dangers of high-voltage switchgear in advance and generate early warning information, thereby reducing the risks of equipment failures and safety accidents; the risk identification list provides clear hidden danger characteristics and occurrence probabilities, which helps operation and maintenance personnel to quickly locate problems and take targeted measures to improve operation and maintenance efficiency; and according to the hidden danger characteristics and occurrence probabilities in the risk identification list, maintenance and replacement plans can be reasonably arranged, resource allocation can be optimized, and unnecessary waste can be avoided; by timely discovering and handling potential hidden dangers, the service life of the high-voltage switchgear can be extended and the reliability and stability of the equipment can be improved; the risk identification list and early warning information provide data support for operation and maintenance personnel and management, which helps to make more informed decisions and improve the overall management level of distribution station buildings.

[0061] In the embodiment of the present application, based on the problem of how to improve the monitoring efficiency of the distribution station, a monitoring method for the distribution station is designed, which realizes the acquisition of real-time partial discharge monitoring data and real-time environmental monitoring data of the high-voltage switchgear in the distribution station, and constructs a partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data; the partial discharge diagnosis waveform spectrum and the partial discharge diagnosis auxiliary text are input into a pre-constructed graphic and text multi-modal partial discharge classification model for processing, and a first classification result of the partial discharge type corresponding to the high-voltage switchgear is obtained; according to the partial discharge diagnosis The waveform spectrum is used to determine multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear to match them with the pre-constructed partial discharge mechanism model, and a second classification result of the partial discharge type corresponding to the high-voltage switchgear is determined according to the matching result; the target partial discharge type of the high-voltage switchgear is determined based on the first classification result and the second classification result, and the abnormal cause of the high-voltage switchgear is determined according to the target partial discharge type, so as to realize the technical solution of monitoring the distribution station; the accuracy of the partial discharge type judgment of the switchgear and the monitoring efficiency of the distribution station are improved, so as to facilitate the precise maintenance of the high-voltage switchgear.

[0062] It should be noted that although the steps in the above flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders.

[0063] In another embodiment, if Figure 3 As shown, the second aspect of the present invention provides a monitoring system for a power distribution station, comprising: The partial discharge information acquisition module 10 is used to acquire the real-time partial discharge monitoring data and the real-time environmental monitoring data of the high-voltage switchgear in the power distribution station, and to construct the partial discharge diagnosis waveform spectrum and the partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data; A first result generating module 20 is used to input the partial discharge diagnosis waveform spectrum and the partial discharge diagnosis auxiliary text into a pre-built graphic and text multi-modal partial discharge classification model for processing, so as to obtain a first classification result of the partial discharge type corresponding to the high-voltage switchgear; A second result generating module 30 is used to determine multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnostic waveform spectrum, so as to match them with the pre-constructed partial discharge mechanism model, and determine a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result; The abnormality cause determination module 40 is used to determine the target partial discharge type of the high-voltage switchgear based on the first classification result and the second classification result, and determine the abnormality cause of the high-voltage switchgear according to the target partial discharge type to realize monitoring of the distribution station.

[0064] It should be noted that each module in the above-mentioned monitoring system for a power distribution station can be fully or partially implemented by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. For the specific definition of a monitoring system for a power distribution station, please refer to the definition of a monitoring method for a power distribution station above. The two have the same functions and effects and will not be repeated here.

[0065] A third aspect of the present invention provides an electronic device, the electronic device comprising: processor, memory, and bus; The bus is used to connect the processor and the memory; The memory is used to store operation instructions; The processor is used to call the operation instruction, and the executable instruction enables the processor to perform an operation corresponding to a method for monitoring a distribution station room as shown in the first aspect of the present application.

[0066] In an alternative embodiment, an electronic device is provided, such as Figure 4 As shown, Figure 4 The electronic device 5000 shown includes: a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are connected, such as through a bus 5002. Optionally, the electronic device 5000 may also include a transceiver 5004. It should be noted that in actual applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation on the embodiments of the present application.

[0067] Processor 5001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 5001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0068] The bus 5002 may include a path to transmit information between the above components. The bus 5002 may be a PCI bus or an EISA bus, etc. The bus 5002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0069] The memory 5003 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an EEPROM, a CD-ROM or other optical disk storage, an optical disk storage (including a compressed optical disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0070] The memory 5003 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 5001. The processor 5001 is used to execute the application code stored in the memory 5003 to implement the content shown in any of the above method embodiments.

[0071] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0072] A fourth aspect of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a method for monitoring a distribution substation shown in the first aspect of the present application is implemented.

[0073] Another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0074] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0075] In summary, the present invention relates to the field of distribution station monitoring technology, and discloses a monitoring method, system, equipment and medium for distribution station buildings. A partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text are constructed through real-time partial discharge monitoring data and real-time environmental monitoring data of high-voltage switchgear in the distribution station building, and the partial discharge diagnosis waveform spectrum and the partial discharge diagnosis auxiliary text are input into a pre-constructed graphic and text multimodal partial discharge classification model for processing, so as to obtain a first classification result of the partial discharge type to which the high-voltage switchgear belongs; multiple partial discharge mechanism model characteristic values ​​of the partial discharge diagnosis waveform spectrum are determined, and matched with the pre-constructed partial discharge mechanism model, and then a second classification result is determined according to the matching result; a target partial discharge type of the high-voltage switchgear is determined based on the first and second classification results, and then the abnormal cause of the high-voltage switchgear is determined, so as to realize the monitoring of the distribution station building, improve the accuracy of the partial discharge type judgment of the switchgear and the monitoring efficiency of the distribution station building, so as to facilitate the precise maintenance of the high-voltage switchgear.

[0076] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A method for monitoring a power distribution station, characterized in that: include: Acquire real-time partial discharge monitoring data and real-time environmental monitoring data of the high-voltage switchgear in the power distribution station, and construct a partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data; Inputting the partial discharge diagnosis waveform graph and the partial discharge diagnosis auxiliary text into a pre-constructed graphic and text multi-modal partial discharge classification model for processing, to obtain a first classification result of the partial discharge type corresponding to the high-voltage switchgear; Determine multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnostic waveform spectrum to match them with a pre-constructed partial discharge mechanism model, and determine a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result; The target partial discharge type of the high-voltage switchgear is determined based on the first classification result and the second classification result, and the abnormal cause of the high-voltage switchgear is determined according to the target partial discharge type to realize monitoring of the distribution station.

2. A method for monitoring a power distribution station according to claim 1, characterized in that: The constructing of a partial discharge diagnosis waveform graph and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data includes: The partial discharge diagnostic waveform spectrum is constructed according to the real-time partial discharge monitoring data, and the mechanism characteristics of the real-time partial discharge monitoring data are extracted to obtain a plurality of partial discharge mechanism characteristic components; the partial discharge mechanism characteristic components include amplitude dispersion, phase aggregation, polarity effect, flight diagram characteristics, pulse balance, 50 Hz frequency component and 100 Hz frequency component; Quantifying the correlation between the real-time partial discharge monitoring data and the real-time environmental monitoring data, and generating a partial discharge external influencing factor according to the correlation quantification result; The partial discharge mechanism characteristic components and the partial discharge external influencing factors are subjected to data discretization and text escape processing, and the processing results are represented in a key-value pair manner to obtain the partial discharge diagnosis auxiliary text.

3. A method for monitoring a power distribution station according to claim 2, characterized in that: The real-time environmental monitoring data includes real-time temperature data and real-time humidity data; wherein, The quantifying the correlation between the real-time partial discharge monitoring data and the real-time environmental monitoring data, and generating a partial discharge external influencing factor according to the correlation quantification result, comprises: Performing Pearson correlation analysis and calculation on the real-time partial discharge monitoring data and the real-time temperature data in the same time period to obtain a partial discharge-temperature correlation coefficient; Performing Pearson correlation analysis and calculation on the real-time partial discharge monitoring data and the real-time humidity data in the same time period to obtain a partial discharge-humidity correlation coefficient; The partial discharge temperature correlation coefficient and the partial discharge humidity correlation coefficient are weighted according to a preset ratio to obtain the partial discharge external influencing factor.

4. A method for monitoring a power distribution station according to claim 1, characterized in that: The image-text multimodal partial discharge classification model includes an image encoder, a text encoder, an image-text multimodal encoder and an image-text multimodal decoder; wherein, The inputting of the partial discharge diagnosis waveform graph and the partial discharge diagnosis auxiliary text into a pre-built graphic and text multi-modal partial discharge classification model for processing to obtain a first classification result of the partial discharge type corresponding to the high-voltage switchgear includes: Encoding the partial discharge diagnosis waveform spectrum through the image encoder to obtain a partial discharge spectrum feature vector, and encoding the partial discharge diagnosis auxiliary text based on the text encoder to obtain a partial discharge text feature vector; Based on the cross-modal feature alignment loss function and the image-text matching loss function, the partial discharge spectrum feature vector and the partial discharge text feature vector are input into the image-text multimodal encoder for processing to obtain an image-text encoding result; The image-text encoding result is input into the image-text multimodal decoder for processing, and a first classification result of the partial discharge type corresponding to the high-voltage switch cabinet is output.

5. A method for monitoring a power distribution station according to claim 1, characterized in that: Determining multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnosis waveform spectrum to match with a pre-constructed partial discharge mechanism model, and determining a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result, includes: Quantifying multiple partial discharge mechanism model characteristic values ​​of the partial discharge diagnostic waveform spectrum; the partial discharge mechanism model characteristic values ​​include amplitude, number of discharges, discharge time interval, 50Hz and 100Hz frequency component comparison, positive and negative semi-axis symmetry, single peak or double peak characteristics, classification diagram, ultrasonic detection probability and PRPS characteristics; The characteristic values ​​of the multiple partial discharge mechanism models are matched with the partial discharge mechanism models corresponding to the multiple pre-constructed partial discharge types to obtain a plurality of matching degrees, and the partial discharge type corresponding to the partial discharge mechanism model with the highest matching degree is taken as the second classification result.

6. A method for monitoring a power distribution station according to claim 5, characterized in that: The first classification result includes the partial discharge type and its corresponding probability value; The determining a target partial discharge type of the high-voltage switchgear based on the first classification result and the second classification result includes: Determine a first weight value of the first classification result according to the probability value, and determine a second weight value of the second classification result based on the matching degree; The first weight value and the second weight value are normalized to obtain a normalized weight value, and a target partial discharge type of the high-voltage switchgear is determined according to the normalized weight value, the first classification result, and the second classification result.

7. A method for monitoring a power distribution station according to claim 1, characterized in that: After determining the abnormal cause of the high-voltage switchgear according to the target partial discharge type, the method further includes: Constructing a hidden danger feature set of the high-voltage switch cabinet; the hidden danger feature set includes excessive humidity in the station room, equipment aging and family defects; Acquire equipment information of the high-voltage switch cabinet, and when it is determined that the high-voltage switch cabinet meets the hidden danger feature set according to the equipment information and the real-time environmental monitoring data, determine the occurrence probability of each hidden danger feature to generate a risk identification list; Early warning information of the power distribution station is generated according to the risk identification list to achieve early warning of the power distribution station.

8. A monitoring system for a power distribution station, characterized in that: include: A partial discharge information acquisition module is used to acquire real-time partial discharge monitoring data and real-time environmental monitoring data of the high-voltage switchgear in the power distribution station, and to construct a partial discharge diagnosis waveform spectrum and a partial discharge diagnosis auxiliary text according to the real-time partial discharge monitoring data and the real-time environmental monitoring data; A first result generating module is used to input the partial discharge diagnosis waveform spectrum and the partial discharge diagnosis auxiliary text into a pre-built graphic and text multi-modal partial discharge classification model for processing, so as to obtain a first classification result of the partial discharge type corresponding to the high-voltage switchgear; A second result generating module is used to determine multiple partial discharge mechanism model characteristic values ​​of the high-voltage switchgear according to the partial discharge diagnostic waveform spectrum, so as to match them with a pre-constructed partial discharge mechanism model, and determine a second classification result of the partial discharge type corresponding to the high-voltage switchgear according to the matching result; An abnormality cause determination module is used to determine a target partial discharge type of the high-voltage switchgear based on the first classification result and the second classification result, and determine the abnormality cause of the high-voltage switchgear according to the target partial discharge type to realize monitoring of the distribution station.

9. An electronic device, characterized in that: The system comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for monitoring a power distribution station according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the method for monitoring a power distribution station according to any one of claims 1 to 7 is implemented.

Images