CN113391172A - Partial discharge diagnosis method and system based on time sequence integration and used for multi-source ultrasonic detection - Google Patents
Partial discharge diagnosis method and system based on time sequence integration and used for multi-source ultrasonic detection Download PDFInfo
- Publication number
- CN113391172A CN113391172A CN202110601395.0A CN202110601395A CN113391172A CN 113391172 A CN113391172 A CN 113391172A CN 202110601395 A CN202110601395 A CN 202110601395A CN 113391172 A CN113391172 A CN 113391172A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- partial discharge
- classifier
- map
- spectrum
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1209—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using acoustic measurements
Abstract
The invention belongs to the field of partial discharge detection, and provides a partial discharge diagnosis method and system for multi-source ultrasonic detection based on time sequence integration. The method comprises the steps of obtaining an ultrasonic time sequence map, wherein the ultrasonic time sequence map comprises an ultrasonic amplitude map, an ultrasonic shape map, an ultrasonic phase map, an ultrasonic flight map and an ultrasonic audio frequency sound spectrum; inputting each signal in the ultrasonic time sequence map into a classifier corresponding to the partial discharge diagnosis model to obtain a partial discharge diagnosis result; the partial discharge diagnosis model is composed of an ultrasonic amplitude spectrum classifier, an ultrasonic shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier and an ultrasonic audio spectrum classifier which have weights, and the partial discharge diagnosis result is the sum of the weights of the classification results of all the classifiers.
Description
Technical Field
The invention belongs to the field of partial discharge detection, and particularly relates to a partial discharge diagnosis method and system based on time sequence integration and multi-source ultrasonic detection.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Ultrasonic detection has been widely used in both live detection and on-line monitoring. Background systems of many power devices retain a large amount of detection data, but due to the differences in the sensitivity, detection frequency, detection requirements, technical levels of detection personnel and intermittent characteristics of local discharge defects, data based on ultrasonic detection are not effectively utilized, and the diagnosis and identification accuracy of the local discharge defects of the power devices is not high enough.
The existing method for distinguishing partial discharge noise from discharge in non-contact ultrasonic detection carries out maximum envelope calculation on a PRPD graph of ultrasonic waves and a PRPD graph spectrogram of the noise during discharge and carries out noise and discharge mode identification according to different expression characteristics of the PRPD graph and the PRPD graph, but a single ultrasonic PRPD graph has limitation and has poor effect on partial discharge identification. In the prior art, ultrasonic detection is utilized to identify insulation defects of a gas insulated switchgear, wherein ultrasonic signals generate 3 signal sequences based on an amplitude mode, a flight mode and a phase mode; judging whether the ultrasonic signal is possibly background noise, metal free particles or partial discharge by using an amplitude mode and a flight mode; if the partial discharge is detected, judging the insulation type of the partial discharge by utilizing a phase compensation identification technology. However, the experimental data given by the ultrasonic signals in the laboratory environment is complex in data situation of the actual environment, and is not suitable for being used in the actual environment.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a partial discharge diagnosis method and system based on time sequence integrated multi-source ultrasonic detection, which are based on a multi-source comprehensive partial discharge diagnosis method and improve the accuracy of partial discharge diagnosis.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a partial discharge diagnosis method of multi-source ultrasonic detection based on time sequence integration.
A partial discharge diagnosis method of multi-source ultrasonic detection based on time sequence integration comprises the following steps:
acquiring an ultrasonic time sequence map, wherein the ultrasonic time sequence map comprises an ultrasonic amplitude map, an ultrasonic shape map, an ultrasonic phase map, an ultrasonic flight map and an ultrasonic audio frequency sound spectrum;
inputting each signal in the ultrasonic time sequence map into a classifier corresponding to the partial discharge diagnosis model to obtain a partial discharge diagnosis result;
the partial discharge diagnosis model is composed of an ultrasonic amplitude spectrum classifier, an ultrasonic shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier and an ultrasonic audio spectrum classifier which have weights, and the partial discharge diagnosis result is the sum of the weights of the classification results of all the classifiers.
The invention provides a partial discharge diagnosis system based on time sequence integrated multi-source ultrasonic detection.
A partial discharge diagnostic system for multi-source ultrasound detection based on temporal integration, comprising:
the signal acquisition module is used for acquiring an ultrasonic time sequence map, and the ultrasonic time sequence map comprises an ultrasonic amplitude map, an ultrasonic shape map, an ultrasonic phase map, an ultrasonic flight map and an ultrasonic audio frequency sound spectrum;
the partial discharge diagnosis module is used for inputting each signal in the ultrasonic time sequence map into a classifier corresponding to the partial discharge diagnosis model to obtain a partial discharge diagnosis result;
the partial discharge diagnosis model is composed of an ultrasonic amplitude spectrum classifier, an ultrasonic shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier and an ultrasonic audio spectrum classifier which have weights, and the partial discharge diagnosis result is the sum of the weights of the classification results of all the classifiers.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps in the partial discharge diagnosis method for multi-source ultrasound detection based on time series integration as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the partial discharge diagnosis method based on time-series integrated multi-source ultrasound detection.
Compared with the prior art, the invention has the beneficial effects that:
(1) when the ultrasonic is applied to the partial discharge detection, the invention can obtain the maps of the amplitude mode, the waveform mode, the phase mode, the flight mode and the audio mode at different time and different ultrasonic detection equipment, and can be used for judging whether the signal belongs to noise interference or partial discharge according to the maps. And the type of noise interference and partial discharge (corona discharge, air gap discharge, levitation discharge, particle discharge, etc.).
(2) The invention solves the problems that the ultrasonic signals generated by typical partial discharge and noise have different physical characteristics, the diagnostic algorithm of a single type map has limitation, the characteristics of the ultrasonic signals cannot be better expressed, and the diagnostic algorithm of each single type map is a weak classifier, and the classification accuracy of the comprehensive classifier integrated with the learning construction is improved by 5-13%, which shows that the algorithm can improve the complementarity, the effectiveness and the robustness of the partial discharge diagnostic algorithm.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a schematic structural diagram of a partial discharge diagnostic model according to an embodiment of the present invention;
FIG. 2 is a diagram of an SVM based ultrasound amplitude map multi-classification process according to an embodiment of the present invention;
FIG. 3 is an ultrasound shape atlas deep learning network architecture diagram of an embodiment of the invention;
FIG. 4 is an ultrasound amplitude map of an embodiment of the present invention;
FIG. 5 is an ultrasonic waveform map of an embodiment of the present invention;
FIG. 6 is an ultrasound phase map of an embodiment of the present invention;
FIG. 7 is an ultrasonic flight map of an embodiment of the present invention;
FIG. 8 is an ultrasonic audio spectrum of an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
The embodiment provides a partial discharge diagnosis method of multi-source ultrasonic detection based on time sequence integration, which comprises the following steps:
step S101: and acquiring an ultrasonic time sequence map, wherein the ultrasonic time sequence map comprises an ultrasonic amplitude map, an ultrasonic shape map, an ultrasonic phase map, an ultrasonic flight map and an ultrasonic audio frequency sound spectrum.
In this embodiment, as shown in fig. 4, the ultrasound amplitude map is: the ultrasonic characteristic diagram shows four test parameter values and background values, which are respectively a signal effective value, a signal maximum value, frequency component 1 correlation and frequency component 2 correlation. Frequency component 1 refers to the system frequency and frequency component 2 refers to twice the system frequency.
As shown in fig. 5, the ultrasound shape atlas: and displaying the time domain waveform data in a plurality of power frequency periods.
As shown in fig. 6, the ultrasound phase map: an ultrasound phase map (AE phase) shows the relationship of amplitude and phase.
As shown in fig. 7, the ultrasonic flight pattern has a relatively obvious characteristic of time of flight and amplitude, and the diagnosis mode of the flight pattern is comprehensively judged by the magnitude of the time of flight and the amplitude of the signal.
As shown in fig. 8, the ultrasonic audio spectrum: it is described the sound distribution of each frequency in a continuous time.
Step S102: inputting each signal in the ultrasonic time sequence map into a classifier corresponding to the partial discharge diagnosis model to obtain a partial discharge diagnosis result;
the partial discharge diagnosis model is composed of an ultrasonic amplitude spectrum classifier, an ultrasonic shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier and an ultrasonic audio spectrum classifier which have weights, and the partial discharge diagnosis result is the sum of the weights of the classification results of the classifiers, as shown in fig. 1.
The partial discharge diagnosis model of the embodiment is formed by a multi-source ultrasonic diagnosis algorithm based on Adaboost.
Specifically, the partial discharge diagnostic result includes six types of corona discharge, floating discharge, air gap discharge, particle discharge, noise, and normal.
In this embodiment, the weight a of each classifier in the partial discharge diagnosis modelmFor its importance in the partial discharge diagnostic model:
wherein e ismIs the m-th classifier G in the partial discharge diagnostic modelmThe training error of (2). The formula is followingmDecreasing and increasing. I.e., classifiers with a small error rate, are of great importance in the final classifier.
Specifically, the ultrasonic amplitude map classifier is composed of k × k (k-1)/2 SVM models, wherein k is the number of categories.
In this embodiment, when an unknown sample is classified, the category with the most votes is the category of the unknown sample. If the detected signals have 6 categories, 15 different two-classification SVM models need to be designed, and the process is shown in FIG. 2.
In this embodiment, the ultrasonic wave shape atlas classifier, the ultrasonic phase atlas classifier, the ultrasonic flight atlas classifier and the ultrasonic audio frequency sound atlas classifier are all ResNet network models, and the ResNet network models are composed of an input part, a convolution part and an output part.
The input data is 224 × 224 picture data, and the input layer specification is (224, 224, 3) since three channels of RGB are common. Following the input layers, the image data was subjected to 7 × 7 convolution and 3 × 3 pooling, converting the data to a 56 × 56 size profile. The processing of the input part reduces the size of the data and lays the foundation for the feature extraction of the convolutional layer.
Unlike the original structure of the ResNet network, the residual unit used in this embodiment is formed by three layers of convolution, and the convolution kernels have sizes of 1 × 1, 3 × 3, and 1 × 1, respectively. The residual unit used in this example, compared to the original residual unit, innovatively introduces a 1 x 1 convolution structure. For 256-dimensional input features, the total number of convolutional layer parameters spliced by three convolutions of 1 × 1, 3 × 3, 1 × 1 is 69632, while the total number of parameters of the original residual unit using two 3 × 3 is 1179648, and the calculation amount can be simplified to 5.9% of the original using a 1 × 1 convolution structure. In this embodiment, the convolutional layer with a 1 × 1 convolutional structure greatly accelerates the training speed of the network, and ensures that a lower training speed is maintained while a larger number of layers are stacked. In the present embodiment, a residual neural network having a depth of 50 layers is constructed using 16 residual unit structures described above and a total of 48 convolutional layers. In the application scenario of the embodiment, the diagnosis conclusion includes six categories, namely corona, levitation, air gap, particle, noise and normal, and the overall architecture of the deep learning network is shown in fig. 3.
The training process of the partial discharge diagnosis model in this embodiment is as follows:
1) constructing a training set and a test set of an ultrasonic diagnostic algorithm as follows:
T＝{(X1，Y1)，(X2，Y2)，…，(Xn，Yn)}
wherein Xi＝{x1，x2，x3，x4，x5In which x1Is an ultrasonic amplitude map training sample, x2Is an ultrasonic shape atlas training sample, x3Is an ultrasonic phase map training sample, x4Is an ultrasonic flight pattern training sample, x5Is an ultrasonic audio spectrum training sample, and i is the serial number of the ultrasonic time sequence spectrum. n is the number of time series samples. Y isiThe corona discharge, the floating discharge, the air gap discharge, the particle discharge, the noise, and the normal are indicated by 1 to 6, respectively {1, 2, 3, 4, 5, 6 }.
2) Initializing distribution of training data
Of training dataThe weight average distribution is as follows: d { W1，W2，W3，W4，W5，}
Wherein the weight of the ultrasonic amplitude map training sample is W1The weight of the ultrasonic wave shape atlas training sample is W2The weight of the ultrasonic phase atlas training sample is W3The weight of the ultrasonic flight pattern training sample is W4And the weight of the ultrasonic audio spectrogram training sample is W5，
N is the total number of training samples.
3) Selecting a basic classifier
The basic classifier comprises the following five classifiers: the ultrasonic wave shape spectrum classifier, the ultrasonic wave phase spectrum classifier, the ultrasonic flight spectrum classifier and the ultrasonic audio frequency spectrum classifier.
4) Calculating speaking weights of the classifiers, namely weights of the classifiers;
5) the sample weight D is updated. Assume that the sample set weight coefficients of the mth weak classifier are:
Dm＝{w1m，w2m,…，wnm}
the formula for calculating the sample set weight coefficient of the corresponding mth weak classifier:
Zmis a normalization factor, the calculation formula:
as can be seen from the calculation formula, if the ith sample is classified incorrectly, YiGm(xi)<0, resulting in the weight of the sample increasing in the mth weak classifier, if the classification is correct, the weight is in the mth weak classifierAnd (4) reduction.
6) Designing a set strategy and constructing a final strong classifier
By using a weighted decision method, the final strong classifier is of the formula:
in the embodiment, an ultrasonic amplitude spectrum classifier, an ultrasonic wave shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier, an ultrasonic audio spectrogram classifier and a multi-source ultrasonic diagnosis model based on time sequence integration are compared in an experiment, 2000 groups of data are selected for each discharge type to be compared, classification accuracy and recall are used as evaluation indexes, and the accuracy and the recall are defined as follows:
judging the accurate number of the atlas/the total number of the atlas in the type according to the accuracy rate;
judging the correct number of the maps/the total number of the maps under the type in the sample according to the recall rate;
tables 1 and 24 show the performance of the classification accuracy and recall for the six diagnostic ultrasound algorithms on different partial discharge signals, where the normal signal is substantially close to the no discharge signal case, and thus the accuracy and recall are both higher in the six diagnostic algorithms by over 90%. Compared with a multi-source ultrasonic diagnosis algorithm based on time sequence integration and other single-map diagnosis algorithms, the multi-source ultrasonic diagnosis algorithm based on time sequence integration has the highest accuracy in various partial discharge types, and the accuracy is improved by 5% -13% compared with the accuracy of other algorithms. The diagnosis accuracy of the ultrasonic detection data can be improved by the algorithm.
TABLE 1 Classification accuracy of six ultrasonic diagnosis algorithms on different partial discharge signals
TABLE 2 Classification recall rate of six ultrasonic diagnosis algorithms on different partial discharge signals
Example two
The embodiment provides a partial discharge diagnostic system based on time sequence integrated multi-source ultrasonic detection, which specifically comprises the following modules:
the signal acquisition module is used for acquiring an ultrasonic time sequence map, and the ultrasonic time sequence map comprises an ultrasonic amplitude map, an ultrasonic shape map, an ultrasonic phase map, an ultrasonic flight map and an ultrasonic audio frequency sound spectrum;
the partial discharge diagnosis module is used for inputting each signal in the ultrasonic time sequence map into a classifier corresponding to the partial discharge diagnosis model to obtain a partial discharge diagnosis result;
the partial discharge diagnosis model is composed of an ultrasonic amplitude spectrum classifier, an ultrasonic shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier and an ultrasonic audio spectrum classifier which have weights, and the partial discharge diagnosis result is the sum of the weights of the classification results of all the classifiers.
It should be noted that, each module in the partial discharge diagnosis system for multi-source ultrasound detection based on time sequence integration according to the present embodiment corresponds to each step in the partial discharge diagnosis method for multi-source ultrasound detection based on time sequence integration according to the first embodiment one by one, and the specific implementation process is the same, and will not be described here again.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the partial discharge diagnosis method based on time-series integrated multi-source ultrasound detection as described above.
Example four
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the steps in the partial discharge diagnosis method based on the time-series integrated multi-source ultrasonic detection.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A partial discharge diagnosis method of multi-source ultrasonic detection based on time sequence integration is characterized by comprising the following steps:
acquiring an ultrasonic time sequence map, wherein the ultrasonic time sequence map comprises an ultrasonic amplitude map, an ultrasonic shape map, an ultrasonic phase map, an ultrasonic flight map and an ultrasonic audio frequency sound spectrum;
inputting each signal in the ultrasonic time sequence map into a classifier corresponding to the partial discharge diagnosis model to obtain a partial discharge diagnosis result;
the partial discharge diagnosis model is composed of an ultrasonic amplitude spectrum classifier, an ultrasonic shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier and an ultrasonic audio spectrum classifier which have weights, and the partial discharge diagnosis result is the sum of the weights of the classification results of all the classifiers.
2. The partial discharge diagnosis method based on time-series integrated multi-source ultrasonic detection according to claim 1, wherein the partial discharge diagnosis result includes six types of corona discharge, floating discharge, air gap discharge, particle discharge, noise and normal.
3. The partial discharge diagnosis method based on time-series integrated multi-source ultrasonic detection of claim 1, wherein the weight a of each classifier in the partial discharge diagnosis modelmFor its importance in the partial discharge diagnostic model:
wherein e ismIs the m-th classifier G in the partial discharge diagnostic modelmThe training error of (2).
4. The partial discharge diagnostic method based on time-series integrated multi-source ultrasound detection according to claim 1, wherein the ultrasound amplitude map classifier is composed of k x (k-1)/2 SVM models, where k is the number of classes.
5. The partial discharge diagnostic method based on time-series integrated multi-source ultrasonic detection as claimed in claim 1, wherein the ultrasonic waveform atlas classifier, the ultrasonic phase atlas classifier, the ultrasonic flight atlas classifier and the ultrasonic audio frequency spectrogram classifier are ResNet network models, and the ResNet network models are composed of an input part, a convolution part and an output part.
6. The partial discharge diagnostic method based on time-series integrated multi-source ultrasound detection according to claim 5, wherein the convolution portion is composed of a plurality of residual units, each residual unit is composed of a three-layer convolution, and the convolution kernels of the three-layer convolution have sizes of 1 × 1, 3 × 3 and 1 × 1, respectively.
7. The partial discharge diagnostic method based on time-series integrated multi-source ultrasonic detection of claim 5, wherein the input part comprises a convolution layer and a pooling layer for extracting a feature map with a set size.
8. A diagnostic system is put in office of multisource ultrasonic testing based on chronogenesis is integrated, its characterized in that includes:
the signal acquisition module is used for acquiring an ultrasonic time sequence map, and the ultrasonic time sequence map comprises an ultrasonic amplitude map, an ultrasonic shape map, an ultrasonic phase map, an ultrasonic flight map and an ultrasonic audio frequency sound spectrum;
the partial discharge diagnosis module is used for inputting each signal in the ultrasonic time sequence map into a classifier corresponding to the partial discharge diagnosis model to obtain a partial discharge diagnosis result;
the partial discharge diagnosis model is composed of an ultrasonic amplitude spectrum classifier, an ultrasonic shape spectrum classifier, an ultrasonic phase spectrum classifier, an ultrasonic flight spectrum classifier and an ultrasonic audio spectrum classifier which have weights, and the partial discharge diagnosis result is the sum of the weights of the classification results of all the classifiers.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps in the partial discharge diagnosis method based on time-series integrated multi-source ultrasound detection according to any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the partial discharge diagnosis method based on time-series integrated multi-source ultrasound detection according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110601395.0A CN113391172A (en) | 2021-05-31 | 2021-05-31 | Partial discharge diagnosis method and system based on time sequence integration and used for multi-source ultrasonic detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110601395.0A CN113391172A (en) | 2021-05-31 | 2021-05-31 | Partial discharge diagnosis method and system based on time sequence integration and used for multi-source ultrasonic detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113391172A true CN113391172A (en) | 2021-09-14 |
Family
ID=77619599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110601395.0A Pending CN113391172A (en) | 2021-05-31 | 2021-05-31 | Partial discharge diagnosis method and system based on time sequence integration and used for multi-source ultrasonic detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113391172A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115857359A (en) * | 2022-12-27 | 2023-03-28 | 广东非凡实业有限公司 | Preparation process and system of high-strength soil |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576600A (en) * | 2009-05-15 | 2009-11-11 | 重庆大学 | Self-walking underground cable failure detection intelligent instrument |
| CN105930861A (en) * | 2016-04-13 | 2016-09-07 | 西安西拓电气股份有限公司 | Adaboost algorithm based transformer fault diagnosis method |
| CN110412431A (en) * | 2019-08-05 | 2019-11-05 | 国网湖南省电力有限公司 | A kind of diagnostic method and diagnostic system of the shelf depreciation defect type of power equipment |
| CN110703057A (en) * | 2019-11-04 | 2020-01-17 | 国网山东省电力公司电力科学研究院 | Power equipment partial discharge diagnosis method based on data enhancement and neural network |
| CN110850244A (en) * | 2019-11-11 | 2020-02-28 | 国网湖南省电力有限公司 | Local discharge defect time domain map diagnosis method, system and medium based on deep learning |
| CN110927537A (en) * | 2019-11-27 | 2020-03-27 | 国网江苏省电力有限公司电力科学研究院 | Partial discharge monitoring device and method based on Internet of things edge calculation |
-
2021
- 2021-05-31 CN CN202110601395.0A patent/CN113391172A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576600A (en) * | 2009-05-15 | 2009-11-11 | 重庆大学 | Self-walking underground cable failure detection intelligent instrument |
| CN105930861A (en) * | 2016-04-13 | 2016-09-07 | 西安西拓电气股份有限公司 | Adaboost algorithm based transformer fault diagnosis method |
| CN110412431A (en) * | 2019-08-05 | 2019-11-05 | 国网湖南省电力有限公司 | A kind of diagnostic method and diagnostic system of the shelf depreciation defect type of power equipment |
| CN110703057A (en) * | 2019-11-04 | 2020-01-17 | 国网山东省电力公司电力科学研究院 | Power equipment partial discharge diagnosis method based on data enhancement and neural network |
| CN110850244A (en) * | 2019-11-11 | 2020-02-28 | 国网湖南省电力有限公司 | Local discharge defect time domain map diagnosis method, system and medium based on deep learning |
| CN110927537A (en) * | 2019-11-27 | 2020-03-27 | 国网江苏省电力有限公司电力科学研究院 | Partial discharge monitoring device and method based on Internet of things edge calculation |
Non-Patent Citations (2)
| Title |
|---|
| YING LIN: "Partial discharge diagnosis algorithm for multi-source ultrasound detection based on time series integration", 《2021 6TH ASIA CONFERENCE ON POWER AND ELECTRICAL ENGINEERING (ACPEE)》 * |
| 律方成: "基于 LLE 降维和 BP_Adaboost 分类器的 GIS 局部放电模式识别", 《电测与仪表》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115857359A (en) * | 2022-12-27 | 2023-03-28 | 广东非凡实业有限公司 | Preparation process and system of high-strength soil |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Virtualization and deep recognition for system fault classification | |
| CN110728360B (en) | Micro-energy device energy identification method based on BP neural network | |
| Su et al. | Performance analysis of multiple aggregated acoustic features for environment sound classification | |
| Jiang et al. | Bearing fault classification based on convolutional neural network in noise environment | |
| Wu et al. | An expert system for fault diagnosis in internal combustion engines using probability neural network | |
| CN110503075B (en) | Planetary gearbox fault diagnosis method and system based on PSO-EEMD method | |
| CN107564513A (en) | Audio recognition method and device | |
| CN113252322B (en) | Method and device for diagnosing mechanical fault of circuit breaker under noise-containing background | |
| CN110657984A (en) | Planetary gearbox fault diagnosis method based on reinforced capsule network | |
| Hong et al. | Supervised-learning-based intelligent fault diagnosis for mechanical equipment | |
| CN110458071B (en) | DWT-DFPA-GBDT-based optical fiber vibration signal feature extraction and classification method | |
| Tian et al. | Compound Fault Diagnosis of Stator Interturn Short Circuit and Air Gap Eccentricity Based on Random Forest and XGBoost | |
| CN113391172A (en) | Partial discharge diagnosis method and system based on time sequence integration and used for multi-source ultrasonic detection | |
| Imran et al. | An analysis of audio classification techniques using deep learning architectures | |
| Wong et al. | Fault diagnosis of induction motors under untrained loads with a feature adaptation and improved broad learning framework | |
| Zhao et al. | Environmental sound classification based on adding noise | |
| CN113076920B (en) | Intelligent fault diagnosis method based on asymmetric domain confrontation self-adaptive model | |
| Xu et al. | Combining DBN and FCM for fault diagnosis of roller element bearings without using data labels | |
| CN113971416A (en) | Cable early fault identification method | |
| Mitiche et al. | Deep complex neural network learning for high-voltage insulation fault classification from complex bispectrum representation | |
| CN110222390B (en) | Gear crack identification method based on wavelet neural network | |
| Barkana et al. | Environmental noise source classification using neural networks | |
| CN111025100A (en) | Transformer ultrahigh frequency partial discharge signal mode identification method and device | |
| CN110610203A (en) | Electric energy quality disturbance classification method based on DWT and extreme learning machine | |
| CN113095381B (en) | Underwater sound target identification method and system based on improved DBN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210914 |