Partial discharge identification method and system based on phase deviation

Abstract

The invention discloses a partial discharge identification method and system based on phase deviation, and relates to the technical field of data processing. The method comprises the following steps: acquiring partial discharge signals of a plurality of equipment monitoring points in target electrical equipment; performing phase synchronization on each partial discharge signal to obtain a signal sample corresponding to each partial discharge signal, and extracting a first phase feature of each signal sample; receiving a current power grid load parameter of the target electrical equipment and an environmental parameter of an environment where the target electrical equipment is located, and correcting each first phase feature based on the power grid load parameter and the environmental parameter to obtain a second phase feature after each first phase feature is corrected; and according to a pre-constructed partial discharge characteristic spectrum, identifying each second phase characteristic to obtain a partial discharge identification result of the target electrical equipment. By implementing the technical scheme provided by the invention, the effect of improving the accuracy of partial discharge identification based on phase deviation is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a partial discharge identification method, system, electronic device and storage medium based on phase shift. Background Art

[0002] With the continuous development and expansion of the power system, combined electrical appliances, that is, fully enclosed gas-insulated combined electrical appliances, as an important medium for power transmission, are crucial to the stability of the entire power system. During the long-term operation of combined electrical appliances, due to the influence of various factors, partial discharge may occur, which will not only reduce the insulation performance of combined electrical appliances, but also may cause serious safety accidents. Therefore, timely and accurate identification of partial discharge in combined electrical appliances is of great significance for preventing combined electrical appliance failures and ensuring the safe operation of the power system.

[0003] At present, the existing partial discharge identification method based on phase shift usually installs sensors on the combined electrical appliances, collects the signals generated by partial discharge, and then analyzes the signals to identify the characteristics of partial discharge. However, the partial discharge of the combined electrical appliances during actual operation will be affected by the changes in grid load and environmental conditions. It is often difficult to dynamically adapt to the error changes of the combined electrical appliances under different operating conditions by only collecting and analyzing the signals generated by partial discharge, resulting in low accuracy of partial discharge identification based on phase shift. Summary of the invention

[0004] The present application provides a phase-shift-based partial discharge identification method, system, electronic device, and storage medium, which have the effect of improving the accuracy of phase-shift-based partial discharge identification.

[0005] In a first aspect, the present application provides a partial discharge identification method based on phase shift, comprising: Obtaining partial discharge signals from multiple equipment monitoring points in target electrical equipment; Performing phase synchronization on each of the partial discharge signals to obtain a signal sample corresponding to each of the partial discharge signals, and extracting a first phase feature of each of the signal samples; Receiving the current grid load parameters of the target electrical device and the environmental parameters of the environment in which the target electrical device is located, and correcting each of the first phase characteristics based on the grid load parameters and the environmental parameters to obtain a second phase characteristic after the correction of each of the first phase characteristics; According to the pre-constructed partial discharge characteristic map, each of the second phase characteristics is identified to obtain a partial discharge identification result of the target electrical equipment.

[0006] In a second aspect of the present application, a partial discharge identification system based on phase shift is provided, the system comprising: A signal acquisition module, used to acquire partial discharge signals of multiple equipment monitoring points in the target electrical equipment; a first phase feature determination module, configured to perform phase synchronization on each of the partial discharge signals, obtain a signal sample corresponding to each of the partial discharge signals, and extract a first phase feature of each of the signal samples; a second phase characteristic determination module, configured to receive current grid load parameters of the target electrical device and environmental parameters of the environment in which the target electrical device is located, and to correct each of the first phase characteristics based on the grid load parameters and the environmental parameters to obtain a second phase characteristic after correction of each of the first phase characteristics; The partial discharge identification module is used to identify each of the second phase characteristics according to the pre-constructed partial discharge characteristic map to obtain the partial discharge identification result of the target electrical equipment.

[0007] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement a partial discharge identification method based on phase shift when loaded and executed by the processor.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a partial discharge identification method based on phase shift.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical solution, the partial discharge signals of multiple equipment monitoring points are obtained, and the phase synchronization processing of these signals is carried out to ensure the consistency and timing accuracy of the signal samples. On this basis, the first phase feature of each signal sample is extracted, which reflects the basic phase characteristics of the partial discharge. Subsequently, by receiving the current grid load parameters and environmental parameters of the target electrical equipment, the first phase feature is accurately corrected using the preset mapping relationship to obtain the corrected second phase feature. This correction process effectively eliminates the interference of grid load changes and environmental condition fluctuations on the phase feature, and improves the stability and accuracy of the phase feature. Finally, based on the pre-constructed partial discharge feature map, the corrected second phase feature is comprehensively identified to identify the partial discharge results in the combined electrical appliances. This technical solution realizes high-precision identification of partial discharge under complex and changeable operating conditions through phase synchronization of multi-monitoring point signals and extraction of multi-dimensional phase features, combined with dynamic correction of grid load and environmental parameters, enhances the adaptability to grid load and environmental changes, reduces misjudgment, and thus improves the accuracy of partial discharge identification based on phase offset. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flow chart of a partial discharge identification method based on phase shift provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of a partial discharge identification system based on phase shift provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0011] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0012] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0014] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0015] The present application embodiment provides a method for identifying partial discharge based on phase shift. In one embodiment, please refer to Figure 1 , Figure 1This is a flow chart of a phase-shift-based partial discharge identification method provided in an embodiment of the present application. The method can be implemented by a computer program, which can be integrated in an application or run as an independent tool application. The method can also be implemented by a single-chip microcomputer or run in a phase-shift-based partial discharge identification system based on a von Neumann system. Specifically, the method can include the following steps: Step 101: Obtain partial discharge signals of multiple equipment monitoring points in a target electrical equipment.

[0016] Among them, the equipment monitoring point refers to the detection equipment set on the circuit of the target electrical equipment for collecting partial discharge signals. In the embodiment of the present application, the equipment monitoring point can be understood as a sensor installed on the external surface of the target electrical equipment, which is used to detect various physical signals generated by partial discharge of the combined electrical equipment, such as electromagnetic waves, sound waves, heat changes, etc.

[0017] Partial discharge signals refer to various physical signals generated when a combined electrical appliance discharges at a local insulation fault. In the embodiments of the present application, partial discharge signals can be understood as original signals collected by the equipment monitoring point containing information about the location and time of partial discharge. Common partial discharge signals include electromagnetic wave signals, sound wave signals, thermal image signals, etc.

[0018] Specifically, in order to eliminate the delay difference between the signals of different equipment monitoring points, it is necessary to obtain the partial discharge signals of multiple equipment monitoring points in the target electrical equipment. First, determine the multi-point layout plan of the target electrical equipment, and select the key parts of the combined electrical equipment, such as connectors, insulators, etc. to set equipment monitoring points. Then install sensors at each monitoring point to collect electromagnetic waves, sound waves and other signals generated by the local discharge of the point. The location selection of the monitoring points should cover the important parts of the combined electrical equipment and be distributed at a certain interval. For example, a monitoring point is set every 5-10 meters. After the target electrical equipment is powered on and started, the sensors begin to collect the partial discharge signals at their respective positions. These signals will have a certain time deviation, that is, the delay difference. In order to eliminate this deviation, it is necessary to obtain the signal data of each monitoring point. By analyzing the signals of multiple monitoring points, the time correspondence between the signals can be found. By setting equipment monitoring points at multiple key parts of the target electrical equipment, using sensors to collect the partial discharge signals of each monitoring point, and obtaining multi-point signal data containing delay information, the foundation is laid for subsequent delay compensation and feature analysis to improve the final partial discharge recognition accuracy.

[0019] Step 102: performing phase synchronization on each partial discharge signal to obtain a signal sample corresponding to each partial discharge signal, and extracting a first phase feature of each signal sample.

[0020] Among them, the signal sample refers to the standardized signal data for analysis after preprocessing. In the embodiment of the present application, the signal sample can be understood as the partial discharge signal obtained through phase synchronization and the delay error has been eliminated. These signal samples correspond to different monitoring points on the combined electrical circuit and contain the information of the occurrence time of partial discharge after alignment.

[0021] The first phase feature refers to the initial original phase parameter extracted from the signal sample. In the embodiment of the present application, the first phase feature can be understood as the phase angle value obtained after the signal sample is subjected to time-frequency analysis, indicating the corresponding phase position of the signal on the time-frequency axis.

[0022] Specifically, since the equipment monitoring points are distributed along the combined electrical circuit, the partial discharge signals collected have time deviations, that is, the partial discharge signals at different locations occur at different times. In order to analyze these signal characteristics, they need to be aligned to the same time axis, that is, phase synchronization is performed to eliminate the influence of delay differences. First, the partial discharge signal of one monitoring point is selected as the reference signal, and then the phase difference between other signals and the reference signal is calculated. According to the propagation speed of the signal in the combined electrical device, the delay parameter of the signal can be estimated, and the delay parameter is compensated to the time of the reference signal, that is, the phase synchronization of the signal is achieved. After phase synchronization, the partial discharge signals at different monitoring points are aligned to a unified time axis to form corresponding partial discharge signal samples. Then, each partial discharge signal sample can be subjected to signal analysis to extract characteristic parameters, such as extracting the frequency, phase and other information of the signal through time-frequency analysis and other methods, where the phase characteristics of the signal can be expressed as the first phase characteristics. By performing phase synchronization on the partial discharge signals at multiple points, aligned signal samples are obtained, and the phase characteristics of the samples are extracted, which lays the foundation for subsequent feature analysis and identification.

[0023] Based on the above embodiment, as an optional embodiment, in step 102: performing phase synchronization on each partial discharge signal to obtain a signal sample corresponding to each partial discharge signal, this step may also include the following steps: Step 201: Acquire a reference phase signal of a target electrical device; calculate a phase difference between each partial discharge signal and the reference phase signal, and compensate for each phase difference according to a preset signal propagation time.

[0024] The reference phase signal refers to a reference signal used to calibrate the time delay of other signals. In the embodiment of the present application, the reference phase signal can be understood as a partial discharge signal obtained by selecting a monitoring point at the end or middle position of the combined electrical appliance. This signal is used as the basis for time calibration, and the partial discharge signals of other monitoring points are phase-adjusted with reference to this reference signal.

[0025] The preset signal propagation time refers to the propagation speed parameter of the signal in the transmission medium of the combined electrical appliance. In the embodiment of the present application, the preset signal propagation time can be understood as the propagation time per unit length of the electromagnetic wave signal or the sound wave signal in the circuit of different types of combined electrical appliances.

[0026] Specifically, in order to achieve accurate phase compensation of the partial discharge signal at each device monitoring point, it is necessary to first obtain the reference phase signal of the target electrical device. The reference signal can select the partial discharge signal of a monitoring point at the end or midpoint of the combined electrical appliance. Next, the phase difference between the partial discharge signal and the reference signal of each device monitoring point is calculated, and the delay parameter between the signals can be obtained through the relevant algorithm. According to the layout of the combined electrical circuit, the propagation speed of the signal in the combined electrical appliance can be preset, that is, the propagation time required per unit distance. Then, the distance between each signal and the reference signal and the preset propagation speed are combined to obtain the theoretical delay or phase offset of each signal relative to the reference signal. Based on this, the phase of each partial discharge signal can be compensated, and its delay parameter can be adjusted to align it to the same time axis as the reference signal. After this processing, the delay deviation of the partial discharge signal at different device monitoring points is eliminated, and the phase synchronization between multiple signals is achieved. Phase synchronization is the basis for subsequent feature extraction and comparison. This step is conducive to improving the accuracy of delay compensation by setting a reference signal and performing quantitative phase compensation, laying the foundation for obtaining standardized signal samples.

[0027] Step 202: Based on the compensated phase differences, the time axis of each partial discharge signal is adjusted to obtain a signal sample corresponding to each partial discharge signal.

[0028] Among them, the phase difference refers to the time deviation between different signals in the timing. In the embodiment of the present application, the phase difference can be understood as the difference between the local discharge signal of each device monitoring point and the set reference phase signal at the occurrence time point. The compensated phase difference refers to the residual delay obtained by correcting the original phase difference according to the combined electrical circuit parameters after determining the initial phase difference between each local discharge signal and the reference signal.

[0029] Specifically, after compensating for the phase difference of each partial discharge signal, relatively accurate delay compensation parameters between signals are obtained. In order to eliminate the influence of these delay errors on subsequent analysis, it is necessary to further adjust the time axis of each partial discharge signal based on the compensated results to achieve accurate time alignment. A unified time axis is set, and then according to the compensated residual delay parameters of each signal and the reference signal, the position of each signal on the unified time axis is accurately adjusted through signal interpolation, shifting and other operations to achieve alignment of different signals on the time axis. After the time axis adjustment, the delay deviation of each partial discharge signal is corrected to obtain signal samples aligned in time. These samples provide observation results at different positions for a partial discharge event. Subsequently, feature comparison, positioning analysis, etc. can be performed based on these samples with unified timing, and the results will not be affected by the delay deviation of the original signal. By adjusting the time axis of the partial discharge signal, time-aligned signal samples are obtained, providing a data basis for improving the accuracy of subsequent analysis and comparison.

[0030] Based on the above embodiment, as an optional embodiment, in step 102: extracting the first phase feature of each signal sample, this step may also include the following steps: Step 203: Perform time-frequency transformation on each signal sample to obtain a time-frequency spectrum corresponding to each signal sample; in each time-frequency spectrum, extract the energy distribution feature of each signal sample.

[0031] Among them, the time-frequency spectrum refers to the two-dimensional distribution spectrum of the signal in the time domain and frequency domain. In the embodiment of the present application, the time-frequency spectrum can be understood as the time-frequency coordinate diagram obtained after the signal sample is transformed into a time-frequency coordinate, which uses time as the horizontal coordinate and frequency as the vertical coordinate to represent the comprehensive distribution of the signal on the time-frequency axis.

[0032] Energy distribution features refer to characteristic parameters extracted from the signal's time-frequency spectrum that represent the energy distribution state of the signal. In the embodiment of the present application, energy distribution features can be understood as features such as energy concentration area, phase value, and energy amplitude obtained by image analysis of the signal's time-frequency spectrum.

[0033] Specifically, in order to comprehensively analyze the characteristics of the signal, it is necessary to extract the signal from both the time domain and the frequency domain. Therefore, by performing time-frequency transformation on each signal sample with a uniform time sequence, the time-frequency distribution diagram of the sample can be obtained, reflecting the comprehensive situation of the signal in the time domain and the frequency domain. For each preprocessed signal sample, the short-time Fourier transform and other algorithms are used to convert it from the time domain to the frequency domain to obtain the two-dimensional time-frequency spectrum of the sample. In the time-frequency spectrum, the distribution of the signal frequency components on the time axis can be clearly observed, and the time-frequency spectrum forms of different types of signals are different. Based on this, image processing and pattern recognition techniques can be used to extract the energy distribution characteristics of the sample time-frequency spectrum and perform sample comparison analysis. This feature reflects the energy concentration of the signal on the time-frequency axis. Different types of partial discharge have identifiable differences in the distribution form of their energy on the spectrum. These energy distribution characteristics can be expressed as the second feature of the signal. By performing time-frequency analysis on the signal, the time-frequency spectrum is obtained, and the energy characteristics are extracted from it, which supplements the phase characteristics, provides a richer basis for identifying different types of partial discharges, and can improve the accuracy of detection.

[0034] Based on the above embodiment, as an optional embodiment, in step 203: extracting energy distribution features of each signal sample in each time-frequency spectrum, this step may also include the following steps: Step 213: Perform energy integration on each time-frequency spectrum to obtain an energy-phase distribution curve corresponding to each time-frequency spectrum.

[0035] Among them, energy integration refers to the summation operation of the signal time-frequency spectrum in the frequency dimension to obtain the sum of the energy of each frequency in the entire time domain. In the embodiment of the present application, energy integration can be understood as projecting the time-frequency spectrum on the time axis to the frequency axis, calculating the sum of the energy values ​​corresponding to each frequency, and reflecting the total energy size of the frequency in the entire signal length.

[0036] The energy-phase distribution curve refers to a two-dimensional distribution curve diagram drawn by correspondingly associating the energy value of each frequency component in the signal time-frequency spectrum with the phase value. In the embodiment of the present application, the energy-phase distribution curve can be understood as a curve obtained by integrating the energy of the time-frequency spectrum and mapping the integral result to the phase coordinate, which takes the phase as the horizontal coordinate and the energy size of the corresponding frequency as the vertical coordinate.

[0037] Specifically, after obtaining the time-frequency spectrum of each signal sample, in order to further analyze the time-frequency structure of the signal, the energy of the time-frequency spectrum can be integrated to obtain an energy-phase distribution curve. For each frequency component on the signal time-frequency spectrum, calculate its energy size in the full time length, that is, integrate the frequency axis. Then, the energy value corresponding to each frequency is associated with the phase coordinate position of the frequency, and a two-dimensional curve graph can be drawn. The horizontal axis is the phase in the time-frequency spectrum, and the vertical axis is the energy value of the corresponding frequency. In this way, the energy and phase information in the time-frequency spectrum are integrated into a two-dimensional distribution curve, which intuitively reflects the time-frequency structure of the signal sample, and the energy-phase curve shapes of different local discharge types are different.

[0038] Step 223: In each energy-phase distribution curve, determine the energy peak point; and use the phase value and energy amplitude of each energy peak point as the energy distribution feature of each signal sample.

[0039] The energy peak point refers to the point where the energy amplitude on the signal energy-phase distribution curve reaches a maximum value. In the embodiment of the present application, the energy peak point can be understood as the local maximum point on the energy-phase distribution curve, which represents that the energy of a certain frequency component of the signal reaches a higher concentration state at this point.

[0040] The phase value refers to the angular coordinate of the frequency component on the time-frequency spectrum or energy-phase curve. In the embodiment of the present application, the phase value can be understood as the phase angle position of a frequency component on the time-frequency plane, reflecting the phase relationship of the frequency component relative to time zero.

[0041] Energy amplitude refers to the energy of a frequency component in the time-frequency distribution. In the embodiment of the present application, energy amplitude can be understood as the energy integration result of a certain frequency component in the full time length, indicating the intensity of the frequency in the signal.

[0042] Specifically, after obtaining the energy-phase distribution curve of each signal sample, the energy peak point on the curve can be further analyzed and determined as the energy distribution feature of the signal sample. By traversing the curve graph, the point where the signal energy value has a maximum value is found. These peak points represent the key frequency bands where the energy is relatively concentrated in the signal time-frequency structure. Then, the specific phase value and energy amplitude corresponding to each energy peak point are extracted. Among them, the phase value represents the phase coordinate of the frequency component, and the energy amplitude represents the intensity of the frequency. Taking the two as a set of features, the time-frequency state of the signal sample on a certain key frequency band can be expressed, reflecting the important time-frequency structure of the signal. There are differences in the key frequency bands and corresponding energy distribution states of different types of partial discharge. The characteristics of these energy peak points can be used to distinguish signals. Finally, by counting the characteristics of all peak points, the energy distribution feature vector of the signal can be constructed, providing richer pattern recognition information to achieve accurate detection of partial discharge.

[0043] Step 204: Determine the phase angle in each signal sample according to each energy distribution feature, and use each phase angle as the first phase feature of each signal sample.

[0044] The phase angle refers to an angle parameter representing the phase characteristics of a signal. In the embodiment of the present application, the phase angle can be understood as the angle characteristics of the phase value within the frequency band obtained by statistical analysis after determining the main frequency band of the signal.

[0045] Specifically, after obtaining the time-frequency energy distribution characteristics of the signal sample, these characteristic information can be used to optimize the extraction of the first phase feature. Since the phase characteristics previously directly obtained from the time domain signal may be affected by noise and are not accurate enough. Therefore, the main frequency band range of the signal, that is, the time-frequency region where the energy is relatively concentrated, can be determined based on the energy distribution state of the signal time-frequency spectrum. Then, when extracting the phase characteristics of the signal, only these main frequency bands with strong energy are selected for analysis, and the phase components in the frequency band are obtained by means such as frequency band filtering. Next, the mean square error or principal component of the phase of each frequency component in the frequency band is calculated to obtain the statistical characteristics of the phase value in the frequency band, that is, the phase angle parameter of the signal in the frequency band. At the same time, combined with the energy amplitude of each frequency in the frequency band, the energy intensity level of the frequency band can be represented. Finally, the phase angle and the corresponding energy amplitude, as a component of the first phase feature of the signal sample, contain the time-frequency structure information of the signal. This phase feature combined with time-frequency domain information can reduce the influence of noise, more comprehensively represent the time-frequency distribution pattern of the signal, and provide more reliable input for subsequent feature correction.

[0046] Step 103: receiving the current grid load parameters of the target electrical device and the environmental parameters of the environment in which the target electrical device is located, and correcting each first phase characteristic based on the grid load parameters and the environmental parameters to obtain a second phase characteristic after the correction of each first phase characteristic.

[0047] Among them, the grid load parameters refer to a set of characteristic parameters that reflect the operation of the grid. In the embodiment of the present application, the grid load parameters can be understood as some characteristic quantities that describe the load state of the grid, such as current, voltage, power, power factor and other indicators, which can fully reflect the load degree and operation state of the grid.

[0048] Environmental parameters refer to a set of characteristic parameters that describe the environmental conditions of the power equipment. In the embodiment of the present application, environmental parameters can be understood as characteristic quantities that reflect the operating environment of the combined electrical equipment circuit, such as temperature, humidity, electromagnetic interference and other indicators, which can fully describe the working environment of the combined electrical equipment.

[0049] The second phase feature refers to a new phase feature obtained after correction according to the grid load parameters and environmental parameters based on the first phase feature. In the embodiment of the present application, the second phase feature can be understood as a phase feature after feature calibration, which eliminates the influence of grid load changes and environmental noise on the basis of the first phase feature, and obtains a more accurate and stable feature expression.

[0050] Specifically, after extracting the first phase feature of the signal sample, feature correction is required to eliminate the influence of grid load and environmental factors and obtain a more accurate feature representation. The grid load parameter data of the combined electrical appliance line, such as current, voltage, power and other information, is received in real time, which can reflect the load state of the grid. At the same time, the parameters of the combined electrical appliance environment, such as temperature, humidity, electromagnetic noise and other data, are obtained to monitor the working environment of the combined electrical appliance. Then, a mapping model of grid load parameters, environmental parameters and the first phase feature is established based on historical statistical analysis, and the deviation of the first phase feature relative to the true value under different load conditions and environments can be evaluated. The grid load parameters and environmental parameters obtained in real time are input into the mapping model to calculate the error compensation value of the first phase feature. By performing calculation correction on the first phase feature and the compensation amount, the influence of grid load changes and environmental noise can be eliminated, and a second phase feature that more accurately expresses the signal characteristics can be obtained. This process corrects the influence of changes in environmental conditions, ensures that the features extracted under different operating environments are comparable, and provides reliable input for subsequent identification.

[0051] Based on the above embodiment, as an optional embodiment, in step 103: based on the grid load parameter and the environmental parameter, each first phase feature is corrected to obtain a second phase feature after the first phase feature is corrected. This step may also include the following steps: Step 301: Based on the mapping relationship between the preset grid load parameters and the phase offset, determine the first phase offset corresponding to the load voltage and load current in the grid load parameters, and based on the mapping relationship between the preset environmental parameters and the phase offset, determine the second phase offset corresponding to the temperature and humidity in the environmental parameters.

[0052] The mapping relationship between the preset grid load parameters and the phase offset refers to a corresponding model between the grid load parameters and the phase offset established based on historical statistical data. In the embodiment of the present application, it can be understood as determining the deviation amount of the characteristic phase under different grid load levels by analyzing a large amount of historical sample data, and establishing a mathematical mapping or lookup table relationship between the load parameters and the phase offset.

[0053] The load voltage and load current refer to the voltage parameters and current parameters that reflect the load conditions of the power grid. In the embodiment of the present application, they can be understood as the voltage effective value and current effective value obtained by real-time detection of the power supply end of the power grid. These two parameters directly reflect the load size and changes of the power grid.

[0054] The mapping relationship between the preset environmental parameters and the phase offset refers to the corresponding model between the environmental parameters and the phase offset established based on historical statistical data. In the embodiment of the present application, it can be understood as analyzing a large amount of historical sample data to determine the deviation of the characteristic phase under different environmental conditions, and establishing a mathematical mapping or lookup table relationship between the environmental parameters and the phase offset.

[0055] Temperature and humidity refer to temperature parameters and humidity parameters that reflect the circuit environment of the combined electrical appliance. In the embodiment of the present application, they can be understood as the ambient temperature and humidity data obtained by real-time monitoring of the power combined electrical appliance. These two parameters directly reflect the working environment of the combined electrical appliance.

[0056] The first phase offset refers to the deviation of the phase feature caused by the change of the grid load. In the embodiment of the present application, the first phase offset can be understood as the angle deviation of the phase feature relative to the true value under different grid load conditions.

[0057] The second phase offset refers to the deviation of the phase feature caused by environmental noise. In the embodiment of the present application, the second phase offset can be understood as the angle deviation of the phase feature relative to the true value under different environmental conditions.

[0058] Specifically, in order to eliminate the influence of power grid load and environment on phase characteristics, it is necessary to establish a mapping relationship between load, environmental parameters and phase offset to perform feature correction. First, based on historical statistical analysis, a corresponding relationship model between power grid load parameters, such as load voltage, load current, etc., and the first phase offset is preset. At the same time, a mapping relationship between environmental parameters, such as temperature, humidity, etc., and the second phase offset is also preset. In real-time detection, the detected load voltage and current will be used as input to query in the preset load-phase mapping model to obtain the first phase offset corresponding to the current load condition. At the same time, the detected ambient temperature and humidity will also be used as input to query in the preset environment-phase mapping relationship to obtain the second phase offset corresponding to the current environment, and the first and second phase offsets are superimposed as the total offset of the sample. By obtaining the phase deviation caused by the load and environment through the pre-built mapping relationship, the original phase characteristic value can be compensated, the influence of changes in environmental conditions can be eliminated, and more accurate data can be obtained.

[0059] Step 302: Add each first phase feature to the first phase offset and the second phase offset respectively to obtain a second phase feature after correction of each first phase feature.

[0060] Specifically, after obtaining the first phase offset and the second phase offset, it is necessary to perform correction calculation of the characteristic value to obtain a more accurate second phase feature. The value of the first phase feature is added to the corresponding first phase offset and second phase offset. The first phase offset reflects the angle error of the phase feature caused by the change in the power grid load, and the second phase offset reflects the deviation of the phase feature caused by the environmental noise. The total deviation of the sample feature can be obtained by superimposing the two, and then added to the original first phase characteristic value, thereby realizing the compensation and correction of the characteristic value. The corrected second phase feature eliminates the influence of power grid load changes and environmental noise, and can accurately express the time-frequency structure characteristics of the signal.

[0061] Step 104: Identify each second phase feature according to the pre-constructed partial discharge feature map to obtain a partial discharge identification result of the target electrical device.

[0062] Among them, the pre-constructed partial discharge characteristic map refers to a feature library containing typical partial discharge characteristic samples. In the embodiment of the present application, it can be understood as collecting various typical partial discharge phase characteristic samples, conducting training and learning, and obtaining a map library reflecting different partial discharge characteristics.

[0063] The partial discharge identification result refers to the partial discharge type classification result obtained after detecting the target electrical equipment signal. In the embodiment of the present application, it can be understood as extracting the second phase feature of the signal and matching it on the pre-constructed partial discharge feature map to finally determine the partial discharge category to which the signal belongs.

[0064] Specifically, after obtaining the second phase feature that accurately expresses the signal characteristics, it is necessary to identify based on these features to realize the detection of the partial discharge type. The identification is performed using a pre-constructed partial discharge feature map. The partial discharge feature map contains the expression of various typical partial discharges on the second phase feature, which is obtained through training. Then, the extracted second phase feature is matched and compared with the samples in the feature map to determine the most matching partial discharge category, that is, the recognition of the target electrical equipment signal is realized. The matching can be achieved based on the similarity calculation of the phase features. The category with high similarity is the recognition result. The second phase feature obtained after feature correction can accurately represent the characteristic information of the signal, which is conducive to improving the accuracy of recognition. This process realizes recognition based on stable features, improves the reliability of the detection effect, and avoids interference from the external environment.

[0065] Based on the above embodiment, as an optional embodiment, in step 104: according to the pre-constructed partial discharge characteristic map, each second phase feature is identified to obtain the partial discharge identification result of the target electrical equipment. This step may also include the following steps: Step 401: Compare each second phase feature with a phase angle feature in a partial discharge feature map to determine a partial discharge type corresponding to each second phase feature.

[0066] Among them, the phase angle feature refers to the phase angle data that reflects the time-frequency structure of the signal. In the embodiment of the present application, it can be understood as the phase angle value that reflects the time-frequency feature information obtained by signal analysis and extraction. The phase angle feature, as the result of time-frequency analysis, contains key information such as the frequency and energy of the signal.

[0067] The partial discharge type refers to the category of partial discharge in different forms in the power equipment. In the embodiment of the present application, it can be understood as the specific discharge form given in the partial discharge identification result, such as different types such as suspended discharge, surface discharge, and internal discharge.

[0068] Specifically, in order to realize the recognition of the extracted signal features, a partial discharge feature spectrum is first pre-constructed, which contains the second phase feature samples and angle information of various typical partial discharges. This can be obtained by collecting partial discharge samples for training. Then, the detected combined electrical signal is processed to extract its second phase feature, which reflects the time-frequency structure information of the signal. Next, the extracted second phase feature is compared with each type of partial discharge phase angle in the partial discharge feature spectrum one by one, and their similarity is calculated. Finally, the category to which the spectrum sample with the highest similarity belongs is the recognition result corresponding to the signal feature, realizing the detection of partial discharge. This process realizes the effective recognition of the second feature by matching with the spectrum, and matching with the original feature can improve the recognition accuracy.

[0069] Step 402: based on the partial discharge types corresponding to the second phase features, determine the occurrence frequency of each partial discharge type; and use the partial discharge type whose occurrence frequency is greater than or equal to the frequency threshold as the partial discharge identification result of the target electrical equipment.

[0070] Specifically, in order to further improve the reliability of partial discharge identification, it is necessary to perform multi-sample voting to determine the final result: First, the partial discharge type identified by each sample detected is counted, and the number of occurrences of each discharge type is calculated. Then, a predetermined minimum frequency threshold is set, such as 5 times. Next, all partial discharge types with a number of occurrences exceeding the threshold are determined as the final identification result of the signal. Finally, the identification result is returned to give the main partial discharge form of the target electrical equipment. This process can filter out some identification errors and improve the accuracy of the results by counting the occurrence frequency of multiple samples.

[0071] Based on the above embodiment, as an optional embodiment, in step 104: according to the pre-constructed partial discharge characteristic map, each second phase feature is identified to obtain the partial discharge identification result of the target electrical equipment. Before this step, the following steps may also be included: Step 501: Acquire a plurality of partial discharge sample data with partial discharge type labels, and extract the phase angle of each partial discharge sample data.

[0072] Among them, the partial discharge sample data with partial discharge type labels refers to the sample signals with partial discharge categories annotated by experts. In the embodiment of the present application, it can be understood as the original signal data of various typical partial discharges collected, and after pre-annotation, the specific partial discharge type to which each sample belongs is given, such as suspended discharge, surface discharge, etc. These partial discharge sample data with category annotations provide input for constructing the feature mapping relationship corresponding to each partial discharge type.

[0073] Specifically, in order to construct the characteristic map of partial discharge, it is necessary to collect samples with category annotations for training. First, obtain the original sample data of partial discharge of different types. These sample data have been labeled by experts in advance, indicating the type of partial discharge to which they belong. Then, perform time-frequency conversion on the collected partial discharge sample data, and extract the phase angle features that express the time-frequency structure information of the sample. In this way, a large number of partial discharge phase angle feature samples with labeled categories are obtained, which lays the foundation for the subsequent construction of characteristic maps reflecting the differences between various types of partial discharges. Collecting sufficient labeled training samples containing various types of partial discharges and extracting corresponding features are the prerequisites for obtaining a robust partial discharge recognition model. By collecting labeled partial discharge samples and extracting features, the training data required for building partial discharge recognition is obtained.

[0074] Step 502: for each partial discharge sample data, perform cluster analysis on the phase angle to obtain multiple cluster centers, and use each cluster center as a phase angle feature of the partial discharge sample data corresponding to the partial discharge type label.

[0075] Cluster analysis refers to an existing unsupervised learning method that groups samples according to their similarity. In the embodiment of the present application, it can be understood as aggregating and grouping the phase angle features extracted from each type of partial discharge sample so that similar features are clustered together to form clusters.

[0076] The cluster center refers to the center point of each cluster in the clustering result. In the embodiment of the present application, it can be understood as the central feature vector inside each cluster obtained after clustering the phase angle features of each type of partial discharge samples.

[0077] Specifically, in order to construct a feature map that can represent various types of partial discharges, it is necessary to obtain the representative feature center of each category through cluster analysis. First, for multiple partial discharge samples of each category, their phase angle characteristics can be regarded as a sample cluster, which may be dispersed to a certain extent. Then, the phase angle characteristics of all samples of each partial discharge category are clustered together to obtain several tight feature clusters. Next, the center point vector of each feature cluster is extracted as the representative feature center of this type of discharge. Finally, the process is repeated to obtain the feature cluster centers of all categories of partial discharges. These cluster centers can represent the main feature distribution of the corresponding categories and constitute the phase angle feature map of the final partial discharge identification model. In this way, by finding the match between new samples and these cluster centers, the partial discharge type can be identified. The representative feature center corresponding to the category is obtained through cluster analysis, which is used to construct the angle map of partial discharge identification.

[0078] Step 503: Generate a pre-constructed partial discharge feature map based on each partial discharge type label and the phase angle feature corresponding to each partial discharge type label.

[0079] Specifically, after obtaining the representative phase angle characteristics of each partial discharge category, it is necessary to construct the final partial discharge feature map. First, based on the collected labeled samples, the label information corresponding to each typical partial discharge has been obtained. Then, the representative phase angle characteristics of each type of partial discharge are obtained through cluster analysis. Next, the mapping relationship between each partial discharge category label and its corresponding phase angle characteristics is established. Finally, the label information of all categories and their corresponding features are integrated to form a partial discharge feature map containing category and feature comparison. This constructed map provides a basis for the subsequent identification of the partial discharge category of unknown signals. By matching the similarity between the signal features and the samples in the map, the partial discharge type can be judged. By integrating the category annotations and corresponding features, the generation of the partial discharge feature map is completed.

[0080] Reference Figure 2 , a partial discharge identification system based on phase shift is provided in an embodiment of the present application, the system comprises: a signal acquisition module, a first phase feature determination module, a second phase feature determination module, and a partial discharge identification module, wherein: A signal acquisition module, used to acquire partial discharge signals of multiple equipment monitoring points in the target electrical equipment; A first phase feature determination module, used to perform phase synchronization on each partial discharge signal, obtain a signal sample corresponding to each partial discharge signal, and extract a first phase feature of each signal sample; A second phase characteristic determination module is used to receive the current grid load parameters of the target electrical equipment and the environmental parameters of the environment in which the target electrical equipment is located, and based on the grid load parameters and the environmental parameters, correct each first phase characteristic to obtain a second phase characteristic after each first phase characteristic is corrected; The partial discharge identification module is used to identify each second phase feature according to a pre-constructed partial discharge feature map to obtain a partial discharge identification result of the target electrical equipment.

[0081] On the basis of the above-mentioned embodiment, the first phase characteristic determination module is also used to obtain a reference phase signal of the target electrical equipment; calculate the phase difference between each local discharge signal and the reference phase signal, and compensate for each phase difference according to a preset signal propagation time; based on the compensated phase differences, adjust the time axis of each local discharge signal to obtain a signal sample corresponding to each local discharge signal.

[0082] Based on the above embodiments, the first phase feature determination module is also used to perform time-frequency transformation on each signal sample to obtain a time-frequency spectrum corresponding to each signal sample; in each time-frequency spectrum, the energy distribution characteristics of each signal sample are extracted; based on each energy distribution characteristic, the phase angle in each signal sample is determined, and each phase angle is used as the first phase feature of each signal sample.

[0083] Based on the above embodiment, the first phase feature determination module is also used to perform energy integration on each time-frequency spectrum to obtain an energy-phase distribution curve corresponding to each time-frequency spectrum; in each energy-phase distribution curve, the energy peak point is determined; and the phase value and energy amplitude of each energy peak point are used as the energy distribution characteristics of each signal sample.

[0084] On the basis of the above embodiment, the second phase characteristic determination module is also used to determine the first phase offset corresponding to the load voltage and load current in the power grid load parameters based on the mapping relationship between the preset power grid load parameters and the phase offset, and determine the second phase offset corresponding to the temperature and humidity in the environmental parameters based on the mapping relationship between the preset environmental parameters and the phase offset; each first phase characteristic is added to the first phase offset and the second phase offset respectively to obtain the second phase characteristic after the first phase characteristics are corrected.

[0085] On the basis of the above-mentioned embodiment, the local discharge identification module is further used to compare each second phase feature with the phase angle feature in the local discharge feature map to determine the local discharge type corresponding to each second phase feature; based on the local discharge type corresponding to each second phase feature, determine the occurrence frequency of each local discharge type; and use the local discharge type with an occurrence frequency greater than or equal to the frequency threshold as the local discharge identification result of the target electrical equipment.

[0086] On the basis of the above embodiment, the local discharge identification module is further used to obtain multiple local discharge sample data with local discharge type labels, and extract the phase angle of each local discharge sample data; for each local discharge sample data, cluster analysis is performed on the phase angle to obtain multiple cluster centers, and each cluster center is used as the phase angle feature of the local discharge sample data corresponding to the local discharge type label; based on each local discharge type label and the phase angle feature corresponding to each local discharge type label, a pre-constructed local discharge feature map is generated.

[0087] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0088] The present application also discloses an electronic device. Figure 3 , Figure 3The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0089] The communication bus 302 is used to realize the connection and communication between these components.

[0090] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0091] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0092] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0093] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a partial discharge identification method based on phase shift.

[0094] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a partial discharge identification method based on phase offset, and when executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0095] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0099] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0100] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0101] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not recorded in the present disclosure. The description and examples are to be regarded as exemplary only.

Claims

1. A partial discharge identification method based on phase shift, characterized in that: include: Obtaining partial discharge signals from multiple equipment monitoring points in target electrical equipment; Performing phase synchronization on each of the partial discharge signals to obtain a signal sample corresponding to each of the partial discharge signals, and extracting a first phase feature of each of the signal samples; Receiving the current grid load parameters of the target electrical device and the environmental parameters of the environment in which the target electrical device is located, and correcting each of the first phase characteristics based on the grid load parameters and the environmental parameters to obtain a second phase characteristic after the correction of each of the first phase characteristics; According to the pre-constructed partial discharge characteristic map, each of the second phase characteristics is identified to obtain a partial discharge identification result of the target electrical equipment.

2. The phase shift-based partial discharge identification method according to claim 1, characterized in that: The step of performing phase synchronization on each of the partial discharge signals to obtain a signal sample corresponding to each of the partial discharge signals includes: Acquire a reference phase signal of the target electrical device; Calculating a phase difference between each of the partial discharge signals and the reference phase signal, and compensating each of the phase differences according to a preset signal propagation time; Based on the compensated phase differences, the time axis of each partial discharge signal is adjusted to obtain a signal sample corresponding to each partial discharge signal.

3. The method for identifying partial discharge based on phase shift according to claim 1, characterized in that: The extracting the first phase feature of each of the signal samples comprises: Performing time-frequency transformation on each of the signal samples to obtain a time-frequency spectrum corresponding to each of the signal samples; In each of the time-frequency spectra, extracting energy distribution characteristics of each of the signal samples; According to each of the energy distribution characteristics, a phase angle in each of the signal samples is determined, and each of the phase angles is used as a first phase characteristic of each of the signal samples.

4. The method for identifying partial discharge based on phase shift according to claim 3, characterized in that: Extracting the energy distribution feature of each signal sample in each time-frequency spectrum includes: Performing energy integration on each of the time-frequency spectra to obtain an energy-phase distribution curve corresponding to each of the time-frequency spectra; In each of the energy-phase distribution curves, determining an energy peak point; The phase value and energy amplitude of each energy peak point are used as energy distribution characteristics of each signal sample.

5. The method for identifying partial discharge based on phase shift according to claim 1, characterized in that: The correcting each of the first phase characteristics based on the power grid load parameter and the environmental parameter to obtain a second phase characteristic after the correction of each of the first phase characteristics comprises: Based on a mapping relationship between a preset grid load parameter and a phase offset, determine a first phase offset corresponding to a load voltage and a load current in the grid load parameter, and based on a mapping relationship between a preset environmental parameter and the phase offset, determine a second phase offset corresponding to a temperature and a humidity in the environmental parameter; Each of the first phase characteristics is added to the first phase offset and the second phase offset respectively to obtain a second phase characteristic after correction of each of the first phase characteristics.

6. The method for identifying partial discharge based on phase shift according to claim 1, characterized in that: The pre-constructed partial discharge characteristic spectrum includes a plurality of partial discharge types and phase angle characteristics corresponding to each of the partial discharge types. The identification of each of the second phase characteristics according to the pre-constructed partial discharge characteristic spectrum to obtain the partial discharge identification result of the target electrical equipment includes: Comparing each of the second phase features with a phase angle feature in the partial discharge feature spectrum to determine a partial discharge type corresponding to each of the second phase features; Determining the occurrence frequency of each of the partial discharge types based on the partial discharge types corresponding to each of the second phase characteristics; The partial discharge type with an occurrence frequency greater than or equal to a frequency threshold is used as a partial discharge identification result of the target electrical equipment.

7. The method for identifying partial discharge based on phase shift according to claim 1, characterized in that: Before identifying each of the second phase features according to the pre-constructed partial discharge feature map to obtain the partial discharge identification result of the target electrical equipment, the method further includes: Acquire a plurality of partial discharge sample data with partial discharge type labels, and extract a phase angle of each of the partial discharge sample data; For each of the partial discharge sample data, cluster analysis is performed on the phase angle to obtain a plurality of cluster centers, and each of the cluster centers is used as a phase angle feature of a partial discharge type label corresponding to the partial discharge sample data; A pre-constructed partial discharge characteristic map is generated based on each of the partial discharge type labels and the phase angle characteristics corresponding to each of the partial discharge type labels.

8. A partial discharge identification system based on phase shift, characterized in that: The system comprises: A signal acquisition module, used to acquire partial discharge signals of multiple equipment monitoring points in the target electrical equipment; a first phase feature determination module, configured to perform phase synchronization on each of the partial discharge signals, obtain a signal sample corresponding to each of the partial discharge signals, and extract a first phase feature of each of the signal samples; a second phase characteristic determination module, configured to receive current grid load parameters of the target electrical device and environmental parameters of the environment in which the target electrical device is located, and to correct each of the first phase characteristics based on the grid load parameters and the environmental parameters to obtain a second phase characteristic after correction of each of the first phase characteristics; The partial discharge identification module is used to identify each of the second phase characteristics according to the pre-constructed partial discharge characteristic map to obtain the partial discharge identification result of the target electrical equipment.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a partial discharge identification method based on phase offset as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method for identifying partial discharge based on phase shift according to any one of claims 1 to 7 is executed.

Images