Partial Discharge Signal Detection Method, Device, Electronic Device and Storage Medium

Abstract

The present application provides a partial discharge signal detection method, device, electronic device and storage medium, relating to the technical field of electrical signal processing. The partial discharge signal detection device includes three input ports and a common output port; the method includes: obtaining a comprehensive output signal of the common output port; wherein, the comprehensive output signal includes three-phase signals A, B, and C after quadrature amplitude modulation (QAM); obtaining the modulation parameters when the three-phase signals A, B, and C are subjected to QAM inside the partial discharge monitor, and obtaining a corresponding pre-trained signal separation model according to the modulation parameters; inputting the comprehensive output signal into the signal separation model to obtain the single-phase output signals corresponding to the three phases A, B, and C respectively. The present application realizes the output of three-phase signals through the common output port, reduces the cost of the partial discharge monitor, and at the same time, performs separation and analysis on the comprehensive output signal based on the signal separation model.

Description

Technical Field

[0001] This application relates to the technical field of electrical signal processing, and particularly to a method, device, electronic device and storage medium for detecting partial discharge signals. Background Art

[0002] With the continuous progress of the state detection technology of distribution network equipment, power enterprises have put forward basic requirements such as "qualitative, phasing, positioning, and quantification". Given the variability of the operating environment and conditions of distribution network equipment, partial discharge may manifest in various forms such as insulation defect discharge, floating discharge, corona discharge, and surface discharge. Under the premise of low investment and high efficiency, it is particularly crucial to solve the operating faults of distribution equipment and ensure the safe and stable operation of the equipment.

[0003] Insulation damage may trigger partial discharge and exist in some insulation gaps. Initially, these partial discharges have little impact on the equipment, but over time, they will cause greater damage to the insulation, and both the intensity and frequency will increase. If these local phenomena cannot be detected and the causes found in a timely manner, the partial discharge will inevitably develop into breakdown discharge, ultimately resulting in equipment damage. In terms of time, from the occurrence of partial discharge to the insulation breakdown stage, it may take several weeks to several months. Therefore, when partial discharge occurs, if it can be detected by a suitable sensor and a warning is issued, corresponding countermeasures can be formulated in advance. Subsequently, partial discharge monitoring equipment was developed. The internal circuit of the relevant partial discharge monitoring equipment is a three-in-three-out architecture, with a large number of output ports and high costs. Adopting a three-in-one-out architecture can solve the cost problem, but there is a lack of a solution for identifying each phase signal from one output port. Summary of the Invention

[0004] Embodiments of this application provide a method, device, electronic device and storage medium for detecting partial discharge signals to solve the problem of how to identify each phase signal at the output port of a three-in-one-out architecture.

[0005] In a first aspect, embodiments of this application provide a method for detecting partial discharge signals. The partial discharge signal detection device includes three input ports and a common output port; the method includes:

[0006] Obtain the comprehensive output signal of the common output port; wherein, the comprehensive output signal includes three-phase signals A, B, and C after Quadrature Amplitude Modulation (QAM);

[0007] Obtain the modulation parameters when the three-phase signals A, B, and C are QAM modulated inside the partial discharge monitor, and obtain the corresponding pre-trained signal separation model according to the modulation parameters;

[0008] Input the combined output signal into the signal separation model to obtain the single-phase output signals corresponding to each of the three phases A, B, and C.

[0009] In a second aspect, an embodiment of the present application provides a partial discharge signal detection device, including:

[0010] A signal acquisition module for acquiring a combined output signal of a shared output port; wherein, the combined output signal includes the three-phase signals of A, B, and C after QAM;

[0011] A model acquisition module for acquiring the modulation parameters when the three-phase signals of A, B, and C are QAM modulated inside the partial discharge monitor, and obtaining a corresponding pre-trained signal separation model according to the modulation parameters;

[0012] A determination module for inputting the combined output signal into the signal separation model to obtain the single-phase output signals corresponding to each of the three phases A, B, and C.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect above.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect above.

[0015] An embodiment of the present application provides a partial discharge signal detection method, device, electronic device, and storage medium. By configuring a shared output port for the partial discharge signal detection device, the integrated output of the information of the three input ports is realized. A signal separation model is introduced to achieve signal separation and extraction, thereby reducing the cost of the partial discharge monitoring device. In addition, according to the parameters when the three-phase signals of A, B, and C are QAM modulated inside the partial discharge monitoring device, the combined output signal of the shared output port is input into the signal separation model corresponding to the modulation parameters, improving the signal separation efficiency and adapting to various working conditions. This provides strong support for the state monitoring and fault prevention of the power system under complex working conditions. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for description in the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 is the implementation flowchart of the partial discharge signal detection method provided by an embodiment of the present application;

[0018] Figure 2 is the implementation flowchart of the partial discharge signal detection method provided by another embodiment of the present application;

[0019] Figure 3 is the structural schematic diagram of the partial discharge signal detection device provided by an embodiment of the present application;

[0020] Figure 4 is the structural schematic diagram of the electronic device provided by an embodiment of the present application. Detailed implementation manners

[0021] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0022] The terms "first", "second", etc. in the specification, claims, and the above accompanying drawings of the embodiments of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances for the embodiments of the present application described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0023] Unless otherwise specified, the term "plurality" means two or more. The character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B. The term "and / or" is an associative relationship describing objects and indicates that three relationships can exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0024] The terms used in this application are only for describing the embodiments and do not limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element.

[0025] In this application, what each embodiment focuses on illustrating may be the differences from other embodiments, and the same or similar parts among the various embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, the relevant parts may refer to the description of the method part.

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0027] Figure 1 is the implementation flowchart of the partial discharge signal detection method provided by an embodiment of this application. As Figure 1 shown, the method includes the following steps:

[0028] S101, obtain the combined output signal of the common output port. Among them, the combined output signal includes the three-phase signals A, B, and C after QAM.

[0029] The execution subject of each embodiment of this application can be a device with data processing functions such as a server, a processor, a microprocessor, etc. In the actual implementation process, the specific implementation manner of the execution subject can be selected according to actual needs, and this embodiment does not make special limitations on this, as long as it is a device with data processing functions.

[0030] In the embodiments of this application, in order to simplify the structure of the partial discharge signal detection device and reduce the volume of the device, a hardware setting method with three input ports and one common output port is adopted. This structural setting reduces the hardware cost of the device.

[0031] To better determine the information of each of the three phases A, B, and C, it is necessary to analyze the composite output signal from the shared output port. This application aims to provide a composite output signal separation solution different from the hardware structure. Based on the method of mathematical modeling, multiple signals mixed together are separated. During the actual implementation process, the signal separation model can be optimized and updated according to the actual situation, which can not only improve the efficiency and accuracy of signal separation, but also reduce the maintenance cost and improve the stability and reliability of the system.

[0032] QAM is a modulation method that performs amplitude modulation on two orthogonal carriers. These two carriers are usually sine waves with a phase difference of 90 degrees (π / 2). Its working principle is that the transmitted data is divided into two paths in the bit / symbol encoder, each being 1 / 2 of the original two signals, and then multiplied by a pair of orthogonal modulation components respectively, and the sum is output.

[0033] In the embodiment of this application, basic carrier signals are respectively set for the three-phase signals of A, B, and C, and orthogonal modulation is performed on each of the three phases of A, B, and C, and then the modulation results of the three phases are summed and output.

[0034] QAM is suitable for digital signal modulation because it can simultaneously use the amplitude and phase changes of the signal to transmit information. QAM technology realizes efficient data transmission by mapping digital data to the amplitude and phase of two orthogonal carriers. This modulation method can transmit more data within the same bandwidth. Therefore, using it for the output of partial discharge signals can meet the requirements of high-speed data transmission.

[0035] S102, Obtain the modulation parameters when the three-phase signals of A, B, and C are subjected to QAM inside the partial discharge monitor, and obtain the corresponding pre-trained signal separation model according to the modulation parameters.

[0036] Among them, the modulation parameters include the modulation parameters for each of the three-phase signals of A, B, and C, including one or more of the basic carrier signal, modulation order, modulation points, and modulation depth.

[0037] In the specific implementation process, when the basic carrier signals corresponding to each phase signal are the same, the corresponding signal separation model is set according to different modulation orders, modulation points, and modulation depths to adapt to various different partial discharge monitoring requirements.

[0038] The pre-trained signal separation model can directly obtain the recognition model when detecting partial discharge signals, so as to efficiently process the partial discharge monitoring signals and realize the separation and recognition of the signals.

[0039] S103, Input the composite output signal into the signal separation model to obtain the single-phase output signals corresponding to each of the three phases A, B, and C.

[0040] After obtaining the single-phase output signal, a more in-depth analysis of the equipment insulation performance is carried out based on each phase signal, which is used for fault diagnosis and triggering of protection devices to ensure the safe operation of the power system.

[0041] In this embodiment, by configuring a shared output port for the partial discharge signal detection device, the integrated output of the information of the three input ports is realized. A signal separation model is introduced to achieve signal separation and extraction, thereby reducing the cost of the partial discharge monitoring device. In addition, according to the parameters during QAM modulation of the three-phase signals of A, B, and C inside the partial discharge monitoring device, the comprehensive output signal of the shared output port is input into the signal separation model corresponding to the modulation parameters, improving the signal separation efficiency and adapting to various working conditions. This provides strong support for the state monitoring and fault prevention of the power system under complex working conditions.

[0042] In the embodiment of the present application, in order to accurately separate the three-phase signals of A, B, and C from the comprehensive output signal, it is necessary to train the signal separation model in advance.

[0043] In a possible implementation manner, before obtaining the comprehensive output signal of the shared output port, it further includes:

[0044] Obtaining historical partial discharge training samples under the same modulation parameters; wherein, the historical partial discharge training samples include: historical three-phase signals of A, B, and C and the corresponding comprehensive output signal of the shared output port;

[0045] Preprocessing the historical partial discharge training samples, and dividing the preprocessed historical partial discharge training samples into a first training set and a second training set;

[0046] Training the model to be trained according to the first training set to obtain an initial model;

[0047] Performing parameter tuning training on the initial model according to the second training set, and obtaining a signal separation model.

[0048] Before training the signal separation model, some preparatory work needs to be done. First, collect historical partial discharge training samples under the same modulation parameters. These historical partial discharge training samples contain historical three-phase signals of A, B, and C and their corresponding comprehensive output signals of the shared output port. Second, during signal transmission, noise and outliers will be generated due to different influences. Therefore, preprocess these historical partial discharge training samples to eliminate the influence of noise and outliers on the signals. After preprocessing, divide the historical partial discharge training samples into two parts: a first training set and a second training set. These two training sets are respectively used for model training and optimization.

[0049] After dividing the training set, the initial model is trained using the first training set. After a certain number of iterative calculations, an initial model is obtained. To some extent, this initial model already has the ability to separate signals. However, to further improve the separation effect, it needs to be further optimized.

[0050] After that, the initial model is trained for parameter tuning using the second training set. After a period of training, a signal separation model with better performance is obtained, enabling the signal separation model to achieve a better separation effect when processing new input signals.

[0051] In this embodiment, first, historical partial discharge training samples are collected and preprocessed. Subsequently, the preprocessed training samples are divided into two parts, which are respectively used to train the initial model and optimize the model parameters, so as to obtain a signal separation model with good performance, thereby effectively realizing the separation and recognition of complex signals.

[0052] Before training the signal separation model, some preparatory work needs to be done. First, historical partial discharge training samples under the same modulation parameters are collected. These historical partial discharge training samples include historical three-phase signals of A, B, and C and the combined output signals of their corresponding common output ports. Secondly, during the signal transmission process, noise and outliers will be generated due to various influences.

[0053] In a possible implementation, the preprocessing of historical partial discharge training samples includes:

[0054] Obtain the phase-resolved partial discharge (PRPD) maps of historical partial discharge training samples, including the PRPD maps of the three-phase signals of A, B, and C and the combined output signal of the corresponding common output port;

[0055] Perform image denoising, image scaling, image grayscale conversion, image binarization, and image enhancement on the PRPD maps of historical partial discharge training samples.

[0056] In the specific implementation process, information such as probability intensity, average intensity, and discharge frequency is determined based on the PRPD maps for partial discharge signal monitoring.

[0057] The PRPD maps intuitively illustrate the partial discharge activities. However, the actually collected PRPD maps are blurred and incomplete in information. Therefore, in order to more accurately determine the three-phase signals of A, B, and C, preprocessing is required. To eliminate the noise in the maps to make the information clear and definite, facilitate observation and analysis, improve the signal quality, and meet the analysis and recognition requirements in different scenarios.

[0058] Optionally, the implementation methods of each preprocessing process are as follows:

[0059] Image denoising: The DBSCAN clustering algorithm is used to process the original image to obtain the initial image;

[0060] Image scaling: The bilinear interpolation algorithm is used to scale the initial image to obtain the discharge area image;

[0061] Image grayscale processing: The discharge area image is grayscaled to obtain the grayscale image;

[0062] Image binarization: The grayscale image is binarized to obtain the binary image;

[0063] Image enhancement: The pixels of the binary image are normalized to the range [0, 1] to obtain the normalized image;

[0064] Feature data: Extract the feature data of the normalized image and construct the feature vector.

[0065] In other embodiments, optionally, preprocess the historical partial discharge training samples through other image denoising, image scaling, image grayscale processing, image binarization, or image enhancement, or, on the basis of image denoising, image scaling, image grayscale processing, image binarization, or image enhancement, combine other preprocessing methods to improve the accuracy of the training sample data and avoid the influence of noise signals on the model training effect.

[0066] In one possible implementation, the historical partial discharge training samples are divided into a first training set and a second training set, including:

[0067] Divide the A, B, and C phase signals in the historical partial discharge training samples according to a set range interval; wherein, the set range interval includes three or more.

[0068] Randomly obtain data from each set range interval according to the same data volume ratio and construct the first training set and the second training set.

[0069] In the specific implementation process, the historical partial discharge training samples usually include the partial discharge data of the A, B, and C phase signals collected under specific conditions (such as different voltage levels, different load states, etc.). There is a certain correlation between the magnitudes of the A, B, and C phase signals and the specific conditions. These signals mainly include voltage values or current values.

[0070] In order to better analyze these historical partial discharge training samples, it is necessary to preprocess the A, B, and C phase signals first. This process mainly includes dividing the signals according to a preset range interval. Among them, the set range interval needs to contain three or more sub-intervals to help better understand the variation law of the signals and thus lay a foundation for subsequent analysis.

[0071] The determination of the set range interval is not arbitrary, but needs to be determined by clustering analysis based on the values of the signals of the three phases A, B, and C in the historical partial discharge training samples. And the number of sub-intervals of the set range interval should not be too many to ensure that each interval has sufficient sample data and model training efficiency.

[0072] Among them, an example is given for the clustering analysis of the set range interval according to the signal values of the three phases A, B, and C in the historical partial discharge training samples. Among them, the signals of the three phases A, B, and C contain voltage information; through clustering analysis, it is found that the voltage value range in the historical partial discharge training samples is 10V to 380V, the voltage values are concentrated in the range of 50V to 220V, and the voltage information less than 50V and the voltage values greater than 220V are relatively few. Then, according to the clustering analysis results, the range can be divided into three sub-intervals: 10V to 50V, 50V to 220V, and 220V to 380V.

[0073] After that, it is necessary to select data according to the range interval to construct a training sample set to ensure that the data training sample set includes the data in each sub-interval of the range interval, improve the applicability of the samples to partial discharge signals in different ranges, and avoid problems of overfitting or underfitting of the model caused by uneven division of the training set.

[0074] In this embodiment, the signals of the three phases A, B, and C in the historical partial discharge training samples are divided according to the set range interval, so as to more clearly understand the distribution law of the signals of the three phases A, B, and C, and provide support for subsequent analysis and application. In the specific implementation process, the divided interval can also be adjusted according to needs to meet the requirements in different scenarios, which helps to better understand the working state of electrical equipment and provide guarantee for preventing potential faults.

[0075] In another possible implementation, the historical partial discharge training samples are divided into a first training set and a second training set, including:

[0076] The historical partial discharge training samples are randomly divided into a first training set and a second training set according to a set ratio; among them, the ratio corresponding to the first training set is greater than that of the second training set. Optionally, the set ratios corresponding to the first training set and the second training set are 7:3 or 6:4 or 8:2.

[0077] In a possible implementation, before inputting the output signal into the signal separation model, it further includes:

[0078] Denoise the comprehensive output signal.

[0079] Noise is an inevitable problem during signal transmission, which can seriously affect the accurate identification and separation of signals. Therefore, before applying the output signal to the signal separation model, it is a crucial step to perform denoising processing on the combined output signal. The purpose of this denoising process is to eliminate noise interference and restore the true appearance of the signal, thereby improving the accuracy of signal separation.

[0080] In this embodiment, the main objective of denoising the combined output signal is to handle obvious outliers. Outliers refer to some data points in the dataset that deviate significantly from the normal data. They may be caused by noise or errors during data acquisition or processing. Handling these outliers helps improve the effect of signal separation, making the final output signal more accurate and reliable.

[0081] In a possible implementation, the denoising process for the combined output signal includes:

[0082] After filtering the combined output signal, the improved wavelet threshold method is used for denoising.

[0083] Among them, the principle of the wavelet threshold method is to decompose the signal simultaneously in the time domain and frequency domain using wavelet transform to obtain multi-scale wavelet coefficients. Noise usually has greater energy in the high-frequency detail part, while the important features of the signal often concentrate in the low-frequency or specific scales. Therefore, the wavelet threshold method sets a threshold for the wavelet coefficients, regards the wavelet coefficients below the threshold as noise and sets them to zero or reduces their amplitude, and retains or moderately adjusts the coefficients above the threshold, thereby achieving signal denoising and detail restoration. The wavelet threshold method is applicable to the processing of non-stationary partial discharge signals, effectively removing noise while retaining the important features of the signal and improving the signal quality.

[0084] In other possible implementations, filtering denoising processing is performed through methods such as mean filtering, median filtering, Gaussian filtering, and adaptive filtering.

[0085] Figure 2 is the implementation flowchart of the partial discharge signal detection method provided by an embodiment of this application. As Figure 2 shown, the method includes the following steps:

[0086] S201, obtain the combined output signal of the common output port. Among them, the combined output signal includes the three-phase signals A, B, and C after QAM.

[0087] S202, obtain the modulation parameters when the three-phase signals A, B, and C are QAM modulated inside the partial discharge monitor, and obtain the corresponding pre-trained signal separation model according to the modulation parameters.

[0088] In S203, after filtering the composite output signal, denoising is performed using an improved wavelet threshold method.

[0089] In S204, the composite output signal after filtering and denoising is input into the signal separation model to obtain the single-phase output signals corresponding to each of the three phases A, B, and C.

[0090] In this embodiment, by configuring a shared output port for the partial discharge signal detection device, the integrated output of the information of the three input ports is realized. A signal separation model is introduced to achieve signal separation and extraction, thereby reducing the cost of the partial discharge monitoring device. In addition, according to the parameters during QAM modulation of the signals of the three phases A, B, and C inside the partial discharge monitoring device, the composite output signal of the shared output port is input into the signal separation model corresponding to the modulation parameters, improving the signal separation efficiency and adapting to various working conditions. In addition, before inputting the composite output signal into the signal separation model, filtering and denoising processing is performed to reduce the influence of noise signals on the signal separation result and improve the signal separation accuracy. It provides strong support for the state monitoring and fault prevention of the power system under complex working conditions.

[0091] In a possible implementation manner, after inputting the composite output signal into the signal separation model to obtain the single-phase output signals corresponding to each of the three phases A, B, and C, it further includes:

[0092] Determine the partial discharge type according to the single-phase output signals corresponding to each of the three phases A, B, and C.

[0093] In a specific embodiment, the partial discharge signal types are roughly divided into the following categories:

[0094] Corona discharge: This common form of partial discharge occurs when charges are directly dissipated from the sharp surface of a conductor into the air. It is the cause of sound and radio frequency emissions, but generally does not need to be overly concerned from the perspective of damage or safety.

[0095] Arc discharge: Arc discharge is a long-term discharge generated by gas breakdown. When current flows through air or any other normally non-conductive medium, plasma is generated.

[0096] Surface discharge: When the discharge propagates along the insulation surface, it is called surface discharge or surface tracking. This may be one of the most destructive types of partial discharge.

[0097] Air gap (internal) discharge: This is usually caused by defects in solid insulation such as cables, bushings, and GIS joints insulation. Air gap discharge is extremely destructive to insulation and usually continues to expand until they cause complete failure.

[0098] After separating the single-phase output signals corresponding to each of the three phases A, B, and C, the type of partial discharge signal is further determined to facilitate relevant personnel to intuitively and quickly determine the repair or maintenance plan.

[0099] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0100] The following is an apparatus embodiment of the present application. For details not described in detail, reference may be made to the corresponding method embodiments above.

[0101] Figure 3 is a schematic structural diagram of a partial discharge signal detection apparatus provided by an embodiment of the present application. As Figure 3 shown, for the sake of convenience of description, only the parts related to the embodiments of the present application are shown. As Figure 3 shown, the apparatus includes:

[0102] A signal acquisition module 301, configured to acquire a combined output signal of a common output port; wherein, the combined output signal includes the three-phase signals of A, B, and C after QAM;

[0103] A model acquisition module 302, configured to acquire modulation parameters when the three-phase signals of A, B, and C are QAM modulated inside the partial discharge monitor, and acquire a corresponding pre-trained signal separation model according to the modulation parameters;

[0104] A determination module 303, configured to input the combined output signal into the signal separation model to acquire the single-phase output signals corresponding to each of the three phases A, B, and C.

[0105] In a possible implementation manner, the apparatus further includes a training module, configured to:

[0106] Acquire historical partial discharge training samples under the same modulation parameters; wherein, the historical partial discharge training samples include: historical three-phase signals of A, B, and C and the corresponding combined output signal of the common output port;

[0107] Preprocess the historical partial discharge training samples, and divide the preprocessed historical partial discharge training samples into a first training set and a second training set;

[0108] Train the model to be trained according to the first training set to obtain an initial model;

[0109] Perform parameter tuning training on the initial model according to the second training set, and obtain a signal separation model.

[0110] In a possible implementation manner, the training module is specifically configured to:

[0111] Obtain the PRPD maps of historical partial discharge training samples, including the PRPD maps of the signals of three phases A, B, and C and the comprehensive output signal of the corresponding shared output port;

[0112] Perform image denoising, image scaling, image grayscaling, image binarization, and image enhancement processing on the PRPD maps of historical partial discharge training samples;

[0113] Based on the processed PRPD maps of historical partial discharge training samples, extract the signals of three phases A, B, and C and the comprehensive output signal to divide them into a first training set and a second training set.

[0114] In a possible implementation manner, the training module is specifically used for:

[0115] Divide the signals of three phases A, B, and C in the historical partial discharge training samples according to a set range interval; where the set range interval includes three or more.

[0116] Randomly obtain data from each set range interval according to the same data volume ratio and construct a first training set and a second training set.

[0117] In a possible implementation manner, the device further includes a denoising module for denoising the comprehensive output signal.

[0118] In a possible implementation manner, the denoising module is specifically used for: after filtering the comprehensive output signal, perform denoising using an improved wavelet threshold method.

[0119] In a possible implementation manner, the device further includes a partial discharge type determination module for determining the partial discharge type according to the single-phase output signals corresponding to the three phases A, B, and C.

[0120] In this embodiment, by configuring a shared output port for the partial discharge signal detection device, the integrated output of the information of three input ports is realized. A signal separation model is introduced to realize the separation and extraction of signals, thereby reducing the cost of the partial discharge monitoring device. In addition, according to the parameters during QAM modulation of the signals of three phases A, B, and C inside the partial discharge monitoring device, the comprehensive output signal of the shared output port is input into the signal separation model corresponding to the modulation parameters, improving the signal separation efficiency and adapting to various working conditions. This provides strong support for the state monitoring and fault prevention of the power system under complex working conditions.

[0121] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 4As shown, the electronic device 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-described embodiments of each partial discharge signal detection method are implemented, such as Figure 1 the steps shown. Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-described device embodiments are implemented, such as Figure 3 the functions of the modules shown.

[0122] Exemplarily, the computer program 42 may be divided into one or more modules / units. The one or more modules / units are stored in the memory 41 and executed by the processor 40 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 42 in the electronic device 4. For example, the computer program 42 may be divided into Figure 3 the modules shown.

[0123] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art can understand that Figure 4 these are merely examples of the electronic device 4 and do not constitute a limitation on the electronic device 4. It may include more or fewer components than shown in the figure, or combine certain components, or have different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0124] The so-called processor 40 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0125] The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 4. Further, the memory 41 may also include both the internal storage unit and the external storage device of the electronic device 4. The memory 41 is used to store the computer program and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store the data that has been output or will be output.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0127] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this application can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0129] In the embodiments provided in this application, it should be understood that the disclosed device / electronic device and method can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0132] If the integrated module / 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 storage medium. Based on this understanding, to implement all or part of the processes in the above embodiment methods of this application, it can also be completed by a computer program instructing the relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned embodiments of the partial discharge signal detection method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0133] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting a partial discharge signal, characterized in that: The partial discharge signal detection device comprises three input ports and one common output port; the method comprises: Obtaining a comprehensive output signal of the common output port; wherein the comprehensive output signal includes A, B, and C three-phase signals after quadrature amplitude modulation (QAM); Obtaining modulation parameters when QAM is performed on the three-phase signals A, B, and C inside the partial discharge monitor, and obtaining a corresponding pre-trained signal separation model according to the modulation parameters; Input the integrated output signal into the signal separation model to obtain the single-phase output signals corresponding to the three phases A, B and C respectively; Wherein, before obtaining the integrated output signal of the common output port, the method further includes: Obtain historical partial discharge training samples under the same modulation parameters; wherein the historical partial discharge training samples include: historical A, B, C three-phase signals and the integrated output signal of the corresponding common output port; Preprocessing the historical partial discharge training samples, and dividing the preprocessed historical partial discharge training samples into a first training set and a second training set; Training the model to be trained according to the first training set to obtain an initial model; Performing parameter tuning training on the initial model according to the second training set to obtain a signal separation model; The preprocessing of the historical partial discharge training samples includes: Obtaining the PRPD spectrum of the historical partial discharge training sample, including the PRPD spectrum of the three-phase signals A, B, and C and the corresponding integrated output signal of the common output port; Performing image denoising, image scaling, image grayscale conversion, image binarization and image enhancement processing on the PRPD atlas of the historical partial discharge training samples; Based on the processed PRPD spectrum of historical partial discharge training samples, the three-phase signals A, B, and C and the comprehensive output signal are extracted to divide them into the first training set and the second training set.

2. The method according to claim 1, characterized in that The dividing the historical partial discharge training samples into a first training set and a second training set comprises: The three-phase signals A, B, and C in the historical partial discharge training samples are divided according to a set range interval; wherein the set range interval includes three or more; Data are randomly acquired from each set range according to the same data volume ratio, and a first training set and a second training set are constructed.

3. The method according to claim 1 or 2, characterized in that: Before inputting the output signal into the signal separation model, the method further includes: The integrated output signal is subjected to denoising processing.

4. The method according to claim 3, characterized in that The denoising process of the integrated output signal comprises: After filtering the integrated output signal, the improved wavelet threshold method is used to perform denoising.

5. The method according to claim 1, characterized in that After inputting the integrated output signal into the signal separation model to obtain the single-phase output signals corresponding to the three phases A, B and C, the method further includes: Determine the type of partial discharge based on the single-phase output signals corresponding to phases A, B, and C.

6. A partial discharge signal detection device for executing the partial discharge signal detection method according to any one of claims 1 to 5, characterized in that: include: A signal acquisition module, used to acquire a comprehensive output signal of the common output port; wherein the comprehensive output signal includes A, B, and C three-phase signals after QAM; A model acquisition module is used to obtain the modulation parameters when QAM is performed on the three-phase signals A, B, and C inside the partial discharge monitor, and obtain the corresponding pre-trained signal separation model according to the modulation parameters; The determination module is used to input the comprehensive output signal into the signal separation model to obtain the single-phase output signals corresponding to the three phases A, B, and C respectively.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images