Method and device for enhancing partial discharge detection data

Abstract

The invention provides a partial discharge detection data enhancement method and device, and belongs to the field of partial discharge detection.The method comprises the steps that a partial discharge detection data set is obtained, the partial discharge detection data set comprises a plurality of partial discharge detection data, and the partial discharge detection data comprises partial discharge data and a partial discharge result; grouping the partial discharge detection data set according to the partial discharge result to obtain a first partial discharge detection data set and a second partial discharge detection data set; performing noise processing on the first partial discharge detection data set and the second partial discharge detection data set; and taking the first partial discharge detection data group and the second partial discharge detection group as input to train a partial discharge detection model, and enabling an output result of the partial discharge detection model to meet a threshold value requirement. According to the method, by constructing the data of the partial discharge detection model, the efficiency of constructing the partial discharge detection model is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of partial discharge monitoring, in particular to a partial discharge detection data enhancement method and device. BACKGROUND

[0002] With the development of AI technology, partial discharge detection based on AI technology is the future development trend. Partial discharge detection through AI technology requires the construction of a partial discharge detection model and a large amount of partial discharge detection data to train the partial discharge detection model.

[0003] Due to the different probabilities of different defect types of power equipment, partial discharge samples are scarce and the distribution between classes is unbalanced, which makes it difficult for deep learning models to learn the characteristics of minority class samples during training, affecting the generalization ability and recognition accuracy of the model. How to construct partial discharge detection data has become a problem that needs to be solved for AI partial discharge detection. SUMMARY

[0004] Therefore, the present application provides a partial discharge detection data enhancement method, device, electronic equipment and storage medium.

[0005] To achieve the above purpose, the present application provides a partial discharge detection data enhancement method, comprising:

[0006] obtaining a partial discharge detection data set, the partial discharge detection data set comprising a plurality of partial discharge detection data, the partial discharge detection data comprising partial discharge data and partial discharge results;

[0007] grouping the partial discharge detection data set according to the partial discharge results to obtain a first partial discharge detection data group and a second partial discharge detection data group;

[0008] noise processing the first partial discharge detection data group and the second partial discharge detection data group to obtain updated first partial discharge detection data group and second partial discharge detection data group;

[0009] training a partial discharge detection model with the updated first partial discharge detection data group and the second partial discharge detection group as input, and making the output result of the partial discharge detection model meet the threshold requirement.

[0010] Based on the same idea, the present application also provides a partial discharge detection data enhancement device, comprising:

[0011] an acquisition module for acquiring a partial discharge detection data set, the partial discharge detection data set comprising a plurality of partial discharge detection data, the partial discharge detection data comprising partial discharge data and partial discharge results;

[0012] grouping the partial discharge detection data sets according to the partial discharge results to obtain a first partial discharge detection data group and a second partial discharge detection data group;

[0013] processing the first partial discharge detection data group and the second partial discharge detection data group to obtain updated first partial discharge detection data group and second partial discharge detection data group;

[0014] training the updated first partial discharge detection data group and the second partial discharge detection data group as input to train a partial discharge detection model, and making the output result of the partial discharge detection model meet a threshold requirement.

[0015] Based on the same idea, the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, so that the one or more processors implement the partial discharge detection data enhancement method according to any one of the above.

[0016] Based on the same idea, the present application also provides a storage medium containing computer executable instructions, when the computer executable instructions are executed by a computer processor, for executing the partial discharge detection data enhancement method according to any one of the above. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments will be briefly introduced below, and obviously, the drawings in the following description only relate to some embodiments of the present application, but not limit the present application.

[0018] Figure 1 is a flowchart of the partial discharge detection data enhancement method provided by the embodiments of the present application;

[0019] Figure 2 is another flowchart of the partial discharge detection data enhancement method provided by the embodiments of the present application;

[0020] Figure 3 is still another flowchart of the partial discharge detection data enhancement method provided by the embodiments of the present application;

[0021] Figure 4 is still another flowchart of the partial discharge detection data enhancement method provided by the embodiments of the present application;

[0022] Figure 5 is a schematic diagram of the partial discharge detection data enhancement device provided by the embodiments of the present application;

[0023] Figure 6 is an electronic device structure diagram provided according to an embodiment of the present application;

[0024] Figure 7 is a storage medium diagram provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the described embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0026] Unless otherwise defined, technical terms or scientific terms used herein should be interpreted as is normally understood by one of ordinary skill in the art to which this application pertains. The terms "first", "second", and similar terms as used in the specification and claims of this patent application do not necessarily have an ordinal, sequential, or chronological significance, but are used to distinguish one element from another. The terms "comprises", "comprising", "includes", "including" and the like can be used in the specification and / or claims of this patent application to indicate that the features listed after such terms are included in the product or process described by the application, but not to the exclusion of other features.

[0027] At least one embodiment of the present application provides a partial discharge detection data enhancement method, which comprises: acquiring a partial discharge detection data set, wherein the partial discharge detection data set comprises a plurality of partial discharge detection data, and the partial discharge detection data comprises partial discharge data and a partial discharge result; grouping the partial discharge detection data set according to the partial discharge result to obtain a first partial discharge detection data group and a second partial discharge detection data group, wherein the first partial discharge detection data group comprises m partial discharge detection data, the second partial discharge detection data group comprises n partial discharge detection data, m and n are integers, m>1, and n>1; performing data enhancement on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge detection data group and an updated second partial discharge detection data group; training a partial discharge detection model by taking the updated first partial discharge detection data group and / or the updated second partial discharge detection data group as input, and making the output result of the partial discharge detection model meet a threshold requirement. The method improves the efficiency of constructing a partial discharge detection model through partial discharge detection data enhancement.

[0028] The embodiment of the present application also provides a partial discharge detection data enhancement device, which comprises: an acquisition module, which is used for acquiring a partial discharge detection data set, wherein the partial discharge detection data set comprises a plurality of partial discharge detection data, and the partial discharge detection data comprises partial discharge data and a partial discharge result; a grouping module, which is used for grouping the partial discharge detection data set according to the partial discharge result to obtain a first partial discharge detection data group and a second partial discharge detection data group, wherein the first partial discharge detection data group comprises m partial discharge detection data, the second partial discharge detection data group comprises n partial discharge detection data, m and n are integers, m>1, and n>1; a processing module, which is used for performing data enhancement on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge detection data group and an updated second partial discharge detection data group; and a training module, which is used for training a partial discharge detection model by taking the updated first partial discharge detection data group and / or the updated second partial discharge detection data group as input, and making the output result of the partial discharge detection model meet a threshold requirement. The method improves the efficiency of constructing a partial discharge detection model by performing partial discharge detection data enhancement.

[0029] The electronic device comprises one or more processors and a storage device, and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the partial discharge detection data enhancement methods provided by the embodiments of the present disclosure.

[0030] The electronic device comprises one or more processors and a storage device, and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the partial discharge detection data enhancement methods provided by the embodiments of the present disclosure.

[0031] Figure 1 is a flowchart of a partial discharge detection data enhancement method provided by the embodiments of the present application. As shown in the figure, the method comprises the following steps. Figure 1

[0032] Step 102: acquiring a partial discharge detection data set, wherein the partial discharge detection data set comprises a plurality of partial discharge detection data, and the partial discharge detection data comprises partial discharge data and a partial discharge result.

[0033] According to the embodiments of the present disclosure, the partial discharge data comprises a partial discharge signal, and the partial discharge result comprises information such as a partial discharge type, a partial discharge degree and a partial discharge position.

[0034] ​Step 104: grouping the partial discharge detection data set according to the partial discharge result to obtain a first partial discharge detection data group and a second partial discharge detection data group, the first partial discharge detection data group including m partial discharge detection data, the second partial discharge data group including n partial discharge detection data, m and n being integers, m > 1, n > 1;

[0035] According to an embodiment of the present disclosure, the partial discharge type is determined according to the partial discharge result, and the partial discharge detection data set is grouped according to the partial discharge type to obtain a first partial discharge detection data group and a second partial discharge detection data group; or, the partial discharge degree is determined according to the partial discharge result, and the partial discharge detection data set is grouped according to the partial discharge degree to obtain a first partial discharge detection data group and a second partial discharge detection data group; or, the partial discharge cycle is determined according to the partial discharge result, and the partial discharge detection data set is grouped according to the partial discharge cycle to obtain a first partial discharge detection data group and a second partial discharge detection data group.

[0036] Step 106: data enhancement is performed on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge data group and an updated second partial discharge data group;

[0037] Step 108: the updated first partial discharge detection data group and / or the updated second partial discharge data group are used as input to train a partial discharge detection model, and the output result of the partial discharge detection model is required to meet a threshold requirement.

[0038] According to an embodiment of the present disclosure, the first partial discharge detection data group and the second partial discharge detection data group are subjected to noise processing to obtain a partial discharge detection data set, the degree of noise can be controlled, and different noise fusion can obtain different partial discharge detection data sets, which can expand the number of partial discharge detection data, reduce the cost of partial discharge data acquisition, and improve the training speed of the partial discharge detection model and the anti-interference ability of the partial discharge detection model.

[0039] According to an embodiment of the present disclosure, random noise is injected into the first partial discharge detection data group and the second partial discharge detection data group to simulate electromagnetic interference and sensor noise.

[0040] According to an embodiment of the present disclosure, the random noise is Gaussian noise, and the noise power to be added is calculated according to the target signal-to-noise ratio SNR and the original signal power, SNR dB =10log 10 ( P noise / Psignal ) using SNR dB precisely control the noise intensity, P noise is the average power of the signal, P signal is the average power of the noise, combined with the adaptive parameter range SNR in 15dB-25dB to enhance diversity.

[0041] Figure 2 is another flow diagram of the partial discharge detection data enhancement method provided by the embodiment of the present application. As shown in the figure, the method comprises: Figure 2

[0042] Step 202: obtaining a partial discharge detection data set, wherein the partial discharge detection data set comprises a plurality of partial discharge detection data, and the partial discharge detection data comprises partial discharge data and partial discharge results;

[0043] Step 204: grouping the partial discharge detection data set according to the partial discharge results to obtain a first partial discharge detection data group and a second partial discharge detection data group, wherein the first partial discharge detection data group comprises m partial discharge detection data, the second partial discharge data group comprises n partial discharge detection data, and m, n are integers, m>1, n>1;

[0044] Step 206: when m>n, performing data enhancement on the partial discharge data in the second partial discharge detection data group after noise reduction processing, wherein the data enhancement on the partial discharge data in the second partial discharge detection data group after noise reduction processing comprises fusing different noises for the partial discharge data in the second partial discharge detection data after noise reduction processing to obtain an updated second partial discharge detection data group;

[0045] Step 208: training the partial discharge detection model by taking the first partial discharge detection device group and the updated second partial discharge detection data group as input.

[0046] According to the embodiment of the present application, by fusing the second partial discharge detection data group with the second noise, the degree of noise can be controlled, and different degrees of noise can be fused to obtain different partial discharge detection data sets, which can expand the number of partial discharge detection data, reduce the cost of partial discharge data acquisition, and improve the training speed of the partial discharge detection model and the anti-interference ability of the partial discharge detection model.

[0047] According to the embodiment of the present application, when the second noise comprises a plurality of noise data, each partial discharge detection data in the second partial discharge detection data group can be fused with a plurality of noises.

[0048] ​When the number of partial discharge detection data in the second partial discharge detection data set and the number of noise data in the second noise do not match, when the number of partial discharge detection data in the second partial discharge detection data set is greater than the number of noise data in the second noise, the noise data in the first noise is subjected to a zero padding operation so that the number of the two is equal; when the number of partial discharge detection data in the partial discharge detection data set is less than the number of noise data in the second noise, the partial discharge detection data in the second partial discharge detection data set can select noise data in the second noise, and the selection rule can be in order (including forward order and reverse order), random selection, etc.

[0049] Figure 3 is another flowchart of the partial discharge detection data enhancement method provided by the embodiment of the present application. As shown in the figure, Figure 3 the method comprises:

[0050] Step 302: Obtain a partial discharge detection data set, wherein the partial discharge detection data set comprises a plurality of partial discharge detection data, and the partial discharge detection data comprises partial discharge data and partial discharge results;

[0051] Step 304: Group the partial discharge detection data set according to the partial discharge results to obtain a first partial discharge detection data set and a second partial discharge detection data set, wherein the first partial discharge detection data set comprises m partial discharge detection data, the second partial discharge data set comprises n partial discharge detection data, m and n are integers, m>1, and n>1;

[0052] Step 306: When m<n, the partial discharge data in the first partial discharge detection data set is subjected to a noise reduction processing, and the partial discharge data in the first partial discharge detection data set after the noise reduction processing is subjected to a data enhancement, wherein the data enhancement of the partial discharge data in the first partial discharge detection data set after the noise reduction processing comprises fusing different noises to obtain an updated first partial discharge data set;

[0053] Step 308: The updated first partial discharge detection device set and the second partial discharge detection data set are used as inputs to train the partial discharge detection model.

[0054] According to the embodiments of the present application, by fusing the first partial discharge detection data set with the first noise, the degree of noise can be controlled, and different partial discharge detection data sets can be obtained by fusing different degrees of noise, which can expand the number of partial discharge detection data, reduce the cost of partial discharge data acquisition, and improve the training speed of the partial discharge detection model and the anti-interference ability of the partial discharge detection model.

[0055] According to an embodiment of the present disclosure, when the first noise includes a plurality of noise data, each of the partial discharge detection data in the first partial discharge detection data set can be fused with the plurality of noise.

[0056] When the number of partial discharge detection data in the first partial discharge detection data set and the number of noise data in the first noise do not match, when the number of partial discharge detection data in the first partial discharge detection data set is greater than the number of noise data in the first noise, the noise data in the first noise is operated by zero padding so that the number of the two is equal; when the number of partial discharge detection data in the first partial discharge detection data set is less than the number of noise data in the first noise, the partial discharge detection data in the first partial discharge detection data set can select the noise data in the first noise, and the selection rule can be in order (including forward order and reverse order), random selection, etc.

[0057] Figure 4 is another flowchart of the partial discharge detection data enhancement method provided by an embodiment of the present application. As shown in Figure 4 the method comprises:

[0058] Step 402: Obtain a partial discharge detection data set, the partial discharge detection data set including a plurality of partial discharge detection data, the partial discharge detection data including partial discharge data and partial discharge results;

[0059] Step 404: Group the partial discharge detection data set according to the partial discharge results to obtain a first partial discharge detection data set and a second partial discharge detection data set, the first partial discharge detection data set including m partial discharge detection data, the second partial discharge detection data set including n partial discharge detection data, m and n being integers, m>1, n>1;

[0060] Step 406: When m=n, the partial discharge data in the first partial discharge detection data set and the second partial discharge detection data set are processed by noise reduction, the partial discharge data after noise reduction is processed is data enhanced, and the first partial discharge detection data set and the second partial discharge detection data set after updating are updated;

[0061] Step 408: The updated first partial discharge detection device set and the updated second partial discharge detection data set are used as input to train the partial discharge detection model.

[0062] According to an embodiment of the present disclosure, by fusing the first partial discharge detection data set and the second partial discharge detection data set with the first noise, the degree of noise can be controlled, and different degrees of noise are fused to obtain different partial discharge detection data sets, which can expand the number of partial discharge detection data, reduce the cost of partial discharge data acquisition, and improve the training speed of the partial discharge detection model and the anti-interference ability of the partial discharge detection model.

[0063] According to an embodiment of the present disclosure, by fusing the first partial discharge detection data set and the second partial discharge detection data set with the first noise, the degree of noise can be controlled, and different degrees of noise are fused to obtain different partial discharge detection data sets, which can expand the number of partial discharge detection data, reduce the cost of partial discharge data acquisition, and improve the training speed of the partial discharge detection model and the anti-interference ability of the partial discharge detection model.

[0064] When the degree of partial discharge of the first partial discharge detection data set is greater than the degree of partial discharge of the second partial discharge detection data set, when the degree of noise of the second noise is greater than the degree of noise of the third noise, the difficulty of the partial discharge detection model in identifying the first partial discharge detection data set and the second partial discharge detection data set is similar; when the degree of noise of the second noise is less than or equal to the degree of noise of the third noise, the difficulty of the partial discharge detection model in identifying the first partial discharge detection data set is greater than the difficulty of identifying the second partial discharge detection data set.

[0065] According to an embodiment of the present disclosure, when the first noise includes a plurality of noise data, each partial discharge detection data in the first partial discharge detection data set and the second partial discharge detection data set can be fused with the plurality of noise.

[0066] When the number of partial discharge detection data in the partial discharge detection data set and the number of noise data in the first noise do not match, when the number of partial discharge detection data in the partial discharge detection data set is greater than the number of noise data in the first noise, the noise data in the first noise is operated by zero filling to make the number of the two equal; when the number of partial discharge detection data in the partial discharge detection data set is less than the number of noise data in the first noise, the partial discharge detection data in the partial discharge detection data set can select the noise data in the first noise, and the selection rule can be in order (including forward and reverse), random selection, etc.

[0067] Figure 5 According to an embodiment of the present disclosure, the device schematic diagram of the partial discharge detection data enhancement is provided, as shown in Figure 5 The partial discharge detection data enhancement device 500 includes:

[0068] The acquisition module is configured to acquire a partial discharge detection data set, the partial discharge detection data set including a plurality of partial discharge detection data, the partial discharge detection data including partial discharge data and a partial discharge result.

[0069] The grouping module is configured to group the partial discharge detection data set according to the partial discharge result to obtain a first partial discharge detection data group and a second partial discharge detection data group, the first partial discharge detection data group including m partial discharge detection data, the second partial discharge detection data group including n partial discharge detection data, m and n being integers, m > 1, and n > 1.

[0070] The processing module is configured to perform data enhancement on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge detection data group and an updated second partial discharge detection data group.

[0071] The training module is configured to train a partial discharge detection model by taking the updated first partial discharge detection data group and / or the updated second partial discharge detection data group as input, and to make the output result of the partial discharge detection model meet a threshold requirement.

[0072] The apparatus system provided by the embodiments of the present disclosure can achieve the same working process and technical effects as the partial discharge detection data enhancement method embodiments, which will not be repeated here, please refer to the previous description.

[0073] The present disclosure at least one embodiment also provides an electronic device 600, referring to Figure 6 The electronic device 600 includes one or more processors 610 and a storage device 620; the storage device 620 is configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the partial discharge detection data enhancement methods provided by the embodiments of the present disclosure.

[0074] The present disclosure at least one embodiment also provides a storage medium containing computer executable instructions, when the computer executable instructions are executed by a computer processor, the computer executable instructions are used to execute any one of the partial discharge detection data enhancement methods provided by the embodiments of the present disclosure.

[0075] The present disclosure at least one embodiment also provides a computer executable instruction storage medium, which can be a non-transitory computer readable storage medium. Illustratively, Figure 7 A schematic diagram of a non-transitory computer readable storage medium provided by the present disclosure at least one embodiment.

[0076] For example, as Figure 7As shown, computer readable instructions 701 are stored non-transitorily on computer readable storage medium 700. For example, the computer readable instructions 701 may, when executed by a processor, perform one or more steps of a partial discharge detection data augmentation method according to one or more of the above.

[0077] For example, the storage medium 700 can be applied in the electronic device 600 described above. For example, the storage medium 700 can include the memory 620 in the electronic device 600.

[0078] The above description is merely exemplary of the disclosure and the application of the principles thereof and the scope of the disclosure is not limited to the specific embodiments described herein, but only by the claims that follow. It is therefore contemplated that in the implementation of the disclosure improvements and / or modifications can occur to persons skilled in the art to which the disclosure pertains. Such improvements and / or modifications are intended to be within the scope of the claims. It is intended that the application not be limited to the particular details shown and described herein, but to include all variations falling within the scope of the application. Various modifications can be made in the implementation without departing from the scope of the present disclosure.

[0079] The following points need to be explained:

[0080] (1) The drawings of the embodiments of the disclosure only involve the structures involved in the embodiments of the disclosure, and other structures can be referred to the general design.

[0081] (2) In the case of no conflict, the embodiments of the disclosure and the features in the embodiments can be combined to obtain new embodiments.

[0082] The above description is merely exemplary of the disclosure and the application of the principles thereof and the scope of the disclosure is not limited to the specific embodiments described herein, but only by the claims that follow. It is therefore contemplated that in the implementation of the disclosure improvements and / or modifications can occur to persons skilled in the art to which the disclosure pertains. Such improvements and / or modifications are intended to be within the scope of the claims. It is intended that the application not be limited to the particular details shown and described herein, but to include all variations falling within the scope of the application. Various modifications can be made in the implementation without departing from the scope of the present disclosure.

Claims

1. A method for enhancing partial discharge detection data, characterized in that: Comprising: Obtaining a partial discharge detection data set, the partial discharge detection data set including a plurality of partial discharge detection data, the partial discharge detection data including partial discharge data and partial discharge results; Grouping the partial discharge detection data set according to the partial discharge results to obtain a first partial discharge detection data group and a second partial discharge detection data group, the first partial discharge detection data group including m partial discharge detection data, the second partial discharge data group including n partial discharge detection data, m and n being integers, m > 1, n > 1; Performing data augmentation on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge data group and an updated second partial discharge data group; Using the updated first partial discharge detection data group and / or the updated second partial discharge data group as inputs to train a partial discharge detection model, and making the output result of the partial discharge detection model meet the threshold requirement.

2. The method according to claim 1, characterized in that The performing data augmentation on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge data group and an updated second partial discharge data group includes: When m > n, performing data augmentation on the partial discharge data after noise reduction processing in the second partial discharge detection data group, and the performing data augmentation on the partial discharge data after noise reduction processing in the second partial discharge detection data group includes fusing different noises into the partial discharge data after noise reduction processing in the second partial discharge detection data to obtain an updated second partial discharge detection data group.

3. The method according to claim 2, characterized in that The using the updated first partial discharge detection data group and / or the updated second partial discharge data group as inputs to train a partial discharge detection model includes: Using the first partial discharge detection device group and the updated second partial discharge detection data group as inputs to train the partial discharge detection model.

4. The method according to claim 1, wherein The performing data augmentation on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge data group and an updated second partial discharge data group includes: When m < n, performing noise reduction processing on the partial discharge data in the first partial discharge detection data group, and performing data augmentation on the partial discharge data after noise reduction processing in the first partial discharge detection data group, and the performing data augmentation on the partial discharge data after noise reduction processing in the first partial discharge detection data group includes fusing different noises into the partial discharge data after noise reduction processing in the first partial discharge detection data to obtain an updated first partial discharge data group.

5. The using the updated first partial discharge detection data group and / or the updated second partial discharge data group as inputs to train a partial discharge detection model according to claim 4 includes: The updated first partial discharge detection device group and the second partial discharge detection data group are used as input to train the partial discharge detection model.

6. The method according to claim 1, characterized in that The performing data enhancement on the partial discharge data in the first partial discharge detection data group and / or the partial discharge data in the second partial discharge detection data group to obtain an updated first partial discharge data group and an updated second partial discharge data group includes: When m=n, the partial discharge data in the first partial discharge detection data group and the second partial discharge detection data group are subjected to noise reduction processing, and the partial discharge data after the noise reduction processing are subjected to data enhancement to obtain the updated first partial discharge detection data group and the second partial discharge detection data group.

7. The method according to claim 6, characterized in that The using the updated first partial discharge detection data set and / or the updated second partial discharge data set as input to train the partial discharge detection model comprises: The updated first partial discharge detection device group and the updated second partial discharge detection data group are used as input to train the partial discharge detection model.

8. The method according to claim 1, characterized in that The step of grouping the partial discharge detection data set according to the partial discharge result to obtain a first partial discharge detection data group and a second partial discharge detection data group includes: Determine the partial discharge type according to the partial discharge result, and group the partial discharge detection data set according to the partial discharge type to obtain a first partial discharge detection data group and a second partial discharge detection data group; or Determine the partial discharge degree according to the partial discharge result, and group the partial discharge detection data set according to the partial discharge degree to obtain a first partial discharge detection data group and a second partial discharge detection data group; or The partial discharge period is determined according to the partial discharge result, and the partial discharge detection data set is grouped according to the partial discharge period to obtain a first partial discharge detection data group and a second partial discharge detection data group.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for enhancing partial discharge detection data as described in any one of claims 1 to 8.

10. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, the computer executable instructions are used to perform the method for enhancing partial discharge detection data according to any one of claims 1 to 8.

Images