CN114201991A - Partial discharge signal detection method and system based on ultrasonic sensor array - Google Patents
Partial discharge signal detection method and system based on ultrasonic sensor array Download PDFInfo
- Publication number
- CN114201991A CN114201991A CN202111477321.7A CN202111477321A CN114201991A CN 114201991 A CN114201991 A CN 114201991A CN 202111477321 A CN202111477321 A CN 202111477321A CN 114201991 A CN114201991 A CN 114201991A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- discharge signal
- signal
- sensor array
- ultrasonic sensor
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 93
- 230000005236 sound signal Effects 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 2
- 239000002994 raw material Substances 0.000 claims 2
- 239000012634 fragment Substances 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Testing Relating To Insulation (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a partial discharge signal detection method based on an ultrasonic sensor array, which comprises the following steps of S1: collecting sound data including partial discharge and sound data not including partial discharge, and training after marking to obtain a partial discharge signal detection model; s2: performing primary detection by using a partial discharge signal detection model; s3: performing DOA estimation on the suspected partial discharge signal in the preliminary detection to determine a partial discharge position; s4: the local discharge direction is used as an enhancement direction to enhance the sound signal; s5: and identifying the enhanced partial discharge signal by using a partial discharge signal monitoring model, and judging whether the partial discharge signal exists. The invention has the advantages that: intercepting suspected partial discharge signal fragments through primary feature identification, and then performing DOA estimation on the intercepted partial discharge signal and the signal, so that the signal-to-noise ratio is improved, and the positioning accuracy is improved; through the array enhancement technology, non-contact detection can be realized, the detection visual field can be enlarged, and the equipment cost and the operation time are reduced.
Description
Technical Field
The invention relates to the technical field of partial discharge detection, in particular to a partial discharge signal detection method and system based on an ultrasonic sensor array.
Background
In common power system equipment, such as a switch cabinet, a GIS (gas insulated switchgear), a transformer, etc., an insulation fault is one of the most common faults. The insulation failure may cause a partial discharge phenomenon, which may further deteriorate the insulation performance of the device, and thus the detection and positioning of the partial discharge signal may play an important role in the power system.
The existing stage partial discharge detection method is mainly divided into two types: ultrasonic methods and ultrahigh frequency methods. The ultrahigh frequency method carries out detection according to electromagnetic wave signals, has good sensitivity, can realize the positioning of a discharge position, is beneficial to the realization of real-time online detection, and can refer to Kabe, S, T.Yamagiwa and H.Okubo.Detection of Harmful Metallic particulate instruments Gas Insulated switched used UHF Sensor [ J ]. IEEE Transactions on semiconductors and electric instruments 2008,15(3): 701-); but have the disadvantages of being susceptible to electromagnetic interference and relatively high equipment costs. The ultrasonic method is a method of detecting by measuring an ultrasonic signal generated by partial discharge. The method has the advantages that the measurement is not connected with an electric loop inside the electric equipment, the influence of electric quantity change is avoided, and the anti-electromagnetic interference is strong. The disadvantage is that the measurement sensitivity is easily affected by the propagation path, and is easily affected by the vibration of the measurement equipment and the environmental noise, which causes great errors. The two methods have advantages and disadvantages respectively, and are different in adaptive scenes.
The invention patent application with publication number CN113092972A discloses a partial discharge type identification method and device based on a non-contact ultrasonic sensor, which adopts single-channel data to perform detection through partial discharge acoustic characteristic comparison. The method can not accurately position the local position, can not form spatial filtering, and has limited acoustic anti-interference performance. The invention patent application with publication number CN105425128A discloses a transformer partial discharge ultrasonic detection and accurate positioning device and method, which adopts a multi-channel microphone to position a partial discharge signal, but the method only adopts signal energy as detection, does not utilize more partial discharge signal characteristics, has low detection accuracy, and the microphone needs to be arranged around the detected equipment, has a small detection range, and can only detect single equipment.
Disclosure of Invention
The invention aims to provide a method for accurately detecting partial discharge signals by an array-based ultrasonic sensor.
The invention solves the technical problems through the following technical scheme: a partial discharge signal detection method based on an ultrasonic sensor array comprises the following steps,
s1: collecting sound data including partial discharge and sound data not including partial discharge, and training after marking to obtain a partial discharge signal detection model;
s2: constructing a sensor array, continuously intercepting a sound signal to be identified through a sliding window, and performing primary detection by using a partial discharge signal detection model;
s3: performing DOA estimation on the suspected partial discharge signal in the preliminary detection to determine a partial discharge position;
s4: the local discharge direction is used as an enhancement direction to enhance the sound signal;
s5: and identifying the enhanced partial discharge signal by using a partial discharge signal monitoring model, and judging whether the partial discharge signal exists.
According to the method, through primary feature identification, suspected partial discharge signal fragments are intercepted, and then DOA estimation is carried out on the intercepted partial discharge signal and the signal, so that the signal-to-noise ratio is improved, and the positioning accuracy is improved; based on the DOA estimation result, array enhancement noise reduction is carried out, and then secondary partial discharge characteristic identification judgment is carried out, so that most of interference information can be removed, and the robustness and accuracy of detection are improved; through the array enhancement technology, non-contact detection can be realized, the detection visual field can be enlarged, unmanned monitoring can be carried out on multiple devices simultaneously, and the device cost and the operation time are reduced.
Preferably, in step S1, the partial discharge signal monitoring model is obtained through 2D convolutional neural network training.
Preferably, the 2D convolutional neural network includes an input layer, a 2D convolutional layer, a pooling layer, a full-link layer, and a softmax layer, which are connected in sequence, where the softmax layer includes two output nodes, and outputs probabilities including and not including the partial discharge information, respectively.
Preferably, in step S1, the audio data is subjected to short-time fourier transform before training, and converted into a spectrogram with equal time length, and the spectrogram is used as input data of the 2D convolutional neural network.
Preferably, the length of the sliding window in step S2 is the same as the time length of the training sample, the moving length of the sliding window is also the same as the time length of the training sample, and the time domain signal intercepted by the sliding window is subjected to short-time fourier transform to obtain the spectrogram.
Preferably, the primary probability of the partial discharge existing in the initial detection output of the partial discharge signal detection model is P1, and if P1> PT1, the signal to be detected is considered as a suspected partial discharge signal, where PT1 is less than 0.5.
Preferably, in step S3, the sound signal and the sensor array position acquired by each sensor in the time period corresponding to the suspected partial discharge signal are acquired, and all the sound signals are used as input of array DOA estimation to perform broadband DOA estimation; and if the DOA spectrum peak value is larger than the preset threshold T, the DOA corresponding to the spectrum peak position is the partial discharge direction.
Preferably, the method for enhancing the sound signal is,
the DOA direction is taken as the enhancement direction, the MVDR enhancement algorithm is adopted to reduce the noise of the signal intercepted in the sliding window, the formula is as follows,
X＝FFT(x)
wherein, X represents a multi-channel signal matrix intercepted by a sliding window, the matrix size is Nr multiplied by N, Nr is the number of channels, N is the time length of the sliding window, FFT () represents fast Fourier transform, IFFT () represents inverse fast Fourier transform, a (f) is a direction vector corresponding to a frequency point f, which is the result of DOA calculation in the last step,
and outputting the noise-reduced output result.
Preferably, the time domain signal after the enhancement and the noise reduction is subjected to short-time Fourier transform again, the spectrogram obtained by conversion is input into the partial discharge signal detection model, the quadratic probability of the existence of the partial discharge signal is calculated to be P2, and when P2 is more than or equal to PT2, the partial discharge signal is considered to exist in the intercepted signal; wherein PT2 is a secondary partial discharge characteristic judgment probability threshold, and PT2 is greater than PT 1.
The invention also provides a partial discharge signal detection system based on the ultrasonic sensor array, which comprises,
the training module is used for acquiring sound data including partial discharge and sound data not including partial discharge, and training the sound data after marking to obtain a partial discharge signal detection model;
the initial detection module is used for constructing a sensor array, continuously intercepting a sound signal to be identified through a sliding window and performing initial detection by using a partial discharge signal detection model;
the partial discharge positioning module is used for carrying out DOA estimation on a suspected partial discharge signal in the preliminary detection to determine a partial discharge position;
the enhancement noise reduction module is used for enhancing the sound signal by taking the partial discharge direction as an enhancement direction;
and the secondary judgment module is used for identifying the enhanced partial discharge signal by using the partial discharge signal monitoring model and judging whether the partial discharge signal exists.
The partial discharge signal detection method and system based on the ultrasonic sensor array have the advantages that: intercepting suspected partial discharge signal fragments through primary feature identification, and then performing DOA estimation on the intercepted partial discharge signal and the signal, so that the signal-to-noise ratio is improved, and the positioning accuracy is improved; based on the DOA estimation result, array enhancement noise reduction is carried out, and then secondary partial discharge characteristic identification judgment is carried out, so that most of interference information can be removed, and the robustness and accuracy of detection are improved; through the array enhancement technology, non-contact detection can be realized, the detection visual field can be enlarged, unmanned monitoring can be carried out on multiple devices simultaneously, and the device cost and the operation time are reduced.
Drawings
Fig. 1 is a flowchart of a partial discharge signal detection method based on an ultrasonic sensor array according to an embodiment of the present invention;
fig. 2 is a structural diagram of a convolutional neural network of a partial discharge signal detection method based on an ultrasonic sensor array according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a sliding window intercepting sound segment of a partial discharge signal detection method based on an ultrasonic sensor array according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an ultrasonic sensor array-based partial discharge signal detection system according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention are described below in detail and completely with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the present embodiment provides a partial discharge signal detection method based on an ultrasonic sensor array, including,
s1: collecting sound data including partial discharge and sound data not including partial discharge, and training after marking to obtain a partial discharge signal detection model;
s2: constructing a sensor array, continuously intercepting a sound signal to be detected through a sliding window, and performing primary detection by using a partial discharge signal detection model;
s3: performing DOA estimation on the suspected partial discharge signal in the preliminary detection to determine a partial discharge position;
s4: the local discharge direction is used as an enhancement direction to enhance the sound signal;
s5: and identifying the enhanced partial discharge signal by using a partial discharge signal monitoring model, and judging whether the partial discharge signal exists.
In the embodiment, through primary feature identification, a suspected partial discharge signal fragment is intercepted, and then DOA estimation is carried out on the intercepted partial discharge signal and a signal, so that the signal to noise ratio is improved, and the positioning accuracy is improved; based on the DOA estimation result, array enhancement noise reduction is carried out, and then secondary partial discharge characteristic identification judgment is carried out, so that most of interference information can be removed, and the robustness and accuracy of detection are improved; through the array enhancement technology, non-contact detection can be realized, the detection visual field can be enlarged, unmanned monitoring can be carried out on multiple devices simultaneously, and the device cost and the operation time are reduced.
Specifically, the partial discharge signal detection method based on the ultrasonic sensor array provided by this embodiment includes the following steps:
s1: collecting sound data including partial discharge and sound data not including partial discharge, and training after marking to obtain a partial discharge signal detection model;
in this embodiment, choose for use 2D convolutional neural network to train and obtain the partial discharge signal detection model, refer to fig. 2, 2D convolutional neural network includes input layer, 2D convolutional layer, pooling layer, full connection layer and softmax layer that connect gradually, softmax layer includes two output nodes, is used for outputting the probability that contains the information of partial discharge and does not contain the information of partial discharge respectively.
The selected sound samples should have the same duration, before model training, sample data needs to be subjected to short-time Fourier transform (STFT) to be converted into a spectrogram with the same time length, the converted spectrogram is input into a 2D convolutional neural network for training, and the specific training process, termination conditions and the like are conventional means in the field and are not described again here.
S2: constructing a sensor array, recording position coordinates of each sensor, continuously intercepting a sound signal to be identified through a sliding window, and performing primary detection by using a partial discharge signal detection model;
because each sensor arranged in the array can collect the sound signal, the sound signal of any one sensor can be selected as the signal to be identified for processing; the time length of the sliding window is consistent with the time length of the training sample, and the moving length of the sliding window should not be greater than the time length of the training sample, so as to avoid the missing situation.
And converting the time domain signal intercepted by the sliding window into a spectrogram through short-time Fourier transform, and then inputting the spectrogram into a trained partial discharge signal detection model for judgment.
The primary probability of the partial discharge signal existing output by the partial discharge signal detection model through preliminary detection is P1, if P1> PT1, the signal to be detected intercepted by the sliding window is considered to be a suspected partial discharge signal, wherein PT1 is a threshold value preset according to experience, and in the embodiment, PT1 is less than 0.5.
S3: performing DOA estimation on the suspected partial discharge signal in the preliminary detection to determine a partial discharge position;
the method comprises the steps of acquiring sound signals of each sensor arranged in an array and the array position of the sensor aiming at a time period corresponding to a suspected partial discharge signal, taking all the sound signals as input of array DOA estimation, carrying out broadband DOA estimation, and if a DOA spectrum peak value is larger than a preset threshold T, determining the DOA corresponding to the spectrum peak position as a partial discharge direction, wherein the DOA estimation method is the prior art, and the threshold T is an empirical value.
S4: the local discharge direction is used as an enhancement direction to enhance the sound signal;
the DOA direction is taken as the enhancement direction, the MVDR enhancement algorithm is adopted to reduce the noise of the signal intercepted in the sliding window, the formula is as follows,
X＝FFT(x)
wherein, X represents a multi-channel signal matrix intercepted by a sliding window, the matrix size is Nr multiplied by N, Nr is the number of channels, N is the time length of the sliding window, FFT () represents fast Fourier transform, IFFT () represents inverse fast Fourier transform, a (f) is a direction vector corresponding to a frequency point f, which is the result of DOA calculation in the last step,
and outputting the noise-reduced output result.
S5: and identifying the enhanced partial discharge signal by using a partial discharge signal monitoring model, and judging whether the partial discharge signal exists.
Performing short-time Fourier transform on the time domain signal subjected to noise reduction enhancement again, inputting a spectrogram obtained by conversion into a partial discharge signal detection model, and calculating that the secondary probability of the partial discharge signal is P2, and when P2 is more than or equal to PT2, considering that the partial discharge signal exists in the intercepted signal; wherein PT2 is a secondary partial discharge characteristic determination probability threshold, PT2> PT1, and in this embodiment, PT2 is 0.5.
Because the partial discharge signal is a transient signal, the accuracy of array positioning cannot be improved through time accumulation, and the partial discharge signal is creatively identified through twice positioning in the embodiment, so that the sound signal of partial discharge obviously does not exist in the filtering process, then the suspected signal is subjected to targeted DOA estimation and signal enhancement, and then the enhanced signal is identified, so that the partial discharge detection and positioning can be quickly, effectively and accurately realized, and an important role is played in the abnormal detection of the power system.
Referring to fig. 4, the present embodiment further provides an ultrasonic sensor array-based partial discharge signal detection system, including,
the training module is used for acquiring sound data including partial discharge and sound data not including partial discharge, and training the sound data after marking to obtain a partial discharge signal detection model;
the initial detection module is used for constructing a sensor array, continuously intercepting a sound signal to be identified through a sliding window and performing initial detection by using a partial discharge signal detection model;
the partial discharge positioning module is used for carrying out DOA estimation on a suspected partial discharge signal in the preliminary detection to determine a partial discharge position;
the enhancement noise reduction module is used for enhancing the sound signal by taking the partial discharge direction as an enhancement direction;
and the secondary judgment module is used for identifying the enhanced partial discharge signal by using the partial discharge signal monitoring model and judging whether the partial discharge signal exists.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A partial discharge signal detection method based on an ultrasonic sensor array is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
s1: collecting sound data including partial discharge and sound data not including partial discharge, and training after marking to obtain a partial discharge signal detection model;
s2: constructing a sensor array, continuously intercepting a sound signal to be identified through a sliding window, and performing primary detection by using a partial discharge signal detection model;
s3: performing DOA estimation on the suspected partial discharge signal in the preliminary detection to determine a partial discharge position;
s4: the local discharge direction is used as an enhancement direction to enhance the sound signal;
s5: and identifying the enhanced partial discharge signal by using a partial discharge signal monitoring model, and judging whether the partial discharge signal exists.
2. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 1, characterized in that: in step S1, the partial discharge signal monitoring model is obtained through 2D convolutional neural network training.
3. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 2, characterized in that: the 2D convolutional neural network comprises an input layer, a 2D convolutional layer, a pooling layer, a full-link layer and a softmax layer which are sequentially connected, wherein the softmax layer comprises two output nodes, and the probability that the partial discharge information is contained and the probability that the partial discharge information is not contained is respectively output.
4. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 2, characterized in that: in step S1, short-time fourier transform is performed on the audio data before training, and the audio data is converted into a spectrogram with an equal time length, and the spectrogram is used as input data of the 2D convolutional neural network.
5. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 4, wherein: in step S2, the length of the sliding window is the same as the time length of the training sample, the moving length of the sliding window is also the same as the time length of the training sample, and the time domain signal intercepted by the sliding window is subjected to short-time fourier transform to obtain a spectrogram.
6. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 1, characterized in that: the primary probability of the partial discharge signal detection model for primary detection output is P1, if P1> PT1, the signal to be detected is considered to be a suspected partial discharge signal, wherein PT1 is less than 0.5.
7. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 1, characterized in that: in step S3, acquiring a sound signal and a sensor array position acquired by each sensor in a time period corresponding to the suspected partial discharge signal, and performing broadband DOA estimation by using all the sound signals as input of array DOA estimation; and if the DOA spectrum peak value is larger than the preset threshold T, the DOA corresponding to the spectrum peak position is the partial discharge direction.
8. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 7, wherein: the method for enhancing the sound signal is that,
the DOA direction is taken as the enhancement direction, the MVDR enhancement algorithm is adopted to reduce the noise of the signal intercepted in the sliding window, the formula is as follows,
X＝FFT(x)
wherein, X represents a multi-channel signal matrix intercepted by a sliding window, the matrix size is Nr multiplied by N, Nr is the number of channels, N is the time length of the sliding window, FFT () represents fast Fourier transform, IFFT () represents inverse fast Fourier transform, a (f) is a direction vector corresponding to a frequency point f, which is the result of DOA calculation in the last step,
and outputting the noise-reduced output result.
9. The partial discharge signal detection method based on the ultrasonic sensor array according to claim 8, wherein: performing short-time Fourier transform on the time domain signal subjected to noise reduction enhancement again, inputting a spectrogram obtained by conversion into a partial discharge signal detection model, and calculating that the secondary probability of the partial discharge signal is P2, and when P2 is more than or equal to PT2, considering that the partial discharge signal exists in the intercepted signal; wherein PT2 is a secondary partial discharge characteristic judgment probability threshold, and PT2 is greater than PT 1.
10. The utility model provides a signal detecting system is put in office based on ultrasonic sensor array which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the training module is used for acquiring sound data including partial discharge and sound data not including partial discharge, and training the sound data after marking to obtain a partial discharge signal detection model;
the initial detection module is used for constructing a sensor array, continuously intercepting a sound signal to be identified through a sliding window and performing initial detection by using a partial discharge signal detection model;
the partial discharge positioning module is used for carrying out DOA estimation on a suspected partial discharge signal in the preliminary detection to determine a partial discharge position;
the enhancement noise reduction module is used for enhancing the sound signal by taking the partial discharge direction as an enhancement direction;
and the secondary judgment module is used for identifying the enhanced partial discharge signal by using the partial discharge signal monitoring model and judging whether the partial discharge signal exists.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111477321.7A CN114201991B (en) | 2021-12-06 | 2021-12-06 | A partial discharge signal detection method and system based on ultrasonic sensor array |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111477321.7A CN114201991B (en) | 2021-12-06 | 2021-12-06 | A partial discharge signal detection method and system based on ultrasonic sensor array |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114201991A true CN114201991A (en) | 2022-03-18 |
| CN114201991B CN114201991B (en) | 2025-03-28 |
Family
ID=80650557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111477321.7A Active CN114201991B (en) | 2021-12-06 | 2021-12-06 | A partial discharge signal detection method and system based on ultrasonic sensor array |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114201991B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115097266A (en) * | 2022-06-20 | 2022-09-23 | 国网上海市电力公司 | Power cable partial discharge type identification method and device and storage medium |
| CN115166453A (en) * | 2022-09-08 | 2022-10-11 | 国网智能电网研究院有限公司 | Method and device for continuous monitoring of partial discharge based on edge real-time radio frequency pulse classification |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101702000A (en) * | 2009-11-26 | 2010-05-05 | 华北电力大学（保定） | Phase-controlled ultrasonic positioning method and system for transformer partial discharge |
| US20140340096A1 (en) * | 2011-09-16 | 2014-11-20 | Olaf Rudolph | Method for Identifying One or More Simultaneously Occurring Partial Discharge Sources |
| CN107505548A (en) * | 2017-08-29 | 2017-12-22 | 华北电力大学（保定） | A kind of type local-discharge ultrasonic localization method based on flexible array sensor |
| CN109655720A (en) * | 2018-12-18 | 2019-04-19 | 北京三听科技有限公司 | Partial discharge detection method and device based on two-dimensional sensor array |
| CN110031729A (en) * | 2018-12-08 | 2019-07-19 | 全球能源互联网欧洲研究院 | Detection method, system and the data fusion analytical unit in local discharge signal source |
-
2021
- 2021-12-06 CN CN202111477321.7A patent/CN114201991B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101702000A (en) * | 2009-11-26 | 2010-05-05 | 华北电力大学（保定） | Phase-controlled ultrasonic positioning method and system for transformer partial discharge |
| US20140340096A1 (en) * | 2011-09-16 | 2014-11-20 | Olaf Rudolph | Method for Identifying One or More Simultaneously Occurring Partial Discharge Sources |
| CN107505548A (en) * | 2017-08-29 | 2017-12-22 | 华北电力大学（保定） | A kind of type local-discharge ultrasonic localization method based on flexible array sensor |
| CN110031729A (en) * | 2018-12-08 | 2019-07-19 | 全球能源互联网欧洲研究院 | Detection method, system and the data fusion analytical unit in local discharge signal source |
| CN109655720A (en) * | 2018-12-18 | 2019-04-19 | 北京三听科技有限公司 | Partial discharge detection method and device based on two-dimensional sensor array |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115097266A (en) * | 2022-06-20 | 2022-09-23 | 国网上海市电力公司 | Power cable partial discharge type identification method and device and storage medium |
| CN115097266B (en) * | 2022-06-20 | 2024-11-29 | 国网上海市电力公司 | Power cable partial discharge type identification method, device and storage medium |
| CN115166453A (en) * | 2022-09-08 | 2022-10-11 | 国网智能电网研究院有限公司 | Method and device for continuous monitoring of partial discharge based on edge real-time radio frequency pulse classification |
| CN115166453B (en) * | 2022-09-08 | 2023-01-24 | 国网智能电网研究院有限公司 | Partial discharge continuous monitoring method and device based on edge real-time radio frequency pulse classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114201991B (en) | 2025-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107942206B (en) | GIS partial discharge positioning method | |
| CN105676085B (en) | Based on extra-high voltage GIS detection method for local discharge combined of multi-sensor information | |
| CN108169639B (en) | A method for identifying switchgear faults based on parallel long-short-term memory neural network | |
| CN107102244B (en) | Discharge source location method for GIS UHF partial discharge on-line monitoring device | |
| CN107748314A (en) | Transformer Faults Analysis system based on sound wave shock detection | |
| CN109029960B (en) | A method for detecting the mechanical state of a circuit breaker | |
| CN207300606U (en) | Transformer information collecting device based on Principles of Acoustics | |
| CN202720309U (en) | Detection and positioning system for partial discharging | |
| CN109029959B (en) | A method for detecting mechanical state of transformer windings | |
| KR20140120331A (en) | System for analyzing and locating partial discharges | |
| CN114201991B (en) | A partial discharge signal detection method and system based on ultrasonic sensor array | |
| CN113156278A (en) | CNN network-based GIS partial discharge positioning method | |
| CN114113943A (en) | Transformer partial discharge detection system, method and equipment based on current and ultrasonic signals | |
| CN114813129B (en) | Rolling bearing acoustic signal fault diagnosis method based on WPE and EMD | |
| CN114839269B (en) | Nondestructive testing method and device for internal defect stress of GIS solid insulator | |
| CN113406441B (en) | Flexible direct-current power grid fault location method based on clustering and iterative algorithm | |
| CN118859038A (en) | A method for detecting electric wire defects | |
| CN109884483A (en) | Acoustic online monitoring method and device for partial discharge of insulated tubular busbar | |
| CN111983390B (en) | GIS fault accurate positioning system based on vibration signal | |
| CN113419152B (en) | Acoustic-electric composite based fault insulator online detection device and detection method | |
| CN114814493B (en) | Four-segment type cable partial discharge source double-end monitoring and positioning method | |
| CN107040269A (en) | Pole based on variance medium filtering/ultralow frequency channel atmospheric noise suppressing method | |
| CN117116293A (en) | Machine equipment fault diagnosis system in complex sound field environment | |
| CN117148074A (en) | Low-frequency transformer partial discharge combined positioning method and related equipment | |
| Tian et al. | Accurate fault location of hybrid lines in distribution networks |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |