Discharge detection method and device, computer equipment and storage medium
By extracting and identifying features from ultrasonic partial discharge data of power equipment, and using CW-DCGAN and MobileNet-V3 models, the problem of low accuracy in discharge detection of power equipment was solved, and efficient and accurate discharge detection results were achieved.
Patent Information
- Application Number
- CN202510922299.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-04
- Publication Date
- 2025-11-07
AI Technical Summary
Existing technologies have low accuracy in detecting discharge in power equipment, making it impossible to accurately obtain the actual partial discharge status of power equipment.
By determining the ultrasonic partial discharge data of the power equipment to be tested, signal framing, frame shifting, and short-time Fourier transform processing are performed to extract ultrasonic time-domain and frequency-domain samples. Combined with the CW-DCGAN model and the MobileNet-V3 model, discharge features are extracted and identified to obtain comprehensive discharge features and achieve partial discharge detection.
It enables accurate acquisition of discharge detection results from power equipment, avoiding the limitations of manual detection and large amounts of training data, and improving the efficiency and accuracy of discharge detection.
Smart Images
Figure CN120908608A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of partial discharge monitoring, and in particular to a discharge detection method and device, computer equipment and a storage medium. BACKGROUND
[0002] As an economic and clean energy, electric energy is widely used in various production activities. At present, the construction of power systems has made remarkable progress, and with the demand for production and economic growth, the scale of power systems is still expanding. Different types of faults will inevitably occur in the long-term operation of power equipment. By detecting partial discharge, the operating state of power equipment can be detected, problems can be found in time, and the reliable operation of equipment can be ensured.
[0003] However, the discharge detection accuracy of the prior art for power equipment is low, and the actual partial discharge of the power equipment cannot be accurately obtained. SUMMARY
[0004] Therefore, it is necessary to provide a discharge detection method, device, computer equipment and storage medium capable of accurately obtaining the discharge detection result of the power equipment to be detected.
[0005] In a first aspect, the present application provides a discharge detection method. The method comprises:
[0006] determining ultrasonic partial discharge data of a power equipment to be detected;
[0007] extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0008] performing partial discharge detection on the power equipment to be detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected.
[0009] In one embodiment, the method further comprises:
[0010] performing data enhancement processing on the ultrasonic partial discharge data to obtain ultrasonic time domain samples and ultrasonic frequency domain samples under different partial discharge types;
[0011] determining the comprehensive discharge features corresponding to the power equipment to be detected according to the ultrasonic time domain samples and the ultrasonic frequency domain samples.
[0012] In one embodiment, the method further comprises:
[0013] performing feature parameter extraction on the ultrasonic time domain samples to obtain ultrasonic time domain features;
[0014] performing feature parameter extraction on the ultrasonic frequency domain samples to obtain ultrasonic frequency domain features;
[0015] performing feature fusion on the ultrasonic time domain features and the ultrasonic frequency domain features to obtain comprehensive discharge features corresponding to the to-be-detected power equipment.
[0016] In one of the embodiments, the partial discharge detection of the to-be-detected power equipment according to the comprehensive discharge features to obtain the discharge detection result of the to-be-detected power equipment comprises:
[0017] performing partial discharge detection of the to-be-detected power equipment according to the comprehensive discharge features to obtain at least one candidate partial discharge type corresponding to the to-be-detected power equipment and an identification accuracy of each candidate partial discharge type;
[0018] determining the discharge detection result of the to-be-detected power equipment according to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type.
[0019] In one of the embodiments, the determining of the discharge detection result of the to-be-detected power equipment according to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type comprises:
[0020] taking a candidate partial discharge type with the highest identification accuracy in the at least one candidate partial discharge type as a target partial discharge type of the to-be-detected power equipment;
[0021] taking the target partial discharge type and the identification accuracy of the target partial discharge type as the discharge detection result of the to-be-detected power equipment.
[0022] In one of the embodiments, the determining of the ultrasonic partial discharge data of the to-be-detected power equipment comprises:
[0023] obtaining ultrasonic initial data of the to-be-detected power equipment;
[0024] performing preprocessing on the ultrasonic initial data to obtain ultrasonic partial discharge data of the to-be-detected power equipment; wherein the preprocessing comprises at least one of signal framing processing, frame shifting processing, windowing processing and short-time Fourier transform processing.
[0025] In a second aspect, the present application further provides a discharge detection device. The device comprises:
[0026] determining ultrasonic partial discharge data of a power equipment to be detected;
[0027] extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0028] detecting partial discharge of the power equipment to be detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected.
[0029] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor implements the following steps when executing the computer program:
[0030] determining ultrasonic partial discharge data of a power equipment to be detected;
[0031] extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0032] detecting partial discharge of the power equipment to be detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected.
[0033] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:
[0034] determining ultrasonic partial discharge data of a power equipment to be detected;
[0035] extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0036] detecting partial discharge of the power equipment to be detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected.
[0037] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the following steps:
[0038] determining ultrasonic partial discharge data of a power equipment to be detected;
[0039] extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0040] According to the comprehensive discharge feature, the partial discharge detection is performed on the to-be-detected power equipment, and a discharge detection result of the to-be-detected power equipment is obtained.
[0041] The discharge detection method, the device, the computer equipment and the storage medium have the following advantages. The ultrasonic partial discharge data of the to-be-detected power equipment is determined, and the comprehensive discharge feature corresponding to the to-be-detected power equipment is extracted from the ultrasonic partial discharge data. Then, the partial discharge detection is performed on the to-be-detected power equipment according to the comprehensive discharge feature, and the discharge detection result of the to-be-detected power equipment is obtained. According to the above content, when the partial discharge detection is performed on the to-be-detected power equipment, the ultrasonic partial discharge data of the to-be-detected power equipment is obtained first. Then, the discharge feature extraction is performed on the ultrasonic partial discharge data of the to-be-detected power equipment, and the comprehensive discharge feature corresponding to the to-be-detected power equipment is obtained. The comprehensive discharge feature fully reflects the partial discharge condition of the to-be-detected power equipment. Since the comprehensive discharge feature is extracted from the ultrasonic partial discharge data and is used to fully reflect the partial discharge condition of the to-be-detected power equipment, the partial discharge detection is performed on the to-be-detected power equipment according to the comprehensive discharge feature. Therefore, the discharge detection result of the to-be-detected power equipment can be accurately obtained, and the discharge detection result can accurately reflect the actual condition of the to-be-detected power equipment. In addition, in the process of obtaining the discharge detection result of the to-be-detected power equipment, the ultrasonic partial discharge sample data does not need to be obtained. The limitation that the manual detection and a large amount of training data are required in the existing discharge detection technology is avoided, and the efficiency and accuracy of the discharge detection are ensured. BRIEF DESCRIPTION OF DRAWINGS
[0042] Figure 1 An application environment diagram of a discharge detection method provided by an embodiment of the present application is shown in the figure.
[0043] Figure 2 A flowchart of a first discharge detection method provided by an embodiment of the present application is shown in the figure.
[0044] Figure 3 A flowchart of a second discharge detection method provided by an embodiment of the present application is shown in the figure.
[0045] Figure 4 A flowchart of a third discharge detection method provided by an embodiment of the present application is shown in the figure.
[0046] Figure 5 A flowchart of a fourth discharge detection method provided by an embodiment of the present application is shown in the figure.
[0047] Figure 6 A structural block diagram of a discharge detection device provided by an embodiment of the present application is shown in the figure.
[0048] Figure 7This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0050] The discharge detection method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed in the cloud or on other network servers. By determining the ultrasonic partial discharge data of the power equipment to be tested, the comprehensive discharge characteristics corresponding to the power equipment to be tested are extracted from the ultrasonic partial discharge data; then, based on the comprehensive discharge characteristics, partial discharge detection is performed on the power equipment to be tested to obtain the discharge detection result of the power equipment to be tested. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.
[0051] In one embodiment, such as Figure 2 As shown, a discharge detection method is provided, which can be applied to... Figure 1 Taking server 104 as an example, the following steps are included:
[0052] S201, Determine the ultrasonic partial discharge data of the electrical equipment to be tested.
[0053] It should be noted that ultrasonic partial discharge data can refer to electrical signal data converted from mechanical vibration signals generated by partial discharge inside electrical equipment, which are collected by a piezoelectric sensor. Since different types of faults inevitably occur during the operation of the electrical equipment under test, and different types of faults will affect the value of ultrasonic partial discharge data, the operating status of electrical equipment can be detected by acquiring ultrasonic partial discharge data, so as to detect problems in time and ensure the reliable operation of the equipment.
[0054] Further, in order to ensure that the ultrasonic partial discharge data can effectively ensure the accuracy of subsequent partial discharge detection of the to-be-detected power equipment, in the process of determining the ultrasonic partial discharge data of the to-be-detected power equipment, the following content can be included: obtaining ultrasonic initial data of the to-be-detected power equipment; and pre-processing the ultrasonic initial data to obtain the ultrasonic partial discharge data of the to-be-detected power equipment.
[0055] The pre-processing includes at least one of signal frame processing, frame shift processing, windowing processing, and short-time Fourier transform processing.
[0056] In an embodiment of the present application, the ultrasonic initial data of the to-be-detected power equipment is obtained, and the signal frame processing is performed on the ultrasonic initial data, so that the signal frame length of the ultrasonic initial data is 256; the frame shift amount is set to 1 / 3 of the frame length to implement the frame shift processing on the ultrasonic initial data; the Hamming window can be used as the window function for the windowing processing on the ultrasonic initial data; and then the ultrasonic initial data after the above operations is subjected to the short-time Fourier transform to construct the ultrasonic time domain sample and the ultrasonic frequency domain sample of the to-be-detected power equipment under the current working condition. At this time, the ultrasonic time domain sample and the ultrasonic frequency domain sample of the to-be-detected power equipment under the current working condition are the ultrasonic partial discharge data of the to-be-detected power equipment.
[0057] The expression of the short-time Fourier transform of the ultrasonic partial discharge sample using the Hamming window as the window function is as follows:
[0058]
[0059] Wherein, u(t) is the partial discharge ultrasonic signal to be analyzed, w(t) is the window function, f is the frequency, t is the time, and τ is the time variable.
[0060] S202, performing discharge feature extraction on the ultrasonic partial discharge data to obtain the comprehensive discharge feature corresponding to the to-be-detected power equipment.
[0061] It should be noted that when the discharge feature extraction is performed on the ultrasonic partial discharge data, the following content can be included: performing data enhancement processing on the ultrasonic partial discharge data to obtain the ultrasonic time domain sample and the ultrasonic frequency domain sample under different partial discharge types; and determining the comprehensive discharge feature corresponding to the to-be-detected power equipment according to the ultrasonic time domain sample and the ultrasonic frequency domain sample.
[0062] S203, performing partial discharge detection on the to-be-detected power equipment according to the comprehensive discharge feature to obtain the discharge detection result of the to-be-detected power equipment.
[0063] In an embodiment of the present application, when partial discharge detection needs to be performed on the to-be-detected power equipment, the cross-entropy loss can be introduced into the loss function of the MobileNet-V3 model to replace the original Softmax function, the partial discharge identification is performed on the comprehensive discharge features, and then the discharge detection result of the to-be-detected power equipment is output.
[0064] The purpose of introducing the cross-entropy loss into the loss function of the model to replace the original Softmax function is to improve the convergence speed of the model.
[0065] The discharge detection method determines the ultrasonic partial discharge data of the to-be-detected power equipment, extracts the comprehensive discharge features corresponding to the to-be-detected power equipment from the ultrasonic partial discharge data, and then performs partial discharge detection on the to-be-detected power equipment according to the comprehensive discharge features to obtain the discharge detection result of the to-be-detected power equipment. According to the above content, when performing partial discharge detection on the to-be-detected power equipment, the ultrasonic partial discharge data of the to-be-detected power equipment is first obtained, and then the discharge feature extraction is performed on the ultrasonic partial discharge data of the to-be-detected power equipment to obtain the comprehensive discharge features corresponding to the to-be-detected power equipment, so that the comprehensive discharge features fully reflect the partial discharge condition of the to-be-detected power equipment. Since the comprehensive discharge features are extracted from the ultrasonic partial discharge data to fully reflect the partial discharge condition of the to-be-detected power equipment, the partial discharge detection is performed on the to-be-detected power equipment according to the comprehensive discharge features, so that the discharge detection result of the to-be-detected power equipment can be accurately obtained, and the discharge detection result can accurately reflect the actual condition of the to-be-detected power equipment. In the process of obtaining the discharge detection result of the to-be-detected power equipment, the ultrasonic partial discharge sample data is not required, which avoids the limitations of manual detection and a large amount of training data in the existing discharge detection technology, and ensures the efficiency and accuracy of the discharge detection.
[0066] In an embodiment, as shown in Figure 3 When the discharge feature extraction needs to be performed on the ultrasonic partial discharge data to obtain the comprehensive discharge features corresponding to the to-be-detected power equipment, the following content can be included:
[0067] S301, performing data enhancement processing on the ultrasonic partial discharge data to obtain ultrasonic time domain samples and ultrasonic frequency domain samples under different partial discharge types.
[0068] It should be noted that when the data enhancement processing needs to be performed on the ultrasonic partial discharge data, the constraint condition of the ultrasonic time-frequency feature can be constructed, and then the sample generation is performed by the CW-DCGAN model to obtain the ultrasonic time domain samples and the ultrasonic frequency domain samples under different partial discharge types.
[0069] The CW-DCGAN model is obtained by adding a constraint condition to the discriminator of the DCGAN model, and adopting a Wasserstein distance as a loss function, and replacing a weight clipping with a gradient penalty.
[0070] In an embodiment of the present application, ultrasonic partial discharge sample data, ultrasonic time domain samples corresponding to the ultrasonic partial discharge sample data, and ultrasonic frequency domain samples corresponding to the ultrasonic partial discharge sample data are obtained in advance, and the generator of the CW-DCGAN model is trained by using the ultrasonic partial discharge sample data to obtain predicted ultrasonic time domain samples and predicted ultrasonic frequency domain samples output by the generator; the predicted ultrasonic time domain samples and the predicted ultrasonic frequency domain samples, and real ultrasonic time domain samples and real ultrasonic frequency domain samples corresponding to the ultrasonic partial discharge sample data are input into the discriminator of the CW-DCGAN model, the parameters of the discriminator are fixed in the discriminator training stage, and label information of the ultrasonic partial discharge is added as a constraint condition in the discriminator, and the type information of the label includes air gap discharge, surface discharge, sharp discharge, and suspension discharge. The trained discriminator is used to identify the authenticity of the predicted ultrasonic time domain samples and the predicted ultrasonic frequency domain samples.
[0071] Finally, the Wasserstein distance is adopted as a loss function of the conditional deep convolutional neural network to represent the similarity between the real ultrasonic time domain samples and the real ultrasonic frequency domain samples and the predicted ultrasonic time domain samples and the predicted ultrasonic frequency domain samples, and the authenticity of the predicted ultrasonic time domain samples and the predicted ultrasonic frequency domain samples, and the greater the Wasserstein distance, the higher the authenticity of the predicted ultrasonic time domain samples and the predicted ultrasonic frequency domain samples; and the gradient penalty is introduced to replace the original weight clipping to solve the mode collapse and gradient vanishing problems.
[0072] The Wasserstein distance is adopted as the loss function of the CW-DCGAN model, and the gradient penalty is introduced, and the objective function V(D, G) in the training is:
[0073]
[0074] G represents the generator; D represents the discriminator; V represents the adversarial loss; c represents the conditional information; x represents the input ultrasonic time-frequency domain sample; is an image obtained by random interpolation between x ~ p g and x ~ p r λ is a coefficient of the gradient penalty function; D(x|c) represents the output of the discriminator under the condition of c, H (D|D) represents the entropy of data from real ultrasonic time domain samples and real ultrasonic frequency domain samples passing through the discriminator; H (D|D) represents the entropy of data from real ultrasonic time domain samples and real ultrasonic frequency domain samples passing through the discriminator; H (D|D) represents the entropy of data from real ultrasonic time domain samples and real ultrasonic frequency domain samples passing through the discriminator;
[0075] S302, according to the ultrasonic time domain sample and the ultrasonic frequency domain sample, determine the comprehensive discharge characteristic corresponding to the power equipment to be detected.
[0076] Need to be explained, when need to according to ultrasonic time domain sample and ultrasonic frequency domain sample, determine the comprehensive discharge characteristic corresponding to the power equipment to be detected, can include the following contents: the feature parameter extraction is carried out to the ultrasonic time domain sample, obtains the ultrasonic time domain feature;The feature parameter extraction is carried out to the ultrasonic frequency domain sample, obtains the ultrasonic frequency domain feature;Ultrasonic time domain feature and ultrasonic frequency domain feature are fused, and the comprehensive discharge characteristic corresponding to the power equipment to be detected is obtained.
[0077] In an embodiment of the present application, the feature parameter extraction can be carried out to the ultrasonic time domain sample by the TE module, and the ultrasonic time domain feature is obtained;The cepstrum operation is carried out to the ultrasonic frequency domain sample, so as to achieve the purpose of extracting the feature parameter of the ultrasonic frequency domain sample and obtaining the ultrasonic frequency domain feature;Further, the parallel splicing operation is carried out to the ultrasonic time domain feature and the ultrasonic frequency domain feature, and the comprehensive discharge characteristic corresponding to the power equipment to be detected is obtained.
[0078] In another embodiment of the present application, the TE module is used to extract the ultrasonic time domain feature, and the TE module contains an up-sampling module and three feature extraction modules, the up-sampling module is composed of a one-dimensional convolution layer, the number of channels of which is determined by the number value on the frequency domain axis of the time-frequency spectrum feature map, the convolution kernel of the convolution layer is equal to the length of the selected window function in the short-time Fourier transform, and the step length of the convolution kernel is equal to the step length of the frame shift;Each convolution layer is followed by a batch normalization layer, which is used to speed up the convergence speed and help to improve the generalization ability;After one-dimensional convolution processing, the features are input into three feature extraction modules, the feature extraction module is composed of LayerNorm, ELU activation function and one-dimensional convolution with a convolution kernel size of 3, and the step length of the convolution kernel is 1.
[0079] The above discharge detection method realizes the determination of the comprehensive discharge characteristic corresponding to the power equipment to be detected according to the ultrasonic time domain sample and the ultrasonic frequency domain sample by obtaining the ultrasonic time domain sample and the ultrasonic frequency domain sample under different local discharge types, and ensures that the discharge detection result can accurately reflect the actual situation of the power equipment to be detected.
[0080] In an embodiment, asFigure 4 As shown, when it is needed to perform partial discharge detection on the to-be-detected power equipment according to the comprehensive discharge feature to obtain a discharge detection result of the to-be-detected power equipment, the following content can be included:
[0081] S401, performing partial discharge detection on the to-be-detected power equipment according to the comprehensive discharge feature to obtain at least one candidate partial discharge type corresponding to the to-be-detected power equipment and an identification accuracy of each candidate partial discharge type.
[0082] In an embodiment of the present application, when it is needed to perform partial discharge detection on the to-be-detected power equipment, the cross-entropy loss can be introduced into the loss function of the MobileNet-V3 model to replace the original Softmax function, and the comprehensive discharge feature is subjected to partial discharge identification to further output at least one candidate partial discharge type corresponding to the to-be-detected power equipment and an identification accuracy of each candidate partial discharge type.
[0083] S402, determining a discharge detection result of the to-be-detected power equipment according to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type.
[0084] In an embodiment of the present application, when it is needed to determine the discharge detection result of the to-be-detected power equipment, the candidate partial discharge type with the highest identification accuracy in the at least one candidate partial discharge type can be determined as a target partial discharge type of the to-be-detected power equipment, and the target partial discharge type and the identification accuracy of the target partial discharge type can be determined as the discharge detection result of the to-be-detected power equipment.
[0085] The above discharge detection method determines at least one candidate partial discharge type corresponding to the to-be-detected power equipment and an identification accuracy of each candidate partial discharge type, realizes selection of a target partial discharge type from the at least one candidate partial discharge type according to the identification accuracy, and further realizes determination of a discharge detection result of the to-be-detected power equipment. This process does not need to obtain the ultrasonic partial discharge sample data, avoids the limitations of the need for manual detection and a large amount of training data support in the existing discharge detection technology, and guarantees the efficiency and accuracy of the discharge detection.
[0086] In an embodiment, as shown in Figure 5 when it is needed to determine a discharge detection result of the to-be-detected power equipment, the following content can be included:
[0087] S501, obtaining ultrasonic initial data of the to-be-detected power equipment.
[0088] S502, pre-process the ultrasonic initial data to obtain ultrasonic partial discharge data of the power equipment to be detected; wherein the pre-processing includes at least one of signal frame processing, frame shift processing, windowing processing and short-time Fourier transform processing.
[0089] S503, performing data enhancement processing on the ultrasonic partial discharge data to obtain ultrasonic time domain samples and ultrasonic frequency domain samples under different partial discharge types.
[0090] S504, extracting feature parameters from the ultrasonic time domain samples to obtain ultrasonic time domain features.
[0091] S505, extracting feature parameters from the ultrasonic frequency domain samples to obtain ultrasonic frequency domain features.
[0092] S506, performing feature fusion on the ultrasonic time domain features and the ultrasonic frequency domain features to obtain comprehensive discharge features corresponding to the power equipment to be detected.
[0093] S507, performing partial discharge detection on the power equipment to be detected according to the comprehensive discharge features to obtain at least one candidate partial discharge type corresponding to the power equipment to be detected, and an identification accuracy of each candidate partial discharge type.
[0094] S508, taking a candidate partial discharge type with the highest identification accuracy in the at least one candidate partial discharge type as a target partial discharge type of the power equipment to be detected.
[0095] S509, taking the target partial discharge type and the identification accuracy of the target partial discharge type as a discharge detection result of the power equipment to be detected.
[0096] The discharge detection method determines the ultrasonic partial discharge data of the power equipment to be detected, extracts the comprehensive discharge feature corresponding to the power equipment to be detected from the ultrasonic partial discharge data, and then performs partial discharge detection on the power equipment to be detected according to the comprehensive discharge feature to obtain the discharge detection result of the power equipment to be detected. According to the above content, when the power equipment to be detected is detected, the ultrasonic partial discharge data of the power equipment to be detected is first obtained, and then the ultrasonic partial discharge data of the power equipment to be detected is extracted to obtain the comprehensive discharge feature corresponding to the power equipment to be detected, so that the comprehensive discharge feature fully reflects the partial discharge condition of the power equipment to be detected. Since the comprehensive discharge feature is a feature extracted from the ultrasonic partial discharge data for fully reflecting the partial discharge condition of the power equipment to be detected, the power equipment to be detected is detected according to the comprehensive discharge feature, so that the discharge detection result of the power equipment to be detected can be accurately obtained, and the actual situation of the power equipment to be detected can be accurately reflected. In addition, in the process of obtaining the discharge detection result of the power equipment to be detected, the ultrasonic partial discharge sample data does not need to be obtained, so that the limitation of manual detection and a large amount of training data in the existing discharge detection technology is avoided, and the efficiency and accuracy of the discharge detection are ensured.
[0097] It should be understood that, although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps.
[0098] Based on the same inventive concept, the embodiments of the present application also provide a discharge detection device for implementing the above-mentioned discharge detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more discharge detection device embodiments provided below can refer to the limitations of the discharge detection method in the above text, which will not be repeated here.
[0099] In one embodiment, as shown in Figure 6 A discharge detection device is provided, comprising: a determination module 10, an extraction module 20 and a detection module 30, wherein:
[0100] determining module 10 configured to determine ultrasonic partial discharge data of the power equipment to be detected;
[0101] extracting module 20 configured to extract discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0102] detecting module 30 configured to detect partial discharge of the power equipment to be detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected.
[0103] In an embodiment, ultrasonic partial discharge data of the power equipment to be detected is determined;
[0104] Discharge features are extracted from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0105] Partial discharge of the power equipment to be detected is detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected.
[0106] In an embodiment, the ultrasonic partial discharge data is subjected to data enhancement processing to obtain ultrasonic time-domain samples and ultrasonic frequency-domain samples under different partial discharge types;
[0107] The comprehensive discharge features corresponding to the power equipment to be detected are determined according to the ultrasonic time-domain samples and the ultrasonic frequency-domain samples.
[0108] In an embodiment, feature parameters are extracted from the ultrasonic time-domain samples to obtain ultrasonic time-domain features;
[0109] Feature parameters are extracted from the ultrasonic frequency-domain samples to obtain ultrasonic frequency-domain features;
[0110] The ultrasonic time-domain features and the ultrasonic frequency-domain features are fused to obtain the comprehensive discharge features corresponding to the power equipment to be detected.
[0111] In an embodiment, partial discharge of the power equipment to be detected is detected according to the comprehensive discharge features to obtain at least one candidate partial discharge type corresponding to the power equipment to be detected, and an identification accuracy of each candidate partial discharge type;
[0112] The discharge detection result of the power equipment to be detected is determined according to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type.
[0113] In an embodiment, a candidate partial discharge type with the highest identification accuracy among the at least one candidate partial discharge type is taken as a target partial discharge type of the power equipment to be detected;
[0114] The target partial discharge type and the identification accuracy of the target partial discharge type are taken as the discharge detection result of the power equipment to be detected.
[0115] In an embodiment, ultrasonic initial data of the power equipment to be detected is acquired.
[0116] The ultrasonic initial data is preprocessed to obtain ultrasonic partial discharge data of the power equipment to be detected; wherein the preprocessing includes at least one of signal framing processing, frame shifting processing, windowing processing, and short-time Fourier transform processing.
[0117] The discharge detection device determines the ultrasonic partial discharge data of the power equipment to be detected, extracts the corresponding comprehensive discharge feature of the power equipment to be detected from the ultrasonic partial discharge data, and then performs partial discharge detection on the power equipment to be detected according to the comprehensive discharge feature to obtain the discharge detection result of the power equipment to be detected. According to the above content, when the power equipment to be detected is detected for partial discharge, the ultrasonic partial discharge data of the power equipment to be detected is first acquired, and then the discharge feature extraction is performed on the ultrasonic partial discharge data of the power equipment to be detected to obtain the corresponding comprehensive discharge feature of the power equipment to be detected, so that the comprehensive discharge feature fully reflects the partial discharge condition of the power equipment to be detected. Since the comprehensive discharge feature is extracted from the ultrasonic partial discharge data and is used to fully reflect the partial discharge condition of the power equipment to be detected, the partial discharge detection of the power equipment to be detected according to the comprehensive discharge feature can accurately obtain the discharge detection result of the power equipment to be detected, and ensures that the discharge detection result can accurately reflect the actual condition of the power equipment to be detected. Moreover, in the process of obtaining the discharge detection result of the power equipment to be detected, the ultrasonic partial discharge sample data is not required, which avoids the limitation of manual detection and a large amount of training data in the existing discharge detection technology, and ensures the efficiency and accuracy of the discharge detection.
[0118] Each module in the discharge detection device can be realized by software, hardware, and a combination thereof in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above modules.
[0119] In an embodiment, a computer device is provided, which can be a terminal, and the internal structure diagram thereof can be as shown in Figure 7As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. Wireless mode can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a discharge detection method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.
[0120] Those skilled in the art can understand that, Figure 7 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.
[0121] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:
[0122] Determine the ultrasonic partial discharge data of the power equipment to be detected;
[0123] Discharge feature extraction is performed on the ultrasonic partial discharge data to obtain the comprehensive discharge feature corresponding to the power equipment to be detected;
[0124] According to the comprehensive discharge feature, the partial discharge detection of the power equipment to be detected is performed to obtain the discharge detection result of the power equipment to be detected.
[0125] In one embodiment, the processor executing the computer program further implements the following steps:
[0126] The ultrasonic partial discharge data is subjected to data enhancement processing to obtain ultrasonic time domain samples and ultrasonic frequency domain samples under different partial discharge types.
[0127] According to the ultrasonic time domain samples and the ultrasonic frequency domain samples, a comprehensive discharge feature corresponding to the power equipment to be detected is determined.
[0128] In one embodiment, the processor, when executing the computer program, also implements the following steps:
[0129] Feature parameter extraction is performed on the ultrasonic time domain samples to obtain ultrasonic time domain features.
[0130] Feature parameter extraction is performed on the ultrasonic frequency domain samples to obtain ultrasonic frequency domain features.
[0131] Feature fusion is performed on the ultrasonic time domain features and the ultrasonic frequency domain features to obtain the comprehensive discharge feature corresponding to the power equipment to be detected.
[0132] In one embodiment, the processor, when executing the computer program, also implements the following steps:
[0133] According to the comprehensive discharge feature, partial discharge detection is performed on the power equipment to be detected to obtain at least one candidate partial discharge type corresponding to the power equipment to be detected and an identification accuracy of each candidate partial discharge type.
[0134] According to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type, a discharge detection result of the power equipment to be detected is determined.
[0135] In one embodiment, the processor, when executing the computer program, also implements the following steps:
[0136] The candidate partial discharge type with the highest identification accuracy among the at least one candidate partial discharge type is taken as a target partial discharge type of the power equipment to be detected.
[0137] The target partial discharge type and the identification accuracy of the target partial discharge type are taken as the discharge detection result of the power equipment to be detected.
[0138] In one embodiment, the processor, when executing the computer program, also implements the following steps:
[0139] Ultrasonic initial data of the power equipment to be detected is obtained.
[0140] The ultrasonic initial data is preprocessed to obtain ultrasonic partial discharge data of the power equipment to be detected; wherein the preprocessing includes at least one of signal framing processing, frame shifting processing, windowing processing, and short-time Fourier transform processing.
[0141] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:
[0142] Determine ultrasonic partial discharge data of the power equipment to be detected;
[0143] Discharge feature extraction is performed on the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected;
[0144] According to the comprehensive discharge features, the partial discharge detection is performed on the power equipment to be detected, and a discharge detection result of the power equipment to be detected is obtained.
[0145] In one embodiment, the computer program is executed by the processor to further implement the following steps:
[0146] Data enhancement processing is performed on the ultrasonic partial discharge data to obtain ultrasonic time domain samples and ultrasonic frequency domain samples under different partial discharge types;
[0147] According to the ultrasonic time domain samples and the ultrasonic frequency domain samples, the comprehensive discharge features corresponding to the power equipment to be detected are determined.
[0148] In one embodiment, the computer program is executed by the processor to further implement the following steps:
[0149] Feature parameter extraction is performed on the ultrasonic time domain samples to obtain ultrasonic time domain features;
[0150] Feature parameter extraction is performed on the ultrasonic frequency domain samples to obtain ultrasonic frequency domain features;
[0151] Feature fusion is performed on the ultrasonic time domain features and the ultrasonic frequency domain features to obtain the comprehensive discharge features corresponding to the power equipment to be detected.
[0152] In one embodiment, the computer program is executed by the processor to further implement the following steps:
[0153] According to the comprehensive discharge features, the partial discharge detection is performed on the power equipment to be detected, at least one candidate partial discharge type corresponding to the power equipment to be detected is obtained, and an identification accuracy of each candidate partial discharge type is obtained;
[0154] According to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type, a discharge detection result of the power equipment to be detected is determined.
[0155] In one embodiment, the computer program is executed by the processor to further implement the following steps:
[0156] The at least one candidate partial discharge type with the highest recognition accuracy is taken as a target partial discharge type of the to-be-detected power equipment.
[0157] The target partial discharge type and the recognition accuracy of the target partial discharge type are taken as a discharge detection result of the to-be-detected power equipment.
[0158] In an embodiment, the computer program, when executed by the processor, further implements the following steps:
[0159] Obtaining ultrasonic initial data of the to-be-detected power equipment;
[0160] Pretreating the ultrasonic initial data to obtain ultrasonic partial discharge data of the to-be-detected power equipment; wherein the pretreatment includes at least one of signal framing processing, frame shifting processing, windowing processing, and short-time Fourier transform processing.
[0161] In an embodiment, a computer program product is provided, comprising a computer program which, when executed by the processor, implements the following steps:
[0162] Determining ultrasonic partial discharge data of the to-be-detected power equipment;
[0163] Extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the to-be-detected power equipment;
[0164] Performing partial discharge detection on the to-be-detected power equipment according to the comprehensive discharge features to obtain a discharge detection result of the to-be-detected power equipment.
[0165] In an embodiment, the computer program, when executed by the processor, further implements the following steps:
[0166] Performing data enhancement processing on the ultrasonic partial discharge data to obtain ultrasonic time-domain samples and ultrasonic frequency-domain samples under different partial discharge types;
[0167] Determining comprehensive discharge features corresponding to the to-be-detected power equipment according to the ultrasonic time-domain samples and the ultrasonic frequency-domain samples.
[0168] In an embodiment, the computer program, when executed by the processor, further implements the following steps:
[0169] Extracting feature parameters from the ultrasonic time-domain samples to obtain ultrasonic time-domain features;
[0170] Extracting feature parameters from the ultrasonic frequency-domain samples to obtain ultrasonic frequency-domain features;
[0171] Performing feature fusion on the ultrasonic time-domain features and the ultrasonic frequency-domain features to obtain comprehensive discharge features corresponding to the to-be-detected power equipment.
[0172] In one embodiment, the computer program, when executed by the processor, further implements the following steps:
[0173] According to the comprehensive discharge characteristics, partial discharge detection is performed on the to-be-detected power equipment to obtain at least one candidate partial discharge type corresponding to the to-be-detected power equipment and an identification accuracy of each candidate partial discharge type;
[0174] According to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type, a discharge detection result of the to-be-detected power equipment is determined.
[0175] In one embodiment, the computer program, when executed by the processor, further implements the following steps:
[0176] The candidate partial discharge type with the highest identification accuracy in the at least one candidate partial discharge type is taken as a target partial discharge type of the to-be-detected power equipment;
[0177] The target partial discharge type and the identification accuracy of the target partial discharge type are taken as the discharge detection result of the to-be-detected power equipment.
[0178] In one embodiment, the computer program, when executed by the processor, further implements the following steps:
[0179] Obtaining ultrasonic initial data of the to-be-detected power equipment;
[0180] Pretreating the ultrasonic initial data to obtain ultrasonic partial discharge data of the to-be-detected power equipment; wherein the pretreatment includes at least one of signal framing processing, frame shifting processing, windowing processing, and short-time Fourier transform processing.
[0181] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant national and regional laws, regulations and standards.
[0182] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.
[0183] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.
[0184] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims
1. A discharge detection method characterized by, The method comprises: determining ultrasonic partial discharge data of a power equipment to be detected; extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected; performing partial discharge detection on the power equipment to be detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected.
2. The method of claim 1, wherein, The step of extracting discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected comprises: performing data enhancement processing on the ultrasonic partial discharge data to obtain ultrasonic time-domain samples and ultrasonic frequency-domain samples under different partial discharge types; determining the comprehensive discharge features corresponding to the power equipment to be detected according to the ultrasonic time-domain samples and the ultrasonic frequency-domain samples.
3. The method of claim 2, wherein, The step of determining the comprehensive discharge features corresponding to the power equipment to be detected according to the ultrasonic time-domain samples and the ultrasonic frequency-domain samples comprises: extracting feature parameters from the ultrasonic time-domain samples to obtain ultrasonic time-domain features; extracting feature parameters from the ultrasonic frequency-domain samples to obtain ultrasonic frequency-domain features; performing feature fusion on the ultrasonic time-domain features and the ultrasonic frequency-domain features to obtain the comprehensive discharge features corresponding to the power equipment to be detected.
4. The method of claim 1, wherein, The step of performing partial discharge detection on the power equipment to be detected according to the comprehensive discharge features to obtain a discharge detection result of the power equipment to be detected comprises: performing partial discharge detection on the power equipment to be detected according to the comprehensive discharge features to obtain at least one candidate partial discharge type corresponding to the power equipment to be detected and an identification accuracy of each candidate partial discharge type; determining the discharge detection result of the power equipment to be detected according to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type.
5. The method of claim 4, wherein, The step of determining the discharge detection result of the power equipment to be detected according to the at least one candidate partial discharge type and the identification accuracy of each candidate partial discharge type comprises: taking a candidate partial discharge type with the highest identification accuracy in the at least one candidate partial discharge type as a target partial discharge type of the power equipment to be detected; taking the target partial discharge type and the identification accuracy of the target partial discharge type as the discharge detection result of the power equipment to be detected.
6. The method of claim 1, wherein, The step of determining ultrasonic partial discharge data of a power equipment to be detected comprises: obtaining ultrasonic initial data of the power equipment to be detected; performing preprocessing on the ultrasonic initial data to obtain ultrasonic partial discharge data of the power equipment to be detected; wherein the preprocessing comprises at least one of signal framing processing, frame shifting processing, windowing processing and short-time Fourier transform processing.
7. A discharge detection device, characterized by comprising: The device comprises: a determination module configured to determine ultrasonic partial discharge data of a power equipment to be detected; an extraction module configured to extract discharge features from the ultrasonic partial discharge data to obtain comprehensive discharge features corresponding to the power equipment to be detected; A detection module is configured to perform partial discharge detection on the power equipment to be detected according to the comprehensive discharge characteristics, and obtain a discharge detection result of the power equipment to be detected.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6. The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.