Handheld partial discharge inspection device and method

Abstract

The invention relates to a handheld partial discharge inspection device and method, and relates to the technical field of electrical equipment insulation defect fault diagnosis, and the method comprises the steps: detecting current environmental data, inputting the environmental data into an environmental partial discharge model, and obtaining the severity levels of different basin-type insulator groups of GIS equipment under different environmental conditions; acquiring a partial discharge position of the GIS equipment; sorting the partial discharge positions from high to low according to the severity levels of the partial discharge under the same environment data, and generating an inspection position sequence; and planning a partial discharge inspection route of the GIS equipment according to the inspection position sequence. According to the method, the partial discharge position of the GIS equipment can be obtained, and meanwhile, the position where partial discharge occurs more easily in the GIS equipment can be detected preferentially, so that faults caused by partial discharge due to the fact that maintenance is not carried out in time are reduced.

Description

Technical Field

[0001] The present application relates to the technical field of insulation defect fault diagnosis of power equipment, and in particular to a handheld partial discharge inspection device and method. Background Art

[0002] The pot insulator of GIS is a key insulating component in GIS, and its operating status directly affects the reliability and safety of the entire GIS equipment. Due to its structural characteristics, the pot insulator is prone to become a high-incidence part of GIS insulation breakdown failure. During the manufacturing and operation of GIS, local defects such as internal bubbles, internal cracks, surface dirt, surface metal particles, and surface scratches may occur. These defects may cause partial discharge under the action of power frequency operating voltage. Long-term partial discharge may lead to further development and expansion of defects, and may eventually develop into insulation breakdown accidents. Therefore, it is very necessary to inspect the local discharge of the pot insulator of GIS.

[0003] At present, the existing partial discharge detection obtains the dynamic process of partial discharge by real-time monitoring of the state of ultra-high frequency signals, and then obtains the location of partial discharge. The staff performs maintenance according to the location of partial discharge.

[0004] However, if long-term partial discharge inspections of GIS equipment are required, it is necessary to travel back and forth to several locations where partial discharges may occur for inspections. Therefore, a handheld partial discharge inspection device and method is needed, which can not only locate the partial discharge position of GIS equipment when partial discharge occurs, but also continuously plan inspection routes according to the location of partial discharge, so as to give priority to inspecting locations where partial discharges are more likely to occur, thereby reducing the occurrence of faults. Summary of the invention

[0005] The first purpose of this application is to provide a handheld partial discharge inspection method, which can not only obtain the partial discharge location of GIS equipment, but also give priority to detecting the locations in GIS equipment where partial discharge is more likely to occur, thereby reducing faults caused by partial discharge due to untimely maintenance.

[0006] In the first aspect, the present application provides a handheld partial discharge inspection method, which adopts the following technical solution: A handheld partial discharge inspection method, comprising: Detect current environmental data, input the environmental data into an environmental partial discharge model, and obtain severity levels of different pot-type insulator groups of GIS equipment under different environmental conditions; Obtain the partial discharge location of GIS equipment; According to the severity level of partial discharge under the same environmental data, the partial discharge locations are sorted from high to low to generate an inspection location sequence; According to the inspection position sequence, a partial discharge inspection route of the GIS equipment is planned.

[0007] By adopting the above technical solution, since the environmental factors in which the GIS equipment is located will affect the partial discharge of the GIS equipment, the severity of the partial discharge of the GIS equipment under the environmental data currently detected can be obtained, and then the locations that are more prone to partial discharge are prioritized for detection based on the severity level, thereby improving the inspection efficiency and fault prevention capabilities, and reducing faults caused by untimely maintenance.

[0008] In a preferred example, the present application may be further configured as follows: before the step of detecting the current environmental data, inputting the environmental data into the environmental partial discharge model, and obtaining the severity levels of different pot-type insulator groups of the GIS equipment under different environmental conditions, the generation of the environmental partial discharge model includes: Acquire historical partial discharge data of the GIS equipment, wherein the historical partial discharge data includes a PRPD spectrum data set and a PRPS spectrum data set of ultra-high frequency signals emitted by the GIS equipment; The historical partial discharge data and environmental data are trained to generate an environmental partial discharge model.

[0009] By adopting the above technical solution and using the PRPD spectrum dataset and PRPS spectrum dataset of UHF signals, an environmental partial discharge model is generated, which can learn the relationship between environmental conditions and partial discharge events, thereby predicting the tendency and severity of partial discharge under different environmental conditions.

[0010] In a preferred example, the present application may be further configured as follows: the step of training the historical partial discharge data and the environmental data to generate an environmental partial discharge model includes: Clean historical partial discharge data; Extracting partial discharge characteristics when partial discharge occurs from historical partial discharge data after cleaning; Generate a partial discharge feature matrix according to the partial discharge feature and the environmental data, wherein each row of the partial discharge feature matrix represents a UHF signal sample under different environmental data, and each column corresponds to a partial discharge feature; According to the partial discharge characteristics, setting a severity level label corresponding to the partial discharge characteristic matrix; The environmental partial discharge model is generated by training the partial discharge feature matrix and severity level labels.

[0011] By adopting the above technical solution, after steps such as data cleaning, feature extraction, environmental data fusion, severity level label setting and model training, the precise positioning of the partial discharge position of GIS equipment and the priority detection of high-risk areas are achieved, which helps to improve the fault prevention capability of GIS equipment and the efficiency of partial discharge inspection.

[0012] In a preferred example, the present application may be further configured as follows: the step of setting a severity level label corresponding to the partial discharge feature matrix according to the partial discharge feature comprises: Performing Gaussian smoothing filtering on the ultra-high frequency signal to obtain the envelope of the ultra-high frequency signal; Obtain characteristic parameters of the rising steepness of the oscillation characteristics and the cumulative energy function in the envelope; Using a machine learning algorithm, the oscillation characteristics and characteristic parameters of the rising steepness of the cumulative energy function are used to classify different types of partial discharge modes to obtain partial discharge types; According to the scrap rate of GIS equipment detected in history, the severity level of different partial discharge types is confirmed; According to the severity levels and the partial discharge features of different partial discharge types detected historically, a severity level label corresponding to the partial discharge feature matrix is ​​set.

[0013] By adopting the above technical solution, the UHF signal is subjected to Gaussian smoothing filtering, which can effectively remove high-frequency noise in the signal, retain the main features of the UHF signal, and improve the accuracy and reliability of subsequent feature extraction. The oscillation characteristics and the rising steepness characteristic parameters of the cumulative energy function can reflect the intensity, frequency and energy changes of the local discharge event, confirm the local discharge type, and provide a quantitative evaluation for the confirmation of the severity of the local discharge event.

[0014] In a preferred example, the present application may be further configured as follows: the step of obtaining historical partial discharge data of GIS equipment, wherein the historical partial discharge data includes a PRPD spectrum data set and a PRPS spectrum data set of a UHF signal emitted by the GIS equipment, comprises: Extract the amplitude, frequency and phase angle of the UHF signal from the historically detected PRPD spectrum data set, and obtain the changing relationship between the amplitude and frequency of the UHF signal and the phase angle; Extract the peak value, phase angle and time of partial discharge pulse of UHF signal from the PRPS spectrum data set of historical detection, and obtain the change relationship of UHF signal peak value and phase angle with time; Calculate the partial discharge characteristics of the UHF signal according to the variation relationship between the UHF signal amplitude and frequency with respect to the phase angle and the variation relationship between the peak value and the phase angle with respect to time, and analyze the correlation between the two variation relationships and the partial discharge characteristics; According to the two variation relationships, partial discharge characteristics and correlation, cluster analysis is performed on the ultra-high frequency signals under different environmental data to obtain historical partial discharge data under different environmental data.

[0015] By adopting the above technical solutions, the PRPD spectrum data set can show the phase distribution characteristics of the local discharge signal over a period of time, and the PRPS spectrum data set can show the continuous change characteristics and intensity changes of the local discharge signal over a period of time. The analysis based on the correlation between the two change relationships and the local discharge characteristics is helpful to identify which features are most influential in the prediction of local discharge events, and then identify the patterns and trends of local discharge events under different environmental conditions, providing a basis for predicting high-risk locations of local discharge in GIS equipment.

[0016] In a preferred example, the present application may be further configured as follows: the step of planning a partial discharge inspection route for GIS equipment according to the inspection position sequence includes: Constructing a graph model, wherein nodes in the graph model are set according to the priorities of the partial discharge positions in the inspection position sequence; The graph model is used through a minimum path algorithm to plan a partial discharge inspection route for GIS equipment.

[0017] By adopting the above technical solution, the inspection route can prioritize high-risk areas, improve the targetedness and efficiency of the inspection, and reduce inspection time and cost.

[0018] In a preferred example, the present application may be further configured as follows: the step of obtaining the partial discharge position of the GIS equipment includes: Performing Hilbert transform processing on the ultra-high frequency signal to obtain an envelope of the ultra-high frequency signal; identifying characteristic points of the envelope corresponding to partial discharge events; The partial discharge position of the pot-type insulator group is calculated based on the time difference between two adjacent characteristic points.

[0019] By adopting the above technical solution, the characteristic points on the envelope line can be identified, which can provide an accurate timestamp of the local discharge event. Then, based on the time difference between two adjacent characteristic points, the local discharge position of the pot-type insulator group can be calculated to achieve high-precision localization of the local discharge position and improve the accuracy of local discharge fault detection.

[0020] In a second aspect, the present application provides a handheld partial discharge inspection device, which adopts the following technical solution: A handheld partial discharge inspection device, comprising: Severity level acquisition module: used to detect current environmental data, input the environmental data into the environmental partial discharge model, and obtain the severity levels of different pot-type insulator groups of GIS equipment under different environmental conditions; Position acquisition module: used to obtain the partial discharge position of GIS equipment; Inspection position sequence generation module: used to sort the partial discharge positions from high to low according to the severity level of partial discharge under the same environmental data, and generate an inspection position sequence; Inspection route planning module: used to plan the partial discharge inspection route of GIS equipment according to the inspection position sequence.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned handheld partial discharge inspection method are implemented.

[0022] In a fourth aspect, the present application provides a computer storage medium, the following technical solution: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned handheld partial discharge inspection method are implemented.

[0023] In summary, this application has the following beneficial technical effects: In this application, when GIS equipment is susceptible to the influence of the environmental conditions in which it is located, the severity of the local discharge phenomenon will change differently. Through real-time monitoring of environmental parameters, the environmental local discharge model is used to evaluate the severity of local discharge of different pot-type insulator groups, determine the locations with higher local discharge severity levels, and give priority to the inspection of high-risk areas, thereby improving the efficiency of inspection work and the ability to prevent faults, reducing equipment failures caused by local discharge, and improving the overall operating safety and reliability of GIS equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of a handheld partial discharge inspection method in one embodiment of the present application.

[0025] Figure 2 It is a flow chart of the steps of generating an environmental partial discharge model in one embodiment of the present application.

[0026] Figure 3 It is a sub-step flow chart of step S11 in one embodiment of the present application.

[0027] Figure 4It is a sub-step flow chart of step S113 in one embodiment of the present application.

[0028] Figure 5 It is a sub-step flow chart of step S10 in one embodiment of the present application.

[0029] Figure 6 It is a sub-step flow chart of step S4 in one embodiment of the present application.

[0030] Figure 7 It is a sub-step flow chart of step S2 in one embodiment of the present application.

[0031] Figure 8 It is a structural schematic diagram of a handheld partial discharge inspection device according to one embodiment of the present application.

[0032] Fig. 9 It is a principle block diagram of an electronic device in one embodiment of the present application.

[0033] Figure numerals: 1. Severity level acquisition module; 2. Location acquisition module; 3. Inspection location sequence generation module; 4. Inspection route planning module. DETAILED DESCRIPTION

[0034] The following is combined with Figure 1-9 This application is described in further detail.

[0035] refer to Figure 1 , a handheld partial discharge inspection method, specifically comprising: S1. Detect the current environmental data, input the environmental data into the environmental partial discharge model, and obtain the severity levels of different pot-type insulator groups of GIS equipment under different environmental conditions.

[0036] The environmental data of the GIS equipment is collected through sensors or monitoring equipment, including temperature, humidity, and air pressure. The environmental data is then input into a pre-trained environmental partial discharge model. The environmental partial discharge model is based on historical data and machine learning algorithms, and can predict the severity of partial discharge of different pot-type insulator groups under specific environmental conditions.

[0037] S2. Obtain the partial discharge position of the GIS equipment.

[0038] In this embodiment, UHF detection is used to perform partial discharge detection on the UHF signal emitted by the pot-type insulator group in the GIS equipment, thereby determining the specific location of the partial discharge. Specifically, two identical UHF sensors are used to collect and detect the electromagnetic wave signals of adjacent pot-type insulators. When there is partial discharge inside the GIS equipment, the two UHF sensors can detect the UHF signal, and then transmit the UHF signal to the intelligent positioning terminal respectively. The intelligent positioning terminal performs time difference analysis on the two different UHF signals to obtain the partial discharge location of the GIS equipment.

[0039] S3. Sort the partial discharge locations from high to low according to the severity level of the partial discharge under the same environmental data, and generate an inspection location sequence.

[0040] Among them, all locations that need to be inspected are sorted in order from high to low severity of partial discharge, generating an optimized inspection location sequence to ensure that the inspection work can give priority to the equipment with the highest risk, effectively allocate inspection resources, and thus improve the efficiency of partial discharge inspection and the timeliness of fault handling.

[0041] S4. Plan the partial discharge inspection route of GIS equipment according to the inspection position sequence.

[0042] In this embodiment, since the environmental factors in which the GIS equipment is located will affect the occurrence of partial discharge in the GIS equipment, the currently detected environmental data, that is, the real-time monitored temperature, humidity, and air pressure, are input into the environmental partial discharge model. The environmental partial discharge model can obtain the severity of partial discharge of the GIS equipment under the environmental data, and then prioritize the detection of locations that are more prone to partial discharge based on the severity level. This is convenient for operation and maintenance personnel to use a handheld partial discharge inspection device to start inspection from the discharge location with the highest severity, then to the discharge location with the second highest severity, and so on, and finally to the discharge location with the lowest severity, so as to realize timely inspection of discharge locations with higher severity, reduce failures caused by failure to timely repair partial discharge problems, and improve the efficiency of partial discharge inspection and fault prevention capabilities.

[0043] refer to Figure 2 Further, in one embodiment, before step S1, the generation of the environmental partial discharge model includes: S10. Acquire historical partial discharge data of the GIS equipment, where the historical partial discharge data includes a PRPD spectrum data set and a PRPS spectrum data set of ultra-high frequency signals emitted by the GIS equipment.

[0044] Among them, the PRPD spectrum dataset records the relationship between local discharge events and the phase of the power system, while the PRPS spectrum dataset provides the phase distribution information of the local discharge pulse sequence. The PRPD spectrum dataset and the PRPS spectrum dataset contain rich local discharge features and are the basis for training environmental local discharge models.

[0045] S11. Train historical partial discharge data and environmental data to generate an environmental partial discharge model.

[0046] Among them, by combining historical partial discharge data with the temperature, humidity, and air pressure of the environment where the GIS equipment is located as a training data set, these data are trained using machine learning or deep learning algorithms, such as support vector machines and neural networks, to establish an environmental partial discharge model. The environmental partial discharge model obtained through training can predict the severity of partial discharge in GIS equipment based on current environmental conditions.

[0047] In this embodiment, a PRPD spectrum data set and a PRPS spectrum data set associated with UHF signals are used to generate an environmental partial discharge model. The environmental partial discharge model learns the relationship between environmental conditions and partial discharge events based on historical local amplification data, thereby predicting the tendency and severity of partial discharge under different environmental conditions, and providing reference nodes for planning inspection routes.

[0048] In addition, reference Figure 3 Further, in one embodiment, step S11 is refined into the following sub-steps: S110, cleaning historical partial discharge data.

[0049] Among them, the collected historical partial discharge data are preprocessed, including but not limited to signal denoising, data smoothing, and outlier detection and elimination, to reduce the interference of noise and outliers on model training.

[0050] S111, extracting partial discharge characteristics when partial discharge occurs from historical partial discharge data after cleaning.

[0051] Among them, the characteristics of local discharge events are extracted from the cleaned data using signal processing techniques, such as wavelet transform and Fourier transform, which can more accurately describe the characteristics of local discharge events, provide richer information for generating environmental local discharge models, and help improve the model's ability to predict the severity of local discharge.

[0052] S112. Generate a partial discharge feature matrix according to the partial discharge feature and the environmental data, wherein each row of the partial discharge feature matrix represents a UHF signal sample under different environmental data, and each column corresponds to a partial discharge feature.

[0053] S113. According to the partial discharge characteristics, a severity level label corresponding to the partial discharge characteristic matrix is ​​set.

[0054] Among them, the severity level label provides supervision information for the model, so that the environmental partial discharge model can learn the relationship between partial discharge characteristics and severity levels, and thus has the ability to predict the severity level of new samples.

[0055] S114. Train the partial discharge feature matrix and severity level labels to generate an environmental partial discharge model.

[0056] Specifically, characteristic parameters, i.e., UHF signal samples, are collected. UHF signal samples refer to data sets used to train models, including structured data on the relationship between the change in amplitude and frequency of UHF signals in the PRPD spectrum data set and the change in phase angle under different humidity, temperature, and air pressure conditions, and structured data on the relationship between the change in peak value and phase angle over time in the PRPS spectrum data set. After obtaining the data in the data set, the extracted data is cleaned and normalized, and the structured data on the relationship between the change in amplitude and frequency of UHF signals in the PRPD spectrum data set and the change in peak value and phase angle over time in the PRPS spectrum data set are continuously trained as local discharge features. The local discharge type is obtained through the local discharge feature, and a severity level is set for each local discharge type.

[0057] In this embodiment, the trained environmental partial discharge model can predict the severity level of partial discharge of each group of pot-type insulators according to the input partial discharge characteristics and environmental data, thereby achieving priority detection of areas with higher severity, which helps to improve the fault prevention capability of GIS equipment and the efficiency of partial discharge inspection.

[0058] In addition, reference Figure 4 Further, in one embodiment, step S113 is further divided into the following sub-steps: S1130 , performing Gaussian smoothing filtering on the UHF signal to obtain an envelope of the UHF signal.

[0059] Among them, the Gaussian filter uses the Gaussian function as a weight through convolution operation to smooth the UHF signal. The envelope of the obtained UHF signal can more clearly reflect the oscillation characteristics and energy distribution of the signal.

[0060] S1131. Obtain characteristic parameters of the oscillation characteristics and the rising steepness of the cumulative energy function in the envelope.

[0061] Among them, the cumulative energy function describes the change of signal energy accumulation over time, and the rising steepness reflects the rate of energy accumulation. It can provide dynamic information about partial discharge events and help distinguish different types of partial discharge modes.

[0062] S1132. Using a machine learning algorithm, the characteristic parameters of the oscillation characteristics and the rising steepness of the cumulative energy function are used to classify different types of local discharge modes and obtain the local discharge type.

[0063] Among them, machine learning algorithms such as support vector machines, decision trees, neural networks, etc. are used to train and classify partial discharge patterns in historical data with characteristic parameters of oscillation characteristics and the steepness of the cumulative energy function as input. The trained environmental partial discharge model can learn the association between different partial discharge types and characteristic parameters, thereby realizing the classification of new samples.

[0064] S1133. Determine the severity levels of different types of partial discharge based on the scrap rate of GIS equipment tested historically.

[0065] Among them, partial discharge types include internal discharge, surface discharge, power supply discharge, suspended discharge, etc. By analyzing historical detection data, the relationship between different partial discharge types and GIS equipment scrapping rates is statistically analyzed, and then based on the scrapping rate, a severity level is set for each partial discharge type. The higher the scrapping rate, the higher the severity level.

[0066] S1134. According to severity levels and partial discharge features of different partial discharge types detected historically, set severity level labels corresponding to the partial discharge feature matrix.

[0067] In this embodiment, Gaussian smoothing filtering technology is applied to process the UHF signal collected by the UHF sensor, which can effectively remove the high-frequency noise in the signal, but retain the main features of the UHF signal, improve the accuracy and reliability of subsequent feature extraction, and the oscillation characteristics and the rising steepness characteristic parameters of the cumulative energy function can reflect the intensity, frequency and energy changes of the local discharge event, and then confirm the type of local discharge, providing a quantitative basis for evaluating the severity of the local discharge event.

[0068] In addition, reference Figure 5 Further, in one embodiment, step S10 is refined into the following sub-steps: S100, extracting the amplitude, frequency and phase angle of the UHF signal from the historically detected PRPD spectrum data set, and obtaining the variation relationship between the amplitude and frequency of the UHF signal and the phase angle.

[0069] Among them, the PRPD spectrum data set can show the phase distribution characteristics of the local discharge signal over a period of time. A high amplitude indicates that the energy of the local discharge is large, and a high frequency indicates that the number of discharge events per unit time is large, indicating that the severity of the local discharge is high.

[0070] S101, extracting the peak value, phase angle and time of the partial discharge pulse of the UHF signal from the PRPS spectrum data set of historical detection, and obtaining the relationship between the change of the peak value and phase angle of the UHF signal with respect to time.

[0071] Among them, the PRPS spectrum data set can show the continuous change characteristics and intensity changes of the local discharge signal over a period of time. The high peak value may indicate that the energy of the discharge event is large, while the change in the phase angle can reveal the timing of the discharge event within the voltage cycle.

[0072] S102, calculating the partial discharge characteristics of the UHF signal according to the variation relationship between the UHF signal amplitude and frequency with respect to the phase angle and the variation relationship between the peak value and the phase angle with respect to time, and analyzing the correlation between the two variation relationships and the partial discharge characteristics.

[0073] S103, performing cluster analysis on the UHF signals under different environmental data according to the two change relationships, the partial discharge characteristics and the correlation, and obtaining historical partial discharge data under different environmental data.

[0074] In this embodiment, the analysis is based on the correlation between the two change relationships and the local discharge characteristics, which helps the environmental local discharge model to identify the local discharge characteristics that are most influential in the prediction of local discharge events, and then identify the patterns and trends of local discharge events under different environmental conditions, providing a basis for predicting high-risk locations of local discharge in GIS equipment according to the severity.

[0075] In addition, reference Figure 6 Further, in one embodiment, step S4 is refined into the following sub-steps: S40: construct a graph model, and set the nodes in the graph model according to the priorities of the partial discharge positions in the inspection position sequence.

[0076] Among them, the nodes of the graph model are created according to the partial discharge locations recorded in the inspection location sequence. Each node represents a partial discharge location, and the weight or attribute of the node is set according to the priority of the severity of the partial discharge location. The higher the severity, the higher the weight or attribute of the node.

[0077] S41. Plan the local discharge inspection route of GIS equipment through the graph model through the minimum path algorithm.

[0078] Among them, a minimum path algorithm, such as Dijkstra algorithm, A* algorithm, etc., is used to find the shortest path from the starting point to all partial discharge location nodes in the graph model. The algorithm considers the connection weights between nodes to minimize the total movement cost.

[0079] In this embodiment, the generated inspection route will cover as many high-priority partial discharge locations as possible within a limited time based on a comprehensive consideration of priority and mobility cost, so that the inspection route can preferentially locate high-risk areas with higher severity. Operation and maintenance personnel conduct inspections according to the inspection route, which improves the targetedness and efficiency of the inspection and reduces the inspection time and cost.

[0080] In addition, reference Figure 7 Further, in one embodiment, step S2 is refined into the following sub-steps: S20, performing Hilbert transform processing on the UHF signal to obtain an envelope of the UHF signal.

[0081] Among them, the Hilbert transform converts the real signal into a complex signal by calculating the analytical signal of the signal, thereby obtaining the envelope of the signal. Therefore, the Hilbert transform is applied to process the UHF signal, which can extract the instantaneous amplitude of the signal, that is, the envelope, and thus clearly reflect the oscillation characteristics and energy distribution of the UHF signal.

[0082] S21. Identify characteristic points of the envelope corresponding to partial discharge events.

[0083] Among them, through threshold detection, peak detection and other methods, characteristic points related to local discharge events are identified, which are usually manifested as peaks or mutation points on the envelope line, and can indicate the occurrence of local discharge events.

[0084] S22. Calculate the local discharge position of the pot-type insulator group according to the time difference between two adjacent characteristic points.

[0085] The time difference between adjacent feature points is calculated using the identified feature points. Based on the time difference and the known signal propagation speed, the distance of the partial discharge event relative to the two UHF sensors can be calculated. The specific location of the partial discharge event can be calculated by multi-point positioning techniques, such as triangulation or multilateral positioning, combined with the geometric structure of the pot insulator group.

[0086] In this embodiment, the characteristic points on the envelope line are identified to provide an accurate timestamp of the local discharge event. The local discharge position of the basin insulator group is then calculated based on the time difference between two adjacent characteristic points, thereby achieving high-precision localization of the local discharge position, providing specific location information for maintenance and troubleshooting of GIS equipment, and improving the efficiency of local discharge inspections.

[0087] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0088] The embodiment of the present application also provides a handheld partial discharge inspection device, which corresponds one-to-one to the handheld partial discharge inspection method in the embodiment.

[0089] refer to Figure 8 A handheld partial discharge inspection device includes: a severity level acquisition module 1, a position acquisition module 2, an inspection position sequence generation module 3, and an inspection route planning module 4. The functional modules are described in detail as follows: Severity level acquisition module 1: used to detect current environmental data, input the environmental data into the environmental partial discharge model, and obtain the severity levels of different pot-type insulator groups of GIS equipment under different environmental conditions.

[0090] Position acquisition module 2: used to obtain the partial discharge position of GIS equipment.

[0091] Inspection position sequence generation module 3: used to sort the partial discharge positions from high to low according to the severity level of partial discharge under the same environmental data, and generate an inspection position sequence.

[0092] Inspection route planning module 4: used to plan the partial discharge inspection route of GIS equipment according to the inspection position sequence.

[0093] Among them, after detecting the current environmental data, the severity level acquisition module 1 can obtain the severity level of the discharge position detected by the GIS equipment in history through the environmental local model, and then locate the local discharge position of the GIS equipment through the position acquisition module 2. The inspection position sequence generation module 3 sets the discharge position that is more likely to have serious consequences to a higher priority according to the severity level of each discharge position, so that the operation and maintenance personnel can go to the high-risk discharge position for inspection in time, and finally the inspection route planning module 4 plans the inspection route for multiple discharge positions according to the inspection position sequence. Through the combination of various modules, it is possible to obtain the local discharge position of the GIS equipment while predicting the position in the GIS equipment that is more prone to local discharge, and to conduct maintenance at the position where local discharge is more likely to occur, thereby reducing the failure caused by local discharge due to untimely maintenance.

[0094] For the specific definition of the handheld partial discharge inspection device, please refer to the definition of the handheld partial discharge inspection method in the context, which will not be repeated here. Each module in the above-mentioned handheld partial discharge inspection device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. In one embodiment, an electronic device is provided, which is a user terminal. Reference Fig. 9 The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a detection data table. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a handheld partial discharge inspection method is implemented.

[0095] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: S1. Detect the current environmental data, input the environmental data into the environmental partial discharge model, and obtain the severity levels of different pot-type insulator groups of GIS equipment under different environmental conditions.

[0096] S2. Obtain the partial discharge position of the GIS equipment.

[0097] S3. Sort the partial discharge locations from high to low according to the severity level of the partial discharge under the same environmental data, and generate an inspection location sequence.

[0098] S4. Plan the partial discharge inspection route of GIS equipment according to the inspection position sequence.

[0099] In one embodiment, before step S4, the generation of the environmental partial discharge model includes: S10. Acquire historical partial discharge data of the GIS equipment, where the historical partial discharge data includes a PRPD spectrum data set and a PRPS spectrum data set of ultra-high frequency signals emitted by the GIS equipment.

[0100] S11. Train historical partial discharge data and environmental data to generate an environmental partial discharge model.

[0101] In one embodiment, the detailed sub-steps of step S11 include: S110, cleaning historical partial discharge data.

[0102] S111, extracting partial discharge characteristics when partial discharge occurs from historical partial discharge data after cleaning.

[0103] S112. Generate a partial discharge feature matrix according to the partial discharge feature and the environmental data, wherein each row of the partial discharge feature matrix represents a UHF signal sample under different environmental data, and each column corresponds to a partial discharge feature.

[0104] S113. According to the partial discharge characteristics, a severity level label corresponding to the partial discharge characteristic matrix is ​​set.

[0105] S114. Train the partial discharge feature matrix and severity level labels to generate an environmental partial discharge model.

[0106] In one embodiment, the detailed sub-steps of step S113 include: S1130 , performing Gaussian smoothing filtering on the UHF signal to obtain an envelope of the UHF signal.

[0107] S1131. Obtain characteristic parameters of the oscillation characteristics and the rising steepness of the cumulative energy function in the envelope.

[0108] S1132. Using a machine learning algorithm, the characteristic parameters of the oscillation characteristics and the rising steepness of the cumulative energy function are used to classify different types of local discharge modes and obtain the local discharge type.

[0109] S1133. Determine the severity levels of different types of partial discharge based on the scrap rate of GIS equipment tested historically.

[0110] S1134. According to severity levels and partial discharge features of different partial discharge types detected historically, set severity level labels corresponding to the partial discharge feature matrix.

[0111] In one embodiment, the detailed sub-steps of step S10 include: S100, extracting the amplitude, frequency and phase angle of the UHF signal from the historically detected PRPD spectrum data set, and obtaining the variation relationship between the amplitude and frequency of the UHF signal and the phase angle.

[0112] S101, extracting the peak value, phase angle and time of the partial discharge pulse of the UHF signal from the PRPS spectrum data set of historical detection, and obtaining the relationship between the change of the peak value and phase angle of the UHF signal with respect to time.

[0113] S102, calculating the partial discharge characteristics of the UHF signal according to the variation relationship between the UHF signal amplitude and frequency with respect to the phase angle and the variation relationship between the peak value and the phase angle with respect to time, and analyzing the correlation between the two variation relationships and the partial discharge characteristics.

[0114] S103, performing cluster analysis on the UHF signals under different environmental data according to the two change relationships, the partial discharge characteristics and the correlation, and obtaining historical partial discharge data under different environmental data.

[0115] In one embodiment, the sub-steps of step S4 include: S40: construct a graph model, and set the nodes in the graph model according to the priorities of the partial discharge positions in the inspection position sequence.

[0116] S41. Plan the local discharge inspection route of GIS equipment through the graph model through the minimum path algorithm.

[0117] In one embodiment, the sub-steps of step S2 include: S20, performing Hilbert transform processing on the UHF signal to obtain an envelope of the UHF signal.

[0118] S21. Identify characteristic points of the envelope corresponding to partial discharge events.

[0119] S22. Calculate the local discharge position of the pot-type insulator group according to the time difference between two adjacent characteristic points.

[0120] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0121] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A handheld partial discharge inspection method, characterized in that: include: Detect current environmental data, input the environmental data into an environmental partial discharge model, and obtain severity levels of different pot-type insulator groups of GIS equipment under different environmental conditions; Obtain the partial discharge location of GIS equipment; According to the severity level of partial discharge under the same environmental data, the partial discharge locations are sorted from high to low to generate an inspection location sequence; According to the inspection position sequence, a partial discharge inspection route of the GIS equipment is planned.

2. The method according to claim 1, characterized in that Before the step of detecting the current environmental data, inputting the environmental data into the environmental partial discharge model, and obtaining the severity levels of different pot-type insulator groups of the GIS equipment under different environmental conditions, the generation of the environmental partial discharge model includes: Acquire historical partial discharge data of the GIS equipment, wherein the historical partial discharge data includes a PRPD spectrum data set and a PRPS spectrum data set of ultra-high frequency signals emitted by the GIS equipment; The historical partial discharge data and environmental data are trained to generate an environmental partial discharge model.

3. The method according to claim 2, characterized in that The step of training the historical partial discharge data and environmental data to generate an environmental partial discharge model also includes: Clean historical partial discharge data; Extracting partial discharge characteristics when partial discharge occurs from historical partial discharge data after cleaning; Generate a partial discharge feature matrix according to the partial discharge feature and the environmental data, wherein each row of the partial discharge feature matrix represents a UHF signal sample under different environmental data, and each column corresponds to a partial discharge feature; According to the partial discharge characteristics, setting a severity level label corresponding to the partial discharge characteristic matrix; The environmental partial discharge model is generated by training the partial discharge feature matrix and severity level labels.

4. The method according to claim 3, characterized in that The step of setting a severity level label corresponding to a partial discharge feature matrix according to the partial discharge feature comprises: Performing Gaussian smoothing filtering on the ultra-high frequency signal to obtain the envelope of the ultra-high frequency signal; Obtain characteristic parameters of the rising steepness of the oscillation characteristics and the cumulative energy function in the envelope; Using a machine learning algorithm, the oscillation characteristics and characteristic parameters of the rising steepness of the cumulative energy function are used to classify different types of partial discharge modes to obtain partial discharge types; According to the scrap rate of GIS equipment detected in history, the severity level of different partial discharge types is confirmed; According to the severity levels and the partial discharge features of different partial discharge types detected historically, a severity level label corresponding to the partial discharge feature matrix is ​​set.

5. The method according to claim 2, characterized in that: The step of obtaining historical partial discharge data of the GIS equipment, wherein the historical partial discharge data includes a PRPD spectrum data set and a PRPS spectrum data set of a UHF signal emitted by the GIS equipment, comprises: Extract the amplitude, frequency and phase angle of the UHF signal from the historically detected PRPD spectrum data set, and obtain the changing relationship between the amplitude and frequency of the UHF signal and the phase angle; Extract the peak value, phase angle and time of partial discharge pulse of UHF signal from the PRPS spectrum data set of historical detection, and obtain the relationship between the peak value and phase angle of UHF signal and time; Calculate the partial discharge characteristics of the UHF signal according to the variation relationship between the UHF signal amplitude and frequency with respect to the phase angle and the variation relationship between the peak value and the phase angle with respect to time, and analyze the correlation between the two variation relationships and the partial discharge characteristics; According to the two variation relationships, partial discharge characteristics and correlation, cluster analysis is performed on the ultra-high frequency signals under different environmental data to obtain historical partial discharge data under different environmental data.

6. The method according to claim 1, characterized in that The step of planning a partial discharge inspection route for GIS equipment according to the inspection position sequence comprises: Constructing a graph model, wherein nodes in the graph model are set according to the priorities of the partial discharge positions in the inspection position sequence; The graph model is used through a minimum path algorithm to plan a partial discharge inspection route for GIS equipment.

7. The method according to claim 1, characterized in that The step of obtaining the partial discharge position of the GIS equipment includes: Performing Hilbert transform processing on the ultra-high frequency signal to obtain an envelope of the ultra-high frequency signal; identifying characteristic points of the envelope corresponding to partial discharge events; The partial discharge position of the pot-type insulator group is calculated based on the time difference between two adjacent characteristic points.

8. A handheld partial discharge inspection device, characterized in that: include: Severity level acquisition module (1): used to detect current environmental data, input the environmental data into the environmental partial discharge model, and obtain the severity levels of different pot-type insulator groups of GIS equipment under different environmental conditions; Position acquisition module (2): used to obtain the local discharge position of GIS equipment; Inspection position sequence generation module (3): used to sort the partial discharge positions from high to low according to the severity level of partial discharge under the same environmental data, and generate an inspection position sequence; Inspection route planning module (4): used to plan the partial discharge inspection route of the GIS equipment according to the inspection position sequence.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes the handheld partial discharge inspection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer program is stored and can be loaded by a processor to execute the handheld partial discharge inspection method according to any one of claims 1 to 7.

Images