CN108693437A - A kind of method and system judging deformation of transformer winding - Google Patents
A kind of method and system judging deformation of transformer winding Download PDFInfo
- Publication number
- CN108693437A CN108693437A CN201810239981.3A CN201810239981A CN108693437A CN 108693437 A CN108693437 A CN 108693437A CN 201810239981 A CN201810239981 A CN 201810239981A CN 108693437 A CN108693437 A CN 108693437A
- Authority
- CN
- China
- Prior art keywords
- transformer
- deformation
- winding
- characteristic parameter
- vibration acceleration
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/72—Testing of electric windings
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of method and system judging deformation of transformer winding, the implementation steps of method include:Obtain the vibration acceleration signal of transformer to be detected;Independent characteristic parameter is extracted according to the vibration acceleration signal of transformer to be detected;Independent characteristic parameter is inputted into trained machine learning model, obtains the current winding deformation state of transformer to be detected, the machine learning model is trained to include the mapping relations between independent characteristic parameter and winding deformation state;System includes being programmed the computer equipment for executing the above method.The method that the present invention can effectively detect deformation of transformer winding state under the conditions of transformer is not stopped transport, has the advantages that not contact that charging equipment, that live detection, convenient test can be achieved is efficient.
Description
Technical field
The present invention relates to running state of transformer detection fields, and in particular to a method of judging deformation of transformer winding
And system.
Background technology
Transformer is the important component of electric system, and the electric energy that carry between different voltages grade electric power networks passes
Defeated task.Its safe operation is of great significance for providing stable, reliable supply of electric power to power consumer.Transformer winding
It is more one of the component that breaks down.By the end of the year 2006, national 110kV and ratings above power transformer are because of external short circuit
The accident that failure damages reaches the 50% of total number of accident.From the point of view of observing conditions to the disintegration of transformer after accident, by around
Transformer fault has accounted for the overwhelming majority caused by group deformation.Therefore, it is necessary to effectively be detected to deformation of transformer winding.Mesh
Before, common deformation of transformer winding detection method include winding capacitance, winding frequency response, short-circuit impedance experiment based on, it is above
Method is required to stop transport in transformer, be primarily present can not live detection, security risk is larger, detection cycle is long, detection efficiency
The problems such as low.
Invention content
The technical problem to be solved in the present invention:For the above problem of the prior art, a kind of judgement transformer winding is provided
The method and system of deformation, the present invention can effectively detect the side of deformation of transformer winding state under the conditions of transformer is not stopped transport
Method, has the advantages that not contact that charging equipment, that live detection, convenient test can be achieved is efficient.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention is:
A method of judging that deformation of transformer winding, implementation steps include:
1) vibration acceleration signal of transformer to be detected is obtained;
2) independent characteristic parameter is extracted according to the vibration acceleration signal of transformer to be detected;
3) independent characteristic parameter is inputted into trained machine learning model, obtains the current winding of transformer to be detected and becomes
Shape state, the machine learning model are trained to include the mapping relations between independent characteristic parameter and winding deformation state.
Preferably, the detailed step of step 2) includes:
2.1) vibration acceleration signal of transformer to be detected is pre-processed;
2.2) spectrum analysis and wavelet packet analysis are carried out to pretreated vibration acceleration signal, therefrom associated extraction around
Group deformation behaviour parameter;
2.3) it is directed to winding deformation characteristic parameter and carries out principal component analysis, obtain independent characteristic parameter.
Preferably, the detailed step of step 2.2) includes:
2.2.1 Fourier transformation) is carried out to the vibration acceleration signal that the multiple measuring points of transformer detect, intercepts 8kHz
Vibration acceleration signal frequency spectrum in range, and the progress arithmetic average processing of the vibration acceleration frequency spectrum of multiple measuring points is formed comprehensive
Sum of fundamental frequencies is composed, and the dominant frequency proportion R of integral spectrum is calculatedm;
2.2.2 the 50Hz and its spectrum complex degree H of harmonic frequency in vibration acceleration signal 8kHz spectral ranges) is calculated;
2.2.3 wavelet packet analysis) is carried out respectively to the vibration acceleration signal of the multiple measuring points of transformer, calculates separately small echo
Packet energy simultaneously carries out arithmetic average processing, obtains comprehensive wavelet pack energy feature E;
2.2.4) by dominant frequency proportion Rm, spectrum complex degree H collectively form winding change with comprehensive wavelet pack energy feature E three
Shape characteristic parameter.
Preferably, step 2.2.1) in integral spectrum dominant frequency proportion RmCalculating function expression such as formula (1) shown in;
In formula (1), AmFor vibration acceleration signal principal frequency component amplitude, AiFor the ith of 50Hz in vibration acceleration signal
Harmonics amplitude, N are signal 50Hz harmonics quantity within the scope of 8kHz.
Preferably, step 2.2.2) in frequency spectrum complexity H calculating function expression such as formula (1) shown in;
In formula (2), RiFor 50Hz ith harmonics vibration amplitude proportions.
Preferably, step 2.2.3) in comprehensive wavelet pack energy feature E calculating function expression such as formula (3) and formula (4)
It is shown;
E=(E1+E2+E3)/3(4)
In formula (3), EjFor the wavelet-packet energy of j-th of measuring point, EjiFor i-th of wavelet packet sub-belt energy of j-th of measuring point,
N is the WAVELET PACKET DECOMPOSITION number of plies.
Preferably, when step 2.3) carries out principal component analysis for winding deformation characteristic parameter, principal component analysis output
Independent characteristic parameter dimensions are 2 dimensions, and it is more than 85% that principal component condition, which is independent characteristic contribution rate, finally obtain winding deformation spy
Levy the corresponding independent characteristic parameter of parameter.
Preferably, the machine learning model in step 3) is least square method supporting vector machine disaggregated model.
Preferably, the training step of the least square method supporting vector machine disaggregated model includes:
S1 it) is directed to the corresponding sample transformer of transformer to be detected, vibration when winding deformation not occurring is acquired respectively and adds
Speed signal x1iAnd vibration acceleration signal x when generation winding deformation2i;
S2) to vibration acceleration signal x when not occurring winding deformation of sample transformer1iAnd winding deformation occurs
When vibration acceleration signal x2iExtract independent characteristic parameter;
S3 whether winding deformation state) is according to sample transformer when acquisition vibration acceleration signal, to sample transformation
The independent characteristic parameter of device is classified, and independent characteristic clock rate when winding deformation not occurring is " 1 ", and winding deformation occurs
When independent characteristic parameter characteristic parameter classification be " -1 ";
S4 sorted independent characteristic parameter and its characteristic parameter classification) are formed into training set, by training set using minimum
Two, which multiply support vector machine method, is trained, and obtains including the mapping pass between independent characteristic parameter and winding deformation state
The least square method supporting vector machine disaggregated model of system.
The present invention also provides a kind of systems judging deformation of transformer winding, including computer equipment, the computer to set
The step of standby method for being programmed to perform the aforementioned judgement deformation of transformer winding of the present invention.
The present invention judges that the method tool of deformation of transformer winding has the advantage that:
1, the present invention can detect the winding deformation state of transformer, it can be achieved that electrification under the conditions of transformer is not stopped transport
Detection;
2, for the present invention with charging equipment there is no electrical contact, safety is higher;
3, detection process of the present invention is shorter, detection efficiency higher.
The present invention judges that the system of deformation of transformer winding judges that the method for deformation of transformer winding is corresponding for the present invention
Equally also there is system the present invention to judge the aforementioned advantages of the method for deformation of transformer winding, and details are not described herein.
Description of the drawings
Fig. 1 is the implementation process schematic diagram of present invention method.
Fig. 2 is the vibration acceleration signal frequency spectrum of transformer when winding deformation does not occur in the embodiment of the present invention.
Fig. 3 is the vibration acceleration signal frequency spectrum of transformer when winding deformation occurring in the embodiment of the present invention.
Specific implementation mode
As shown in Figure 1, the present embodiment judges that the implementation steps of the method for deformation of transformer winding include:
1) vibration acceleration signal of transformer to be detected is obtained;
2) independent characteristic parameter is extracted according to the vibration acceleration signal of transformer to be detected;
3) independent characteristic parameter is inputted into trained machine learning model, obtains the current winding of transformer to be detected and becomes
Shape state, machine learning model are trained to include the mapping relations between independent characteristic parameter and winding deformation state.
The present embodiment judges that the method for deformation of transformer winding can effectively detect to become under the conditions of transformer is not stopped transport
Deformation of transformer winding state, has the advantages that not contact that charging equipment, that live detection, convenient test can be achieved is efficient.
In the present embodiment, the detailed step of step 2) includes:
2.1) vibration acceleration signal of transformer to be detected is pre-processed (noise reduction process);
2.2) spectrum analysis and wavelet packet analysis are carried out to pretreated vibration acceleration signal, therefrom associated extraction around
Group deformation behaviour parameter;
2.3) it is directed to winding deformation characteristic parameter and carries out principal component analysis, obtain independent characteristic parameter.
In the present embodiment, the detailed step of step 2.2) includes:
2.2.1 Fourier transformation) is carried out to the vibration acceleration signal that the multiple measuring points of transformer detect, intercepts 8kHz
Vibration acceleration signal frequency spectrum in range, and the progress arithmetic average processing of the vibration acceleration frequency spectrum of multiple measuring points is formed comprehensive
Sum of fundamental frequencies is composed, and the dominant frequency proportion R of integral spectrum is calculatedm;In the present embodiment, the multiple measuring points of transformer specifically refer to 3 measuring points, measuring point
Position is located at the large-area flat-plate position of 1/4 height of high voltage side of transformer fuel tank facade, 3 measuring points respectively with Three-Phase Transformer around
Group position is corresponding, and requires every time test point position identical, and sample frequency is not less than 16kHz;Due to different location transformation
There is some difference for device vibration acceleration signal, and identical point position advantageously ensures that test result has comparability.Due to
Vibration acceleration signal is normally within the scope of 8kHz when deformation of transformer winding, and therefore, sample frequency should be not less than 16kHz.
2.2.2 the 50Hz and its spectrum complex degree H of harmonic frequency in vibration acceleration signal 8kHz spectral ranges) is calculated;
2.2.3 wavelet packet analysis) is carried out respectively to the vibration acceleration signal of the multiple measuring points of transformer, calculates separately small echo
Packet energy simultaneously carries out arithmetic average processing, obtains comprehensive wavelet pack energy feature E;
2.2.4) by dominant frequency proportion Rm, spectrum complex degree H collectively form winding change with comprehensive wavelet pack energy feature E three
Shape characteristic parameter.
In the present embodiment, step 2.2.1) in integral spectrum dominant frequency proportion RmCalculating function expression such as formula (1) institute
Show;
In formula (1), AmFor vibration acceleration signal principal frequency component amplitude, AiFor the ith of 50Hz in vibration acceleration signal
Harmonics amplitude, N are signal 50Hz harmonics quantity within the scope of 8kHz.
In the present embodiment, step 2.2.2) in frequency spectrum complexity H calculating function expression such as formula (1) shown in;
In formula (2), RiFor 50Hz ith harmonics vibration amplitude proportions.
In the present embodiment, step 2.2.3) in comprehensive wavelet pack energy feature E calculating function expression such as formula (3) and formula
(4) shown in;
E=(E1+E2+E3)/3 (4)
In formula (3), EjFor the wavelet-packet energy of j-th of measuring point, EjiFor i-th of wavelet packet sub-belt energy of j-th of measuring point,
N is the WAVELET PACKET DECOMPOSITION number of plies.Comprehensive wavelet pack energy feature reflects different frequency range transformer vibration acceleration signal energy
Distribution situation.
In the present embodiment, when step 2.3) carries out principal component analysis for winding deformation characteristic parameter, principal component analysis is defeated
The independent characteristic parameter dimensions gone out are 2 dimensions, and it is more than 85% that principal component condition, which is independent characteristic contribution rate, finally obtain winding change
The corresponding independent characteristic parameter of shape characteristic parameter.Due to dominant frequency proportion Rm, spectrum complex degree H and comprehensive wavelet pack energy feature
There may be interrelated between tri- characteristic parameters of E, therefore, the present embodiment step 3) using principal component analytical method to its into
Row decorrelative transformation, to further decrease feature quantity, final deformation of transformer winding characteristic parameter is only two, respectively
For " characteristic parameter 1 " and " characteristic parameter 2 ".It should be noted that it is principal component analysis side to carry out dimensionality reduction using principal component analysis
The basic application of method, therefore this will not be detailed here for the specific steps of progress principal component analysis.
In the present embodiment, the machine learning model in step 3) is least square method supporting vector machine disaggregated model, in addition
Other machine learning models can be used as needed.
In the present embodiment, the training step of least square method supporting vector machine disaggregated model includes:
S1 it) is directed to the corresponding sample transformer of transformer to be detected, vibration when winding deformation not occurring is acquired respectively and adds
Speed signal x1iAnd vibration acceleration signal x when generation winding deformation2i;
S2) to vibration acceleration signal x when not occurring winding deformation of sample transformer1iAnd winding deformation occurs
When vibration acceleration signal x2iExtract independent characteristic parameter;
S3 whether winding deformation state) is according to sample transformer when acquisition vibration acceleration signal, to sample transformation
The independent characteristic parameter of device is classified, and independent characteristic clock rate when winding deformation not occurring is " 1 ", and winding deformation occurs
When independent characteristic parameter characteristic parameter classification be " -1 ";
S4 sorted independent characteristic parameter and its characteristic parameter classification) are formed into training set, by training set using minimum
Two, which multiply support vector machine method, is trained, and obtains including the mapping pass between independent characteristic parameter and winding deformation state
The least square method supporting vector machine disaggregated model of system.
As shown in Fig. 2, when winding deformation not occurring, transformer vibration acceleration signal frequency spectrum is concentrated mainly on 2kHz ranges
Interior, transformer vibration acceleration signal energy is concentrated mainly on 100Hz, 200Hz, 300Hz, 400Hz, 500Hz and 600Hz etc.
On 50Hz even number overtones bands, dominant frequency 600Hz, the frequency component in frequency spectrum is relatively fewer, and spectrum complex degree is relatively low.Such as Fig. 3 institutes
Show, after winding deformation occurs, significant changes have occurred compared with normal condition in vibration acceleration signal spectrum distribution, and dominant frequency position occurs
Variation, dominant frequency 400Hz, principal frequency component proportion reduce, 50Hz odd multiple number of frequency component amplitude and spectrum distribution model in frequency spectrum
Cross existing increase situation.It is found by comparing, before and after winding deformation occurs, dominant frequency proportion Rm, spectrum complex degree H and synthesis it is small
Significant change has occurred in wave packet energy feature E, and the winding deformation of transformer can be reflected by being constituted relevant feature parameters with this
Problem.
The present embodiment also provides a kind of system judging deformation of transformer winding, including computer equipment, computer equipment
The step of being programmed to perform the method for the aforementioned judgement deformation of transformer winding of the present invention.
The above is only a preferred embodiment of the present invention, protection scope of the present invention is not limited merely to above-mentioned implementation
Example, all technical solutions belonged under thinking of the present invention all belong to the scope of protection of the present invention.It should be pointed out that for the art
Those of ordinary skill for, several improvements and modifications without departing from the principles of the present invention, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of method judging deformation of transformer winding, it is characterised in that implementation steps include:
1) vibration acceleration signal of transformer to be detected is obtained;
2) independent characteristic parameter is extracted according to the vibration acceleration signal of transformer to be detected;
3) independent characteristic parameter is inputted into trained machine learning model, obtains the current winding deformation shape of transformer to be detected
State, the machine learning model are trained to include the mapping relations between independent characteristic parameter and winding deformation state.
2. the method according to claim 1 for judging deformation of transformer winding, which is characterized in that the detailed step of step 2)
Including:
2.1) vibration acceleration signal of transformer to be detected is pre-processed;
2.2) spectrum analysis and wavelet packet analysis are carried out to pretreated vibration acceleration signal, therefrom associated extraction winding becomes
Shape characteristic parameter;
2.3) it is directed to winding deformation characteristic parameter and carries out principal component analysis, obtain independent characteristic parameter.
3. the method according to claim 2 for judging deformation of transformer winding, which is characterized in that the detailed step of step 2.2)
Suddenly include:
2.2.1 Fourier transformation) is carried out to the vibration acceleration signal that the multiple measuring points of transformer detect, intercepts 8kHz ranges
Interior vibration acceleration signal frequency spectrum, and arithmetic average processing is carried out to the vibration acceleration frequency spectrum of multiple measuring points and forms comprehensive frequency
Spectrum, calculates the dominant frequency proportion R of integral spectrumm;
2.2.2 the 50Hz and its spectrum complex degree H of harmonic frequency in vibration acceleration signal 8kHz spectral ranges) is calculated;
2.2.3 wavelet packet analysis) is carried out respectively to the vibration acceleration signal of the multiple measuring points of transformer, calculates separately wavelet packet energy
Arithmetic average processing is measured and carried out, comprehensive wavelet pack energy feature E is obtained;
2.2.4) by dominant frequency proportion Rm, spectrum complex degree H collectively form winding deformation spy with comprehensive wavelet pack energy feature E three
Levy parameter.
4. the method according to claim 3 for judging deformation of transformer winding, which is characterized in that step 2.2.1) in it is comprehensive
The dominant frequency proportion R of frequency spectrummCalculating function expression such as formula (1) shown in;
In formula (1), AmFor vibration acceleration signal principal frequency component amplitude, AiFor the ith harmonics of 50Hz in vibration acceleration signal
Amplitude, N are signal 50Hz harmonics quantity within the scope of 8kHz.
5. it is according to claim 3 judge deformation of transformer winding method, which is characterized in that step 2.2.2) in frequency spectrum
Shown in the calculating function expression such as formula (1) of complexity H;
In formula (2), RiFor 50Hz ith harmonics vibration amplitude proportions.
6. the method according to claim 3 for judging deformation of transformer winding, which is characterized in that step 2.2.3) in it is comprehensive
Shown in the calculating function expression such as formula (3) and formula (4) of wavelet pack energy feature E;
E=(E1+E2+E3)/3 (4)
In formula (3), EjFor the wavelet-packet energy of j-th of measuring point, EjiFor i-th of wavelet packet sub-belt energy of j-th of measuring point, n is
The WAVELET PACKET DECOMPOSITION number of plies.
7. the method according to claim 2 for judging deformation of transformer winding, which is characterized in that step 2.3) is directed to winding
When deformation behaviour parameter carries out principal component analysis, the independent characteristic parameter dimensions of principal component analysis output are tieed up for 2, and principal component item
Part is that independent characteristic contribution rate is more than 85%, finally obtains the corresponding independent characteristic parameter of winding deformation characteristic parameter.
8. the method according to claim 1 for judging deformation of transformer winding, which is characterized in that the engineering in step 3)
Habit model is least square method supporting vector machine disaggregated model.
9. the method according to claim 8 for judging deformation of transformer winding, which is characterized in that the least square is supported
The training step of vector machine disaggregated model includes:
S1 it) is directed to the corresponding sample transformer of transformer to be detected, acquires vibration acceleration when winding deformation not occurring respectively
Signal x1iAnd vibration acceleration signal x when generation winding deformation2i;
S2) to vibration acceleration signal x when not occurring winding deformation of sample transformer1iAnd when generation winding deformation
Vibration acceleration signal x2iExtract independent characteristic parameter;
S3 whether winding deformation state) is according to sample transformer when acquisition vibration acceleration signal, to sample transformer
Independent characteristic parameter is classified, and independent characteristic clock rate when winding deformation not occurring is " 1 ", is occurred only when winding deformation
The characteristic parameter classification of vertical characteristic parameter is " -1 ";
S4 sorted independent characteristic parameter and its characteristic parameter classification) are formed into training set, training set is used into least square
Support vector machine method is trained, and obtains including the mapping relations between independent characteristic parameter and winding deformation state
Least square method supporting vector machine disaggregated model.
10. a kind of system judging deformation of transformer winding, including computer equipment, which is characterized in that the computer equipment
The step of being programmed to perform the method for any one of claim 1~9 judgement deformation of transformer winding.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810239981.3A CN108693437B (en) | 2018-03-22 | 2018-03-22 | Method and system for judging deformation of transformer winding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810239981.3A CN108693437B (en) | 2018-03-22 | 2018-03-22 | Method and system for judging deformation of transformer winding |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108693437A true CN108693437A (en) | 2018-10-23 |
CN108693437B CN108693437B (en) | 2020-12-25 |
Family
ID=63844491
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810239981.3A Active CN108693437B (en) | 2018-03-22 | 2018-03-22 | Method and system for judging deformation of transformer winding |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108693437B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110006527A (en) * | 2019-04-12 | 2019-07-12 | 国网湖南省电力有限公司 | High-voltage switch gear cabinet and its unreasonable design extraordinary noise diagnostic method, system and medium |
CN111537919A (en) * | 2020-05-14 | 2020-08-14 | 莫毓昌 | Transformer fault diagnosis method based on voiceprint characteristics |
CN112665707A (en) * | 2020-12-15 | 2021-04-16 | 国网天津市电力公司电力科学研究院 | Cumulative effect after short circuit impact of transformer and diagnosis method |
CN113701684A (en) * | 2021-08-05 | 2021-11-26 | 西安交通大学 | Transformer winding state detection method, device, equipment and storage medium |
CN114485540A (en) * | 2022-01-20 | 2022-05-13 | 西安交通大学 | Method and system for rapidly acquiring deformation degree and position of transformer winding |
US11474163B2 (en) * | 2019-08-12 | 2022-10-18 | Wuhan University | Power transformer winding fault positioning method based on deep convolutional neural network integrated with visual identification |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012039768A (en) * | 2010-08-06 | 2012-02-23 | Toshiba Corp | Device failure evaluation system |
CN103267907A (en) * | 2013-04-19 | 2013-08-28 | 上海交通大学 | Method for identifying modal parameters of transformer coil |
CN106443259A (en) * | 2016-09-29 | 2017-02-22 | 国网山东省电力公司电力科学研究院 | Transformer fault diagnosis new method based on Euclidean clustering and SPO-SVM |
CN106569069A (en) * | 2016-11-04 | 2017-04-19 | 广州供电局有限公司 | Power transformer fault diagnosis method |
KR20170053304A (en) * | 2015-11-06 | 2017-05-16 | 주식회사 파워토스 | Sound spectrum sensor for abnormal state detection of transformer |
-
2018
- 2018-03-22 CN CN201810239981.3A patent/CN108693437B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012039768A (en) * | 2010-08-06 | 2012-02-23 | Toshiba Corp | Device failure evaluation system |
CN103267907A (en) * | 2013-04-19 | 2013-08-28 | 上海交通大学 | Method for identifying modal parameters of transformer coil |
KR20170053304A (en) * | 2015-11-06 | 2017-05-16 | 주식회사 파워토스 | Sound spectrum sensor for abnormal state detection of transformer |
CN106443259A (en) * | 2016-09-29 | 2017-02-22 | 国网山东省电力公司电力科学研究院 | Transformer fault diagnosis new method based on Euclidean clustering and SPO-SVM |
CN106569069A (en) * | 2016-11-04 | 2017-04-19 | 广州供电局有限公司 | Power transformer fault diagnosis method |
Non-Patent Citations (3)
Title |
---|
吴晓文等: "城市轨道交通引起的变压器直流偏磁噪声与振动特性", 《电测与仪表》 * |
钱国超等: "振动频谱特征值在诊断变压器故障中的应用", 《云南电力技术》 * |
钱国超等: "电力变压器振动频谱特征值在绕组变形检测中的应用", 《云南电力技术》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110006527A (en) * | 2019-04-12 | 2019-07-12 | 国网湖南省电力有限公司 | High-voltage switch gear cabinet and its unreasonable design extraordinary noise diagnostic method, system and medium |
US11474163B2 (en) * | 2019-08-12 | 2022-10-18 | Wuhan University | Power transformer winding fault positioning method based on deep convolutional neural network integrated with visual identification |
CN111537919A (en) * | 2020-05-14 | 2020-08-14 | 莫毓昌 | Transformer fault diagnosis method based on voiceprint characteristics |
CN112665707A (en) * | 2020-12-15 | 2021-04-16 | 国网天津市电力公司电力科学研究院 | Cumulative effect after short circuit impact of transformer and diagnosis method |
CN112665707B (en) * | 2020-12-15 | 2023-03-03 | 国网天津市电力公司电力科学研究院 | Cumulative effect after short circuit impact of transformer and diagnosis method |
CN113701684A (en) * | 2021-08-05 | 2021-11-26 | 西安交通大学 | Transformer winding state detection method, device, equipment and storage medium |
CN114485540A (en) * | 2022-01-20 | 2022-05-13 | 西安交通大学 | Method and system for rapidly acquiring deformation degree and position of transformer winding |
Also Published As
Publication number | Publication date |
---|---|
CN108693437B (en) | 2020-12-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108693437A (en) | A kind of method and system judging deformation of transformer winding | |
Stefanidou-Voziki et al. | A review of fault location and classification methods in distribution grids | |
CN102253283B (en) | A kind of distributed micro-grid grid-connected island detection method based on Wavelet Packet Energy Spectrum | |
CN109633368A (en) | The method of duration power quality disturbances containing distributed power distribution network based on VMD and DFA | |
CN110174585B (en) | Method for identifying open circuit fault of high-voltage capacitor of double-tuned alternating current filter | |
CN110118900A (en) | A kind of remained capacity and power frequency series arc faults detection method | |
Fatama et al. | A multi feature based islanding classification technique for distributed generation systems | |
CN108169583A (en) | Auto-transformer D.C. magnetic biasing method of discrimination and system of the neutral point through capacity earth | |
CN103018537A (en) | Disturbance classification and recognition method for quality of transient electric energy based on CWD Choi-Williams Distribution spectral kurtosis | |
CN112418638A (en) | Early warning system and early warning method for operation and maintenance risks of DC power supply system for station | |
CN106980051B (en) | A kind of intermittence tandem type fault electric arc recognition methods | |
Prasad et al. | Optimal threshold-based high impedance arc fault detection approach for renewable penetrated distribution system | |
CN108519526A (en) | A kind of method and system judging transformer harmonic load operating status | |
CN108508318A (en) | A kind of method and system judging transformer unbalanced load operating status | |
CN109387713A (en) | A kind of mixed method of distributed grid-connected isolated island detection | |
Singh et al. | Supervisory framework for event detection and classification using wavelet transform | |
CN105629144B (en) | High-tension switch gear partial discharge diagnostic method and system based on fingerprint base | |
Xiong et al. | Development of a Fault Detection and Localization Algorithm for Photovoltaic Systems | |
Thomas et al. | Machine learning based detection and classification of power system events | |
Behzadi et al. | Identification of combined power quality disturbances in the presence of distributed generations using variational mode decomposition and K-nearest neighbors classifier | |
Gao et al. | Internal overvoltage identification of distribution network via time-frequency atomic decomposition | |
Qi et al. | Ungrounded fault detection in medium voltage distribution network based on machine learning | |
Chen et al. | Identification of typical partial discharge defects of distribution system equipment based on classification learner | |
Cai et al. | Reviews of research on mechanical fault diagnosis in GIS | |
CN206114827U (en) | Power cable insulating properties on -line monitoring device |
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 |