CN108733957A - A kind of noise characteristic extraction of for transformer fault diagnosis and judgment method - Google Patents
A kind of noise characteristic extraction of for transformer fault diagnosis and judgment method Download PDFInfo
- Publication number
- CN108733957A CN108733957A CN201810548305.4A CN201810548305A CN108733957A CN 108733957 A CN108733957 A CN 108733957A CN 201810548305 A CN201810548305 A CN 201810548305A CN 108733957 A CN108733957 A CN 108733957A
- Authority
- CN
- China
- Prior art keywords
- transformer
- noise
- membership
- template
- characteristic
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses a kind of extraction of the noise characteristic of for transformer fault diagnosis and judgment methods, solve the problems, such as that the existing sense organ empirical analysis based on people and transformer fault diagnosis technology are incomplete, include the following steps：The characteristic frequency spectrum of transformer normal operating condition and various failures is collected, and establishes database；Receiving transformer acoustic signals, and judge whether to be sent out by transformer；The characteristic vector of transformer noise is extracted, membership function is built；Calculate the distance between the noise template that is preserved in feature of noise vector sum database, obtain close to degree of membership；According to close to degree of membership, search same or similar template；Export recognition result.The characteristic vector that the present invention passes through extraction noise, further according to fuzzy recognition algorithm, calculate the distance between the noise template preserved in the characteristic vector and database of noise, find same or similar template, export recognition result, the Hidden fault for finding transformer early, ensures the safe operation of transformer.
Description
Technical field
The invention belongs to transformer monitoring technical fields, special more particularly to a kind of noise of for transformer fault diagnosis
Sign extraction and judgment method.
Background technology
Power transformer is transformer equipment important in electric system, operating status directly affect system safety,
Stability.The Hidden fault for finding transformer early, ensures the safe operation of transformer, the reliability to improve power supply is
One major issue of power department concern.Transformer fault is transformer itself and its application environment comprehensive function and long-term product
It is tired that as a result, thus the sign of transformer fault is varied, contacting between failure symptom and failure mechanism is also intricate, this
Just prodigious difficulty is caused to establishing general transformer fault control method.So far, transformer fault diagnosis technology
Research it is perfect not enough.
The acoustic signals that send out are different when its operation of different power equipments, same power transformer normally with
Under abnormal condition, the acoustic signals sent out also have very big difference.The different keys for the sound that human ear is heard are that sound
Power it is different with frequency, but the sense organ experience based on people is to the running state analysis of power equipment, also only qualitatively,
Fail to reach quantitative analysis, staff is also impossible to the acoustic signals to a certain power equipment for a long time and monitors.
Invention content
The purpose of the present invention is to provide a kind of extraction of the noise characteristic of for transformer fault diagnosis and judgment methods, lead to
The characteristic frequency spectrum for determining monitored transformer normal operating condition and different faults is crossed, using these characteristic values, structure is subordinate to letter
Number, find out close to degree of membership, the operating status of equipment is may determine that with Fuzzy Recognition, solves the existing sense based on people
Official's experience fails to reach quantitative analysis to the running state analysis of power equipment and transformer fault diagnosis technology is incomplete asks
Topic.
In order to solve the above technical problems, the present invention is achieved by the following technical solutions：Include the following steps：
SS00：The feature sound wave spectrum for being monitored transformer normal operating condition and various failures is collected, and establishes characteristic frequency spectrum
Database；
SS01：Transformer acoustic signals are acquired, and determine whether the sound wave of transformer using dynamic time warping algorithm；
SS02：The temporal characteristics vectors such as amplitude, phase, energy and probability distribution are extracted from acoustic signals, for characterizing transformation
Device state；According to above-mentioned characteristic vector, membership function is built using fuzzy statistical method, i.e.,：
Degree of membership；
SS03：Using fuzzy recognition algorithm, calculate noise characteristic vector and characteristic frequency spectrum database in the noise mould that is preserved
The distance between plate, obtain close to degree of membership；
SS04：According to close to degree of membership, search same or similar noise template；
SS05：Export recognition result, the i.e. state or failure code of transformer.
Further, in the step SS04 close to degree of membership be more than or equal to 0.9 when, find same or similar make an uproar
Sound template exports recognition result and fault type.
Further, the fault type includes that iron core magnetic flux density caused by overload increases, and big power-equipment starts
Caused load variations are larger and higher hamonic wave, and iron core is seriously saturated caused by system short-circuit, and interior contact is bad or breakdown, iron
Magnetic resonance, the filth on bushing shell for transformer surface and dense fog, rainy, cloudy day cause corona discharge, winding deformation, oil circuit to block, point
Switch is connect to loosen.
Uniform when further, noise template includes normal operation in the step SS03 " drone " several wave templates,
It is slightly rung than normal operation when overload and slightly heavy " drone " several wave templates, big power-equipment moment when starting " crying of a child " is several
When prodigious noise sound wave template, interior contact are bad when wave template, system short-circuit or have at breakdown " " or " crack "
Discharging sound sound wave template, due to ferromagnetic resonance sends out " drone " sound and tapering " " several wave templates, bushing shell for transformer table
The filth in face and dense fog, rain, the cloudy day when send out " " several wave templates.
The invention has the advantages that：The present invention will be by will largely store typical normal and fault-signal spectrum value
In a computer, constitutive characteristic frequency spectrum data library, statistics are concluded, the changing rule of analysis spectrum, obtain sentencing for fault diagnosis
According to；The characteristic vector of extraction input noise calculates the feature vector sequence and feature frequency of noise further according to the algorithm of fuzzy diagnosis
The distance between noise template preserved in modal data library, obtain close to degree of membership, degree of membership be greater than or equal to 0.9 when look for
To same or similar template, recognition result, the i.e. state or failure code of transformer are exported；Improve the accurate of transformer monitoring
Property, the Hidden fault of transformer is found early, ensures the safe operation of transformer.
Certainly, it implements any of the products of the present invention and does not necessarily require achieving all the advantages described above at the same time.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will be described below to embodiment required
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the flow chart of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained all other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
Refering to Figure 1, the present invention includes the following steps：SS00：Collect be monitored transformer normal operating condition and
The feature sound wave spectrum of various failures, and establish characteristic frequency spectrum database；
SS01：Transformer acoustic signals are acquired, and determine whether the sound wave of transformer using dynamic time warping algorithm；
SS02：The temporal characteristics such as amplitude, phase, energy and probability distribution are extracted from acoustic signals by well known computational methods
Vector, for characterizing transformer state；According to above-mentioned characteristic vector, membership function is built using fuzzy statistical method, i.e.,：
Degree of membership；
SS03：Using fuzzy recognition algorithm, calculate noise characteristic vector and characteristic frequency spectrum database in the noise mould that is preserved
The distance between plate, obtain close to degree of membership；
SS04：According to close to degree of membership, search same or similar noise template；
SS05：Export recognition result, the i.e. state or failure code of transformer.
When studying the property of sound, signal waveform is not handled directly, but becomes frequency spectrum and auto-correlation function, that is, is converted
At being handled after feature associated with frequency spectrum, sound waveform can use amplitude is constant, phase at any time it is slowly varying just
String wave is constituted.The sound characteristic for embodying transformer station high-voltage side bus situation is contained mainly in amplitude information, and phase does not work generally.
Wherein, in step SS04 close to degree of membership be more than or equal to 0.9 when, find same or similar noise template,
Export recognition result and fault type.When being less than 0.9 such as degree of membership, then illustrate transformer fault-free.
Wherein, fault type includes that iron core magnetic flux density caused by overload increases, failure code 01；Big power-equipment rises
Load variations caused by dynamic are larger and higher hamonic wave, failure code 02；Iron core caused by system short-circuit is seriously saturated, failure code
03；Interior contact is bad or punctures, failure code 04；Ferromagnetic resonance, failure code 05；The filth on bushing shell for transformer surface and big
Mist, rainy, cloudy day cause corona discharge, failure code 06；Winding deformation failure code 07；Oil circuit plugging fault code 08；Point
Connect switch looseness fault code 09.
It is uniform when noise template includes normal operation in step SS03 " drone " several wave templates, overload when than normal
Operation is slightly rung and slightly heavy " drone " several wave templates, big power-equipment moment when starting " crying of a child " several wave templates, system are short
The discharging sound sound wave mould of " " or " crack " when prodigious noise sound wave template, interior contact are bad when road or have at breakdown
Plate, due to ferromagnetic resonance sends out " drone " sound and tapering " " several wave templates, the filth on bushing shell for transformer surface and big
Mist, rain, the cloudy day when send out " " several wave templates.The operating status and failure of each transformer have it specifically to levy
Million, largely typical normal and fault-signal spectrum value storage in a computer, the characteristic frequency spectrum database of sound wave will be constituted, will be united
Meter is concluded, the changing rule of analysis spectrum, can obtain the criterion of fault diagnosis.
The present invention can establish expert system on the basis of accumulating mass data, to the operating status of power transformer into
Row intelligent diagnostics, and can expand and be applied on the operating status intelligent diagnostics of other power equipments, judge the failure classes occurred
Type predicts the failure symptom of power equipment, finds the Hidden fault of transformer early, ensures the safe operation of transformer.
Present invention disclosed above preferred embodiment is only intended to help to illustrate the present invention.There is no detailed for preferred embodiment
All details are described, are not limited the invention to the specific embodiments described.Obviously, according to the content of this specification,
It can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is in order to preferably explain the present invention
Principle and practical application, to enable skilled artisan to be best understood by and utilize the present invention.The present invention is only
It is limited by claims and its full scope and equivalent.
Claims (4)
1. a kind of noise characteristic of for transformer fault diagnosis extracts and judgment method, which is characterized in that include the following steps：
SS00：The feature sound wave spectrum for being monitored transformer normal operating condition and various failures is collected, and establishes characteristic frequency spectrum
Database；
SS01：Transformer acoustic signals are acquired, and determine whether the sound wave of transformer using dynamic time warping algorithm；
SS02：The temporal characteristics vectors such as amplitude, phase, energy and probability distribution are extracted from acoustic signals, for characterizing transformation
Device state；According to above-mentioned characteristic vector, membership function is built using fuzzy statistical method, i.e.,：
Degree of membership；
SS03：Using fuzzy recognition algorithm, calculate noise characteristic vector and characteristic frequency spectrum database in the noise mould that is preserved
The distance between plate, obtain close to degree of membership；
SS04：According to close to degree of membership, search same or similar noise template；
SS05：Export recognition result, the i.e. state or failure code of transformer.
2. the noise characteristic of for transformer fault diagnosis as described in claim 1 extracts and judgment method, it is characterised in that：
In the step SS04 close to degree of membership be more than or equal to 0.9 when, find same or similar noise template, output identification knot
Fruit and fault type.
3. the noise characteristic of for transformer fault diagnosis as claimed in claim 2 extracts and judgment method, it is characterised in that：
The fault type includes that iron core magnetic flux density caused by overload increases, and load variations are larger caused by big power-equipment starts
And higher hamonic wave, iron core caused by system short-circuit are seriously saturated, interior contact is bad or breakdown, ferromagnetic resonance, bushing shell for transformer
The filth on surface and dense fog, rainy, cloudy day cause corona discharge, winding deformation, oil circuit to block, and tap switch loosens.
4. the noise characteristic of for transformer fault diagnosis as described in claim 1 extracts and judgment method, it is characterised in that：
It is uniform when noise template includes normal operation in the step SS03 " drone " several wave templates, overload when compare normal operation
It slightly rings and when slightly heavy " drone " several wave templates, big power-equipment moment when starting " crying of a child " several wave templates, system short-circuit
The discharging sound sound wave template of " " or " crack " when prodigious noise sound wave template, interior contact are bad or have at breakdown, by
Send out in ferromagnetic resonance " drone " sound and tapering " " several wave templates, the filth on bushing shell for transformer surface and dense fog, under
Sent out when rain, cloudy day " " several wave templates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810548305.4A CN108733957A (en) | 2018-05-31 | 2018-05-31 | A kind of noise characteristic extraction of for transformer fault diagnosis and judgment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810548305.4A CN108733957A (en) | 2018-05-31 | 2018-05-31 | A kind of noise characteristic extraction of for transformer fault diagnosis and judgment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108733957A true CN108733957A (en) | 2018-11-02 |
Family
ID=63931442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810548305.4A Pending CN108733957A (en) | 2018-05-31 | 2018-05-31 | A kind of noise characteristic extraction of for transformer fault diagnosis and judgment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108733957A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111707352A (en) * | 2020-05-27 | 2020-09-25 | 国网新疆电力有限公司阿克苏供电公司 | Real-time monitoring method for vibration noise of transformer |
| CN111814917A (en) * | 2020-08-28 | 2020-10-23 | 成都千嘉科技有限公司 | Character wheel image digital identification method with fuzzy state |
| CN112484843A (en) * | 2020-11-23 | 2021-03-12 | 国网北京市电力公司 | State analysis method and device for transformer substation and electronic equipment |
| CN113253156A (en) * | 2021-05-17 | 2021-08-13 | 国网江苏省电力有限公司检修分公司 | Sound monitoring-based latent defect diagnosis method for transformer |
| CN113537082A (en) * | 2021-07-20 | 2021-10-22 | 郑州轻工业大学 | Fault identification method based on information insufficiency |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160020729A1 (en) * | 2014-07-21 | 2016-01-21 | Sungrow Power Supply Co., Ltd. | Method, device, and system for detecting direct-current arc fault of photovoltaic system |
| CN106569056A (en) * | 2016-10-21 | 2017-04-19 | 广州供电局有限公司 | Power transformer fault diagnosis method and diagnosis device |
| CN107748314A (en) * | 2017-10-18 | 2018-03-02 | 国网重庆市电力公司北碚供电分公司 | Transformer Faults Analysis system based on sound wave shock detection |
| CN107907783A (en) * | 2017-12-19 | 2018-04-13 | 西安交通大学 | Transformer fault integrated diagnostic system and diagnostic method based on fuzzy association rules |
-
2018
- 2018-05-31 CN CN201810548305.4A patent/CN108733957A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160020729A1 (en) * | 2014-07-21 | 2016-01-21 | Sungrow Power Supply Co., Ltd. | Method, device, and system for detecting direct-current arc fault of photovoltaic system |
| CN106569056A (en) * | 2016-10-21 | 2017-04-19 | 广州供电局有限公司 | Power transformer fault diagnosis method and diagnosis device |
| CN107748314A (en) * | 2017-10-18 | 2018-03-02 | 国网重庆市电力公司北碚供电分公司 | Transformer Faults Analysis system based on sound wave shock detection |
| CN107907783A (en) * | 2017-12-19 | 2018-04-13 | 西安交通大学 | Transformer fault integrated diagnostic system and diagnostic method based on fuzzy association rules |
Non-Patent Citations (6)
| Title |
|---|
| 何洪军 等: "大型变压器故障诊断识别方法", 《噪声与振动控制》 * |
| 吴松: "基于声学特征的变压器故障诊断研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
| 庞茂 等: "在线噪声检测及噪声信号的故障诊断技术研究", 《传感技术学报》 * |
| 易琳 等: "无人值守变电站电力设备音频监测及故障诊断***", 《计算机测量与控制》 * |
| 潘亮亮 等: "基于声波信号分析的电气设备故障诊断新方法", 《电力自动化设备》 * |
| 马晓强 等: "电气设备噪声的实时监测与故障诊断", 《电力学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111707352A (en) * | 2020-05-27 | 2020-09-25 | 国网新疆电力有限公司阿克苏供电公司 | Real-time monitoring method for vibration noise of transformer |
| CN111814917A (en) * | 2020-08-28 | 2020-10-23 | 成都千嘉科技有限公司 | Character wheel image digital identification method with fuzzy state |
| CN112484843A (en) * | 2020-11-23 | 2021-03-12 | 国网北京市电力公司 | State analysis method and device for transformer substation and electronic equipment |
| CN113253156A (en) * | 2021-05-17 | 2021-08-13 | 国网江苏省电力有限公司检修分公司 | Sound monitoring-based latent defect diagnosis method for transformer |
| CN113253156B (en) * | 2021-05-17 | 2023-01-06 | 国网江苏省电力有限公司检修分公司 | Sound monitoring-based latent defect diagnosis method for transformer |
| CN113537082A (en) * | 2021-07-20 | 2021-10-22 | 郑州轻工业大学 | Fault identification method based on information insufficiency |
| CN113537082B (en) * | 2021-07-20 | 2023-04-07 | 郑州轻工业大学 | Fault identification method based on information insufficiency |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108733957A (en) | A kind of noise characteristic extraction of for transformer fault diagnosis and judgment method | |
| CN106597231B (en) | GIS fault detection system and method based on Multi-source Information Fusion and deep learning network | |
| Alam et al. | An approach for assessing the effectiveness of multiple-feature-based SVM method for islanding detection of distributed generation | |
| CN103278746B (en) | Consider the implementation method of the electric network failure diagnosis system of uncertain information | |
| CN109633370B (en) | Power grid fault diagnosis method based on fault information coding and fusion method | |
| Alam et al. | Evaluating the effectiveness of a machine learning approach based on response time and reliability for islanding detection of distributed generation | |
| CN106646043B (en) | Power distribution network ferromagnetic resonance on-line monitoring system and ferromagnetic resonance classifying identification method | |
| CN111458599A (en) | Series arc fault detection method based on one-dimensional convolutional neural network | |
| CN110245168B (en) | Method and system for extracting abnormal event characteristic signals in power grid historical alarm | |
| CN112834865B (en) | Quick fault finder for secondary circuit of power system | |
| CN109417285A (en) | DC electrical loop protection device and arc method for measuring | |
| CN113671361A (en) | High-voltage circuit breaker characteristic parameter prediction method and system based on multi-source signal fusion | |
| US20020118022A1 (en) | Arc detection | |
| El Chamie et al. | Physics-based features for anomaly detection in power grids with micro-pmus | |
| CN110082082A (en) | A kind of GIS state identification method based on vibration signal Principal Component Analysis | |
| CN105337314B (en) | A kind of multi-source based on distributed power source black starting-up technology coordinates control fault handling method | |
| CN101846717A (en) | Low-current ground fault line selection device | |
| CN101860002A (en) | Computing method of preventive control measure for short-circuit current in electric power system | |
| CN108399579A (en) | The intelligently parsing system of substation equipment monitoring data signal | |
| CN112838564B (en) | Low-voltage line electric shock fault judgment method based on triple combined criteria and residual current circuit breaker | |
| CN109375037A (en) | Delay unloading a ship in one kind oceangoing ship Single-phase Earth Fault of Power System alarm designs method | |
| Niazazari et al. | Event cause analysis in distribution networks using synchro waveform measurements | |
| CN108563652A (en) | Reference information sorting technique based on brute-force searching algorithm | |
| CN112485744A (en) | Fault identification method and equipment for capacitor voltage transformer | |
| CN108196163A (en) | A kind of intelligent diagnostics analysis method for realizing complex fault |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181102 |