CN109507510A - A kind of transformer fault diagnosis system - Google Patents
A kind of transformer fault diagnosis system Download PDFInfo
- Publication number
- CN109507510A CN109507510A CN201811437681.2A CN201811437681A CN109507510A CN 109507510 A CN109507510 A CN 109507510A CN 201811437681 A CN201811437681 A CN 201811437681A CN 109507510 A CN109507510 A CN 109507510A
- Authority
- CN
- China
- Prior art keywords
- frame
- audio
- audio signal
- transformer
- fault diagnosis
- 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.)
- Withdrawn
Links
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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Abstract
The invention discloses a kind of transformer fault diagnosis systems, including data acquisition module, data processing module, fault diagnosis module and monitor supervision platform;The audio signal that data collecting module collected transformer issues when working;Data processing module handles the audio signal of acquisition, to obtain the audio feature information of audio signal;The audio feature information for the audio signal that fault diagnosis module is used to issue when working normally obtained audio feature information with pre-stored transformer is compared, and determines whether transformer breaks down, and export diagnostic result to monitor supervision platform;Monitor supervision platform is alarmed, while maintenance personal being reminded to overhaul for receiving diagnostic result, and when diagnostic result shows that transformer breaks down.The system is easy to use, can be judged by the audio signal that transformer issues a variety of different faults states of substation transformer, improve the integrated level of the system, reduce the inspection number of staff, reduce costs.
Description
Technical field
The present invention relates to power equipment monitoring technical fields, and in particular to a kind of transformer fault diagnosis system.
Background technique
Abnormal voltage, abnormal current, abnormal temperature etc. are related generally to the status monitoring of transformer at present, need not simultaneous interpretation
Sensor cell is monitored.Transformer is after energization operation of closing a floodgate, and the magnetic flux of alternation can generate between iron core silicon-steel sheet in iron core
A kind of vibration of power is recorded a demerit.Therefore have " drone " sound issue, the size of this sound and be applied on transformer
Voltage and current is directly proportional.In normal operation, transformer core sound should be it is uniform, still, if there is abnormal current or
The characteristic of person's abnormal voltage, this sound will change.Meanwhile the loose-parts of transformer, iron core failure, turn-to-turn short circuit etc.
Other situations will lead to the variation of this sound property.
It is mainly at present staff's regular visit to the monitoring form of transformer sound, cannot finds the problem in time, and
And only abnormal voltage and abnormal current situation of main the problem of reflecting, subjective judgement factor is also larger, lacks quantizating index.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of transformer fault diagnosis system.
The purpose of the present invention is realized using following technical scheme:
A kind of transformer fault diagnosis system, the transformer fault diagnosis system include data acquisition module, data processing
Module, fault diagnosis module and monitor supervision platform;The data acquisition module is fixedly mounted on the transformer, for acquiring transformation
The audio signal that device issues when working;The data processing module, for handling the audio signal of acquisition, to obtain
State the audio feature information of audio signal;The fault diagnosis module, the audio for will be obtained from the data processing module
The audio feature information for the audio signal that characteristic information issues when working normally with pre-stored transformer is compared, and determines and becomes
Whether depressor breaks down, and exports diagnostic result to monitor supervision platform;The monitor supervision platform, for receiving the diagnostic result,
And when the diagnostic result shows that transformer breaks down, alarm, while maintenance personal being reminded to overhaul.
Preferably, the monitor supervision platform is equipped with memory, for storing the diagnostic result of the fault diagnosis module.
Preferably, which further includes the database being connected with the fault diagnosis module, described
The audio feature information of the audio signal issued when transformer works normally is prestored in database.
Preferably, the data acquisition module is acoustic sensor.
Preferably, the data processing module includes: audio detection unit, noise reduction unit, end-point detection unit and feature
Extraction unit;The audio detection unit, for being detected to the audio signal of acquisition, to obtain the first audio fragment;Institute
Noise reduction unit is stated, for carrying out noise reduction process to first audio fragment;The end-point detection unit, after to noise reduction
First audio fragment carries out end-point detection, to obtain the second audio fragment;The feature extraction unit is used for from second sound
Frequency snippet extraction audio feature information.
Preferably, the audio signal of described pair of acquisition detects, to obtain the first audio fragment, specifically:
(1) framing, adding window and Fast Fourier Transform (FFT) are carried out to the audio signal of acquisition, and obtains each frame audio signal
Amplitude spectrum;
(2) based on the amplitude spectrum of acquisition, the decision function of each frame audio signal is calculated using customized decision function
Value, wherein customized decision function are as follows:
In formula, in formula, T (i) is the decision function value of the i-th frame audio signal, and i=1,2 ..., I, I is the number of frame, |
Wi+1(k)|、|Wi(k)|、|Wi-1(k) | and | Wi+j(k) | it is respectively (i+1) frame, the i-th frame, (i-1) frame, (i+j) audio
The amplitude spectrum of signal, M are preset frame number, and k is frequency point;
(3) basis obtains the judgement item of the decision function value of each frame and the start frame of the first audio fragment and abort frame
Part determines the start frame and abort frame of speech frame, specifically, if connection R frame audio signal is all satisfied T (i+ since the i-th frame
R) >=λ and | Wi+r(k) | >=A, at this time the i-th frame be the first audio fragment start frame, if since s frame, and i, s meet s >=
I+R, continuous R frame audio signal be all satisfied T (s+r) < λ and | Ws+r(k) | < A, s frame is the termination of the first audio fragment at this time
Frame;The audio signal between the i-th frame and s frame is the first audio fragment at this time, wherein | Wi+r(k) | it is (i+r) frame sound
The amplitude spectrum of frequency signal, | Ws+r(k) | it is the amplitude spectrum of (s+r) frame audio signal, A is the amplitude spectrum threshold value of setting, and λ is pre-
If decision threshold, r=1,2 ..., R, R be preset frame number.
The invention has the benefit that transformer fault diagnosis system provided by the invention is easy to use, it can be to substation
A variety of different faults states of transformer are judged by the audio signal that transformer issues, and improve transformer fault diagnosis
The integrated level of system reduces the inspection number of staff, reduces costs.Transformer fault diagnosis system diagnosis simultaneously
When transformer breaks down as the result is shown, maintenance personal can be notified to repair by monitor supervision platform in time, so as to
It realizes the high performance of substation transformer, restores reliability, improves the economy of maintenance and replace faulty equipment in due course.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the structural block diagram of transformer fault diagnosis system provided in an embodiment of the present invention;
Fig. 2 is the frame construction drawing of data processing module 2 in the embodiment of the present invention.
Appended drawing reference: data acquisition module 1;Data processing module 2;Fault diagnosis module 3;Monitor supervision platform 4;Database 5;
Audio monitoring unit 20;Noise reduction unit 21;End-point detection unit 22;Feature extraction unit 23.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, it illustrates a kind of transformer fault diagnosis system, which includes that data are adopted
Collect module 1, data processing module 2, fault diagnosis module 3 and monitor supervision platform 4;The data acquisition module 1, is fixedly mounted on change
On depressor, for acquiring the audio signal issued when transformer work;The data processing module 2, for the audio to acquisition
Signal is handled, to obtain the audio feature information of the audio signal;The fault diagnosis module 3, for will be from described
The audio for the audio signal that the audio feature information and pre-stored transformer that data processing module 2 obtains issue when working normally
Characteristic information is compared, and determines whether transformer breaks down, and exports diagnostic result to monitor supervision platform 4;The monitoring is flat
Platform 4 is alarmed, is mentioned simultaneously for receiving the diagnostic result, and when the diagnostic result shows that transformer breaks down
Awake maintenance personal overhauls.
The invention has the benefit that transformer fault diagnosis system provided by the invention is easy to use, it can be to substation
A variety of different faults states of transformer are judged by the audio signal that transformer issues, and improve transformer fault diagnosis
The integrated level of system reduces the inspection number of staff, reduces costs.Transformer fault diagnosis system diagnosis simultaneously
When transformer breaks down as the result is shown, maintenance personal can be notified to repair by monitor supervision platform in time, so as to
It realizes the high performance of substation transformer, restores reliability, improves the economy of maintenance and replace faulty equipment in due course.
Preferably, the monitor supervision platform 4 is equipped with memory, for storing the diagnostic result of the fault diagnosis module 3.
Preferably, which further includes the database 5 being connected with the fault diagnosis module 3, institute
State the audio feature information that the audio signal issued when transformer works normally is prestored in database 5.
Preferably, the data acquisition module 1 is acoustic sensor.
Preferably, referring to fig. 2, the data processing module 2 includes: audio detection unit 20, noise reduction unit 21, endpoint inspection
Survey unit 22 and feature extraction unit 23;The audio detection unit 20, for being detected to the audio signal of acquisition, to obtain
Take the first audio fragment;The noise reduction unit 21, for carrying out noise reduction process to first audio fragment;The end-point detection
Unit 22, for carrying out end-point detection to the first audio fragment after noise reduction, to obtain the second audio fragment;The feature extraction
Unit 23, for extracting audio feature information from second audio fragment.
Preferably, the audio signal of described pair of acquisition detects, to obtain the first audio fragment, specifically:
(1) framing, adding window and Fast Fourier Transform (FFT) are carried out to the audio signal of acquisition, and obtains each frame audio signal
Amplitude spectrum;
(2) based on the amplitude spectrum of acquisition, the decision function of each frame audio signal is calculated using customized decision function
Value, wherein customized decision function are as follows:
In formula, in formula, T (i) is the decision function value of the i-th frame audio signal, and i=1,2 ..., I, I is the number of frame, |
Wi+1(k)|、|Wi(k)|、|Wi-1(k) | and | Wi+j(k) | it is respectively (i+1) frame, the i-th frame, (i-1) frame, (i+j) audio
The amplitude spectrum of signal, M are preset frame number, and k is frequency point;
(3) basis obtains the judgement item of the decision function value of each frame and the start frame of the first audio fragment and abort frame
Part determines the start frame and abort frame of speech frame, specifically, if connection R frame audio signal is all satisfied T (i+ since the i-th frame
R) >=λ and | Wi+r(k) | >=A, at this time the i-th frame be the first audio fragment start frame, if since s frame, and i, s meet s >=
I+R, continuous R frame audio signal be all satisfied T (s+r) < λ and | Ws+r(k) | < A, s frame is the termination of the first audio fragment at this time
Frame;The audio signal between the i-th frame and s frame is the first audio fragment at this time, wherein | Wi+r(k) | it is (i+r) frame sound
The amplitude spectrum of frequency signal, | Ws+r(k) | it is the amplitude spectrum of (s+r) frame audio signal, A is the amplitude spectrum threshold value of setting, and λ is pre-
If decision threshold, r=1,2 ..., R, R be preset frame number.
The utility model has the advantages that in the above-described embodiment, by being carried out in framing, adding window and quick Fu to the audio signal of acquisition
After leaf transformation, the amplitude spectrum of each frame audio signal is calculated, later based on obtained amplitude spectrum, utilizes customized judgement letter
Number calculates the decision function value of each frame audio signal, the decision function value and the first audio of each frame being then based on
The start frame of segment and the judgment condition of abort frame are successively sentenced to whether each frame audio signal belongs to the first audio fragment
It is fixed, and then the accurate detection to the first audio fragment is realized, which simply easily realizes, reduction alleviates noise reduction unit
21, endpoint detection module 22, characteristic extracting module 23 and fault diagnosis module 3 work load, i.e., noise reduction unit 21, endpoint inspection
3 survey module 22, characteristic extracting module 23 and fault diagnosis module need are directed to the speech frame extracted and are handled, and improve change
The working efficiency of depressor fault diagnosis system realizes the accurate detection whether broken down to transformer.
Preferably, described that noise reduction process is carried out to first audio fragment, specifically:
(1) obtain the amplitude spectrum, phase spectrum, power spectral density value of each frame audio signal of first audio fragment with
And the average power spectral density value of noise;
(2) it according to the average power spectral density value of obtained power spectral density value and noise, is calculated using following formula each
The gain factor of frame:
In formula, g (k, d) is the gain factor of d frame audio signal, and d=1,2 ..., D, D is the frame of the first audio fragment
Number, Py(k, d) is the power spectral density value of d frame, Pσ(k) be noise average power spectral density value, ζ be preset decaying because
Son meets 0 < ζ < 1, and η is preset gain compensation factor, and k is frequency point;
(3) according to the gain factor and amplitude spectrum being calculated, the amplitude spectrum of each frame in the first audio fragment is calculated
Estimated value:
In formula,For the estimated value of the amplitude spectrum of d frame, | Wd(k) | it is the amplitude spectrum of d frame;
(4) it is inverse to carry out Fourier for the estimated value to the amplitude spectrum of each frame of the first obtained audio fragment and phase spectrum
Transformation restores time-domain audio signal;
(5) window and superposition processing are carried out to obtained time-domain audio signal, the first audio piece after noise reduction can be obtained
Section.
The utility model has the advantages that in above-described embodiment, by calculating the gain factor of each frame in the first audio fragment, so it is adaptive
That answers estimates the amplitude spectrum of each frame, obtains the estimated value of the amplitude spectrum of each frame of the first audio fragment, right again later
Each frame carries out inverse Fourier transform, removes window, superposition processing, the time domain sound after the first audio fragment noise reduction process can be obtained
Frequency signal.The algorithm can effectively inhibit the random noise in the first audio fragment, while enhance non-noise part, Er Qiegen
According to the relationship of the average power spectral density value of the amplitude spectrum and noise of each frame, corresponding formula is selected to obtain the increasing of each frame
The beneficial factor realizes the self-adaptive solution to each frame, so that retaining the thin of non-noise part in the first audio fragment after noise reduction
Feature is saved, and then is conducive to extract audio feature information in subsequent the first audio fragment from after noise reduction, improves the transformer
The accuracy of the fault diagnosis of fault diagnosis system.
In one embodiment, first audio fragment to after noise reduction carries out end-point detection, to obtain the second audio
Segment, specifically: framing, adding window and Fast Fourier Transform (FFT) first being carried out to the first audio fragment after noise reduction, then to processing
Every frame signal of the first audio fragment afterwards carries out end-point detection, judges whether each frame is effective audio frame, all effective sounds
The set that frequency frame is constituted is the second audio fragment.
Wherein, end-point detection is carried out to every frame signal of treated the first audio fragment, judges whether each frame has
Imitate audio frame.By taking pth frame signal as an example, realization process is:
(1) by the frame voice signal be divided into (2L+1) it is a it is uniform, do not overlap subband, according to the frequency spectrum of the subband
Energy generates subband power and composes entropy probability density, the calculating formula of the probability density of the Power Spectral Entropy of subband are as follows: Wherein, pltFor the probability density of the Power Spectral Entropy of t-th of subband, E (t), E (l) are respectively
For t-th of subband, the spectrum energy of first subband, t=1,2 ..., (2L+1), by (2L+1) a subband according to spectral energy values
After carrying out descending arrangement,It indicates to take median from the sub-bands of frequencies energy sequence to have sorted;
(2) processing is weighted to the probability density of the Power Spectral Entropy of obtained subband, obtains the son of the frame voice signal
Band power spectral envelope entropy, the calculating formula of subband power spectral envelope entropy are as follows:Wherein, HpFor the subband weighted power of pth frame voice signal
Compose entropy, plmaxThe probability density of entropy, pl are composed for maximum powerminThe probability density of entropy, pl are composed for minimum powertFor t-th of subband
Power Spectral Entropy probability density;
(3) the subband power spectral envelope entropy of the obtained frame voice signal and preset sound end decision threshold are carried out
Compare, if subband power spectral envelope entropy is greater than preset voice segments endpoint decision threshold, judges that the frame voice signal is effective
Speech frame, conversely, then the frame voice signal is noise frame.
The utility model has the advantages that by the way that every frame signal equalization is divided into multiple subbands, and utilize the formula in above-described embodiment
Calculate the probability density of the Power Spectral Entropy of each subband, so according to the probability density of the Power Spectral Entropy of obtained each subband with
The subband power spectral envelope entropy of every frame signal is calculated, and then completes end-point detection work, which improves the Shandong of end-point detection
Stick can be realized the accurate detection to effective audio frame, while the end-point detection algorithm is simple, Yi Shixian, can be quickly complete
The effectively extraction of audio frame in pairs, in order to the subsequent audio extracted from the second obtained audio fragment when the transformer works
Characteristic information.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of transformer fault diagnosis system, which is characterized in that examined including data acquisition module, data processing module, failure
Disconnected module and monitor supervision platform;
The data acquisition module is fixedly mounted on the transformer, for acquiring the audio signal issued when transformer work;
The data processing module, it is special with the audio for obtaining the audio signal for handling the audio signal of acquisition
Reference breath;
The fault diagnosis module, audio feature information and pre-stored transformation for will be obtained from the data processing module
The audio feature information for the audio signal that device issues when working normally is compared, and determines whether transformer breaks down, and defeated
Diagnostic result is to monitor supervision platform out;
The monitor supervision platform, for receiving the diagnostic result, and when the diagnostic result shows that transformer breaks down, into
Row alarm, while maintenance personal being reminded to overhaul.
2. transformer fault diagnosis system according to claim 1, which is characterized in that the monitor supervision platform is equipped with storage
Device, for storing the diagnostic result of the fault diagnosis module.
3. transformer fault diagnosis system according to claim 1, which is characterized in that further include and the fault diagnosis mould
Block connected database prestores the audio frequency characteristics letter of the audio signal issued when transformer works normally in the database
Breath.
4. transformer fault diagnosis system according to claim 1, which is characterized in that the data acquisition module is acoustics
Sensor.
5. transformer fault diagnosis system according to claim 1, which is characterized in that the data processing module includes:
Audio detection unit, noise reduction unit, end-point detection unit and feature extraction unit;
The audio detection unit, for being detected to the audio signal of acquisition, to obtain the first audio fragment;
The noise reduction unit, for carrying out noise reduction process to first audio fragment;
The end-point detection unit, for carrying out end-point detection to the first audio fragment after noise reduction, to obtain the second audio piece
Section;
The feature extraction unit, for extracting audio feature information from second audio fragment.
6. transformer fault diagnosis system according to claim 5, which is characterized in that described pair acquisition audio signal into
Row detection, to obtain the first audio fragment, specifically:
(1) framing, adding window and Fast Fourier Transform (FFT) are carried out to the audio signal of acquisition, and obtains the width of each frame audio signal
Degree spectrum;
(2) based on the amplitude spectrum of acquisition, the decision function value of each frame audio signal is calculated using customized decision function,
In, customized decision function are as follows:
In formula, in formula, T (i) is the decision function value of the i-th frame audio signal, and i=1,2 ..., I, I is the number of frame, | Wi+1(k)
|、|Wi(k)|、|Wi-1(k) | and | Wi+j(k) | it is respectively (i+1) frame, the i-th frame, (i-1) frame, (i+j) audio signal
Amplitude spectrum, M are preset frame number, and k is frequency point;
(3) basis obtains the judgment condition of the decision function value of each frame and the start frame of the first audio fragment and abort frame,
Determine the start frame and abort frame of speech frame, specifically, if since the i-th frame, connection R frame audio signal be all satisfied T (i+r) >=
λ and | Wi+r(k) | >=A, the i-th frame is the start frame of the first audio fragment at this time, if since s frame, and i, s meet s >=i+R,
Continuous R frame audio signal be all satisfied T (s+r) < λ and | Ws+r(k) | < A, s frame is the abort frame of the first audio fragment at this time;
The audio signal between the i-th frame and s frame is the first audio fragment at this time, wherein | Wi+r(k) | believe for (i+r) frame audio
Number amplitude spectrum, | Ws+r(k) | it is the amplitude spectrum of (s+r) frame audio signal, A is the amplitude spectrum threshold value of setting, and λ is preset
Decision threshold, r=1,2 ..., R, R are preset frame number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811437681.2A CN109507510A (en) | 2018-11-28 | 2018-11-28 | A kind of transformer fault diagnosis system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811437681.2A CN109507510A (en) | 2018-11-28 | 2018-11-28 | A kind of transformer fault diagnosis system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109507510A true CN109507510A (en) | 2019-03-22 |
Family
ID=65751089
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811437681.2A Withdrawn CN109507510A (en) | 2018-11-28 | 2018-11-28 | A kind of transformer fault diagnosis system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109507510A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110296842A (en) * | 2019-06-28 | 2019-10-01 | 潍柴动力股份有限公司 | The diagnostic method and device of engine |
CN110398647A (en) * | 2019-06-26 | 2019-11-01 | 深圳供电局有限公司 | Transformer's Condition Monitoring method |
CN110597130A (en) * | 2019-09-20 | 2019-12-20 | 广东电网有限责任公司 | Unattended substation remote information acquisition system |
CN110595597A (en) * | 2019-10-24 | 2019-12-20 | 国网湖南省电力有限公司 | Installation equipment for internal noise monitoring sensor of oil-immersed transformer and correction method thereof |
CN111198525A (en) * | 2020-01-03 | 2020-05-26 | 扬州海铭石油工程技术有限公司 | Audio monitoring system based on operation of oilfield field equipment and fault detection method |
CN112305462A (en) * | 2020-11-09 | 2021-02-02 | 北京中拓新源科技有限公司 | System for recognizing typical faults of transformer based on transformer sound |
CN112731026A (en) * | 2020-12-21 | 2021-04-30 | 国网上海市电力公司 | Based on transformer noise fault detection recognition device |
CN115240691A (en) * | 2022-09-23 | 2022-10-25 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
CN115993503A (en) * | 2023-03-22 | 2023-04-21 | 广东电网有限责任公司东莞供电局 | Operation detection method, device and equipment of transformer and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103165130A (en) * | 2013-02-06 | 2013-06-19 | 湘潭安道致胜信息科技有限公司 | Voice text matching cloud system |
CN104112453A (en) * | 2014-04-09 | 2014-10-22 | 天津思博科科技发展有限公司 | Audio preprocessing system |
CN105388772A (en) * | 2015-12-04 | 2016-03-09 | 重庆财信合同能源管理有限公司 | Indoor intelligent control system and method based on voice recognition |
CN107464563A (en) * | 2017-08-11 | 2017-12-12 | 潘金文 | A kind of interactive voice toy |
CN108414079A (en) * | 2018-03-21 | 2018-08-17 | 广东电网有限责任公司电力科学研究院 | A kind of transformer noise monitoring system |
CN108694954A (en) * | 2018-06-13 | 2018-10-23 | 广州势必可赢网络科技有限公司 | A kind of Sex, Age recognition methods, device, equipment and readable storage medium storing program for executing |
CN108877826A (en) * | 2018-08-29 | 2018-11-23 | 昆明理工大学 | A kind of voice noise reducing method based on more windows spectrum |
-
2018
- 2018-11-28 CN CN201811437681.2A patent/CN109507510A/en not_active Withdrawn
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103165130A (en) * | 2013-02-06 | 2013-06-19 | 湘潭安道致胜信息科技有限公司 | Voice text matching cloud system |
CN104112453A (en) * | 2014-04-09 | 2014-10-22 | 天津思博科科技发展有限公司 | Audio preprocessing system |
CN105388772A (en) * | 2015-12-04 | 2016-03-09 | 重庆财信合同能源管理有限公司 | Indoor intelligent control system and method based on voice recognition |
CN107464563A (en) * | 2017-08-11 | 2017-12-12 | 潘金文 | A kind of interactive voice toy |
CN108414079A (en) * | 2018-03-21 | 2018-08-17 | 广东电网有限责任公司电力科学研究院 | A kind of transformer noise monitoring system |
CN108694954A (en) * | 2018-06-13 | 2018-10-23 | 广州势必可赢网络科技有限公司 | A kind of Sex, Age recognition methods, device, equipment and readable storage medium storing program for executing |
CN108877826A (en) * | 2018-08-29 | 2018-11-23 | 昆明理工大学 | A kind of voice noise reducing method based on more windows spectrum |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110398647A (en) * | 2019-06-26 | 2019-11-01 | 深圳供电局有限公司 | Transformer's Condition Monitoring method |
CN110398647B (en) * | 2019-06-26 | 2022-02-15 | 深圳供电局有限公司 | Transformer state monitoring method |
CN110296842A (en) * | 2019-06-28 | 2019-10-01 | 潍柴动力股份有限公司 | The diagnostic method and device of engine |
CN110597130A (en) * | 2019-09-20 | 2019-12-20 | 广东电网有限责任公司 | Unattended substation remote information acquisition system |
CN110595597A (en) * | 2019-10-24 | 2019-12-20 | 国网湖南省电力有限公司 | Installation equipment for internal noise monitoring sensor of oil-immersed transformer and correction method thereof |
CN110595597B (en) * | 2019-10-24 | 2024-03-12 | 国网湖南省电力有限公司 | Installation equipment of noise monitoring sensor in oil immersed transformer and correction method thereof |
CN111198525B (en) * | 2020-01-03 | 2023-09-22 | 扬州海铭石油工程技术有限公司 | Operation audio monitoring system and fault detection method based on oilfield field equipment |
CN111198525A (en) * | 2020-01-03 | 2020-05-26 | 扬州海铭石油工程技术有限公司 | Audio monitoring system based on operation of oilfield field equipment and fault detection method |
CN112305462A (en) * | 2020-11-09 | 2021-02-02 | 北京中拓新源科技有限公司 | System for recognizing typical faults of transformer based on transformer sound |
CN112731026A (en) * | 2020-12-21 | 2021-04-30 | 国网上海市电力公司 | Based on transformer noise fault detection recognition device |
CN115240691B (en) * | 2022-09-23 | 2022-12-06 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
CN115240691A (en) * | 2022-09-23 | 2022-10-25 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
CN115993503A (en) * | 2023-03-22 | 2023-04-21 | 广东电网有限责任公司东莞供电局 | Operation detection method, device and equipment of transformer and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109507510A (en) | A kind of transformer fault diagnosis system | |
CN105548832B (en) | High voltage power cable fault recognition method | |
CN110534118A (en) | Transformer/reactor method for diagnosing faults based on Application on Voiceprint Recognition and neural network | |
CN102426835B (en) | Method for identifying local discharge signals of switchboard based on support vector machine model | |
CN110417351A (en) | Photovoltaic system DC side arc fault detection systems and detection method | |
CN106934421A (en) | Converting station electric power transformer fault detecting system and detection method based on 2DPCA and SVM | |
CN107748314A (en) | Transformer Faults Analysis system based on sound wave shock detection | |
CN108802525A (en) | Equipment fault intelligent Forecasting based on small sample | |
CN110244204A (en) | A kind of switchgear method for diagnosing faults, system and the medium of multiple characteristic values | |
CN110398647B (en) | Transformer state monitoring method | |
CN106875938A (en) | A kind of improved nonlinear adaptive sound end detecting method | |
CN108490349A (en) | Motor abnormal sound detection method based on Mel frequency cepstral coefficients | |
CN109949823A (en) | A kind of interior abnormal sound recognition methods based on DWPT-MFCC and GMM | |
CN109472288A (en) | A kind of pump-storage generator vibration hybrid feature extraction and classification method | |
CN112599134A (en) | Transformer sound event detection method based on voiceprint recognition | |
CN114217149A (en) | Transformer acoustic fingerprint uninterrupted power detection and state early warning method | |
Geng et al. | Mechanical fault diagnosis of power transformer by GFCC time-frequency map of acoustic signal and convolutional neural network | |
CN102988041A (en) | Selective cardiac-magnetic signal averaging method in signal noise suppression | |
CN112666430B (en) | Intelligent fault detection method and system for voiceprint of transformer | |
Dang et al. | Cochlear filter cepstral coefficients of acoustic signals for mechanical faults identification of power transformer | |
Dang et al. | Fault diagnosis of power transformer by acoustic signals with deep learning | |
CN116884432A (en) | VMD-JS divergence-based power transformer fault voiceprint diagnosis method | |
CN105352541A (en) | Transformer operation auxiliary monitoring system and method based on disaster prevention and reduction system of power grid | |
CN107040269A (en) | Pole based on variance medium filtering/ultralow frequency channel atmospheric noise suppressing method | |
CN114487952A (en) | Quench detection system and method using acoustic optical fiber |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190322 |