CN108196161A - A kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults - Google Patents
A kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults Download PDFInfo
- Publication number
- CN108196161A CN108196161A CN201810023214.9A CN201810023214A CN108196161A CN 108196161 A CN108196161 A CN 108196161A CN 201810023214 A CN201810023214 A CN 201810023214A CN 108196161 A CN108196161 A CN 108196161A
- Authority
- CN
- China
- Prior art keywords
- neural network
- asynchronization
- super
- loss
- synchronous generator
- 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
- 230000001360 synchronised effect Effects 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 53
- 239000013598 vector Substances 0.000 claims abstract description 30
- 230000007257 malfunction Effects 0.000 claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 claims abstract description 4
- 238000010276 construction Methods 0.000 claims abstract description 3
- 210000002569 neuron Anatomy 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000005284 excitation Effects 0.000 abstract description 21
- 238000003745 diagnosis Methods 0.000 abstract description 4
- 238000004804 winding Methods 0.000 description 13
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000002405 diagnostic procedure Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 101100257981 Arabidopsis thaliana S-ACP-DES3 gene Proteins 0.000 description 1
- 101150057677 DAD3 gene Proteins 0.000 description 1
- 102100034004 Gamma-adducin Human genes 0.000 description 1
- 101000799011 Homo sapiens Gamma-adducin Proteins 0.000 description 1
- 101001080624 Homo sapiens Proline/serine-rich coiled-coil protein 1 Proteins 0.000 description 1
- 101000652684 Homo sapiens Transcriptional adapter 3 Proteins 0.000 description 1
- 102100027427 Proline/serine-rich coiled-coil protein 1 Human genes 0.000 description 1
- 101100433696 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) AAD3 gene Proteins 0.000 description 1
- 102100030836 Transcriptional adapter 3 Human genes 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000036552 dowling-degos disease 3 Diseases 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 208000002153 familial abdominal 3 aortic aneurysm Diseases 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
Abstract
The present invention relates to asynchronization super-pressure synchronous generator technical field more particularly to a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults.Include the following steps:Step (1) acquires the rotor voltage signal of asynchronization super-pressure synchronous generator, stator voltage sig and stator current signal;Step (2) carries out wavelet packet analysis, obtains rotor voltage signal, the energy value feature vector of each sub-band of stator voltage sig and stator current signal;Step (3) builds BP neural network, is trained using Levenberg Marquardt algorithms and exports malfunction;The malfunction that unlike signal is analyzed is passed through logical operation, final output malfunction by step (4), construction logic arithmetic element.The present invention realizes the diagnosis to asynchronization super-pressure Synchronous Generator after Loss-of-Excitation failure, can quickly and accurately judge the type of loss of excitation failure, and effectively eliminates the interference of the stator terminal three phase short circuit fault when judging loss of excitation failure.
Description
Technical field
The present invention relates to asynchronization super-pressure synchronous generator technical fields more particularly to a kind of asynchronization super-pressure to synchronize
Loss of exicitation method for diagnosing faults.
Background technology
Asynchronization super-pressure synchronous generator is a kind of to combine the new of asynchronized synchronous generator and supervoltage generator
Generator has the advantages that asynchronized synchronous generator and supervoltage generator simultaneously, be it is a kind of can be with direct grid-connected
Novel high-pressure generator, asynchronization super-pressure synchronous generator have the following advantages compared with conventional electric generators:It is active power, idle
Power and rotating speed can be separately adjustable, it can be achieved that variable speed constant frequency generator is, it can be achieved that depth leading phase operation.
Part or all of loss of excitation is one of common failure of generator excitation circuit to generator suddenly, generator excitation winding
Short circuit or open circuit can lead to loss of excitation failure, and loss of excitation failure can lead to motor hot-spot, system element overcurrent or even meeting
Make electric system that collapse phenomenon, the safe and stable operation of serious threat Generator Set occur.If using effective loss of excitation
Fault diagnosis technology, electricity generation system safe and stable operation can be ensured by being accurately judged to loss of excitation failure, so, to asynchronization superelevation
The research of pressure Synchronous Generator after Loss-of-Excitation fault diagnosis is a kind of extremely necessary, asynchronization super-pressure Synchronous Generator after Loss-of-Excitation detection
System [CN206627603U] detects loss of excitation failure using the mode that main auxiliary criterion is combined, but can not judge to lead to loss of excitation
Fault type.At present, it is domestic not yet for the phase of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation fault type diagnostic method
Close research.
Invention content
In order to overcome the above-mentioned existing missing for asynchronization super-pressure Synchronous Generator after Loss-of-Excitation fault type diagnostic method,
The present invention provides a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults.
A kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults, includes the following steps:
Step (1) acquires the rotor voltage signal of asynchronization super-pressure synchronous generator, stator voltage sig and stator electricity
Flow signal;
Step (2) carries out wavelet packet analysis, obtains rotor voltage signal, stator voltage sig and stator current signal
The energy value feature vector of each sub-band;
Step (3) builds neural network W1, neural network W2 and neural network W3;The rotor that wavelet packet analysis is extracted
Input vector of the energy value feature vector of voltage signal as neural network W1 is trained and exports malfunction G1;It will
Input vector of the energy value feature vector of the stator voltage sig of wavelet packet analysis extraction as neural network W2, is trained
And export malfunction G2;Using the energy value feature vector of the stator current signal of wavelet packet analysis extraction as neural network W3
Input vector, be trained and export malfunction G3;
Step (4), construction logic arithmetic element, by malfunction G1, malfunction G2 and malfunction G3 as logic
The input of arithmetic element, logical unit output malfunction G.
The wavelet packet analysis is included to rotor voltage signal, and stator voltage sig and stator current signal carry out denoising,
It decomposes, reconstruct and extraction wavelet-packet energy value.
The wavelet packet analysis method uses db4 wavelet functions signal and carries out three layers of WAVELET PACKET DECOMPOSITION, obtains third
Each sub-band wavelet-packet energy value of layer.
By the wavelet-packet energy value composition energy value feature vector T={ E0, E1, E2, E3, E4, E5, E6, E7 }, use
In the input of neural network.
The neural network W1, neural network W2 and neural network W3 include input using 3 layers of BP neural network
Layer, hidden layer and output layer, the neuron node number of input layer is 8, and the neuron node number of output layer is 3, hidden layer nerve
First number of nodes meets:Wherein h be hidden layer neuron number of nodes, n be input layer number of nodes, m
For output layer neuron node number, a is regulating constant, between the value range of a is 1 to 10.
The neural network W1, neural network W2, neural network W3 are hidden using Levenberg-Marquardt algorithms
It is activation primitive that neuron containing layer, which selects S type tangent functions, and output layer neuron selects S types logarithmic function as activation primitive.
Beneficial effects of the present invention:
(1) using wavelet packet analysis sampled signal, analysis method of wavelet packet overcomes traditional based on Fourier transformation
The shortcomings that signal analysis method is difficult to carry out feature extraction to the small-signal in fault-signal and singular signal ingredient, further
State recognition is carried out using the learning training function of neural network, makes diagnostic result more accurate, reliable;
(2) rotor voltage signal, stator voltage sig and stator current signal are acquired respectively, and add in logic fortune
Unit is calculated, further improves the accuracy and reliability of diagnostic result;
It (3) can be to generator excitation winding short circuit loss of excitation failure, generator excitation winding open circuit loss of excitation failure and stator
End three kinds of malfunctions of three phase short circuit fault are diagnosed, and can be accurately judged to loss of excitation fault type, and effectively exclude
When the judging loss of excitation failure interference of stator terminal three phase short circuit fault;
(4) BP neural network of the invention is trained network using L-M algorithms, overcomes the BP algorithm convergence of standard
Speed is slow, the problem of being easily absorbed in local minimum.
Description of the drawings
Fig. 1 is failure diagnostic process figure of the present invention;
Fig. 2 is three layers of WAVELET PACKET DECOMPOSITION process schematic of the present invention;
Fig. 3 is the logic diagram of the logical unit of the present invention.
In figure:L1, L2, L3, L4, L5, L6- logical AND gate, L7- logic sum gates.
Specific embodiment
The exemplary embodiment of the present invention is described hereinafter in connection with attached drawing.It is understood that this place
The specific embodiment of description is used only for explaining the embodiment of the present invention rather than the restriction to the embodiment of the present invention.It further needs exist for
Illustrate, illustrate only part relevant with the embodiment of the present invention rather than entire infrastructure for ease of description, in attached drawing, and attached
Scheme certain components to have omission, zoom in or out, do not represent the size of actual product.
As shown in Figure 1, a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults, includes the following steps:
Step S1 acquires the rotor voltage signal of asynchronization super-pressure synchronous generator, stator voltage sig and stator electricity
Flow signal.Collected signal includes:Signal during generator normal operation, signal during generator excitation winding short circuit,
Signal during generator excitation winding open circuit, the signal during three-phase shortcircuit of generator unit stator end.
Step S2 carries out wavelet packet analysis to collected signal, and the wavelet packet analysis method uses db4 small echo letters
Number signal simultaneously carries out three layers of WAVELET PACKET DECOMPOSITION, i.e. vanishing moment N=4 obtains the signal in 8 different frequency bands, further, such as schemes
2 be three layers of WAVELET PACKET DECOMPOSITION process schematic, wherein, A represents low frequency, and D represents high frequency, and the serial number at end represents WAVELET PACKET DECOMPOSITION
The number of plies.Its exploded relationship is:S=AAA3+DAA3+ADA3+DDA3+AAD3+DAD3+ADD3+DDD3.S is then total reconstruct
Signal as can be seen that wavelet packet decomposes more careful to the high frequency section of signal from exploded relationship, can make full use of extraction
Signal;The decomposition coefficient of each sub-band that the WAVELET PACKET DECOMPOSITION obtains successively is reconstructed, is extracted in each frequency range
Simultaneously each sub-band wavelet-packet energy value is obtained in signal, and form energy value feature vector T=E0, E1, E2, E3, E4, E5, E6,
E7 }, in using matlab Software simulation calculations, since energy value is often very big, it generally may be used and it be normalized
Processing.
Step S3 builds neural network W1, neural network W2 and neural network W3;The neural network W1, nerve net
Network W2 and neural network W3 uses 3 layers of BP neural network, comprising input layer, hidden layer and output layer, and the neuron of input layer
Number of nodes is 8, i.e., the energy value feature vector obtained by wavelet packet analysis, and the neuron node number of output layer is 3, is failure
State, wherein normal operating condition are (1,1,1), and loss of excitation failure caused by Exciting Windings for Transverse Differential Protection short circuit is (0,0,1), and Exciting Windings for Transverse Differential Protection is broken
Loss of excitation failure caused by road is (0,1,0), and stator terminal three-phase shortcircuit is (1,0,0);Hidden layer neuron number of nodes meets formula:Wherein h is hidden layer neuron number of nodes, and n is input layer number of nodes, and n values are that 8, m is defeated
Go out a layer neuron node number, m values are regulating constant for 3, a, between the value range of a is 1 to 10.Therefore nerve net of the present invention
For the hidden layer neuron number of nodes value range of network between 5 to 14, the present embodiment takes 14.
Using the energy value feature vector of rotor voltage as the input vector of neural network W1, corresponding malfunction
As desired output, it is trained;It is right therewith using stator voltage energy value feature vector as the input vector of neural network W2
The malfunction answered is trained as desired output;Using stator current energy value feature vector as the defeated of neural network W3
Incoming vector, corresponding malfunction are trained as desired output;Specifically, by it is collected be Exciting Windings for Transverse Differential Protection
Rotor voltage signal when short-circuit carries out wavelet packet analysis, by the rotor voltage energy value feature vector after wavelet packet analysis
As neural network W1 input vectors, by the malfunction (0,0,1) of Exciting Windings for Transverse Differential Protection short circuit as desired output, to neural network
W1 is trained.By it is collected be Exciting Windings for Transverse Differential Protection open circuit when rotor voltage signal carry out wavelet packet analysis, will be through wavelet packet
Rotor voltage energy value feature vector after analysis is as neural network W1 input vectors, by the failure shape of Exciting Windings for Transverse Differential Protection short circuit
State (0,1,0) is trained neural network W1 as desired output.For the training method of other failures of neural network W1
It is consistent with the above method, the training of neural network W2 and neural network W3 are similarly understood.After training, neural network W1
The energy value feature vector of rotor voltage can be analyzed, obtain malfunction G1.Similarly, neural network W2 exports failure
State G2, neural network W3 output malfunction G3.
The neural network W1, neural network W2 and neural network W3 are using Levenberg-Marquardt algorithms, letter
Claim L-M algorithms, L-M algorithms are actually the combination of gradient descent method and Newton method, can be improved learning efficiency, hidden layer nerve
Member selects S types tangent function as activation primitive, and output layer neuron selects S types logarithmic function as activation primitive.Maximum training time
Number is 1000, target error 0.001, learning rate 0.1.
Step S4, by fault status signal G1, fault status signal G2 and fault status signal G3 as logical operation list
The input of member, arithmetic element output fault status signal G.The structure of logical unit as shown in figure 3, logical unit by
With door L1, L2, L3, L4, L5, L6 and/or door L7 compositions, further, signal G1 and signal G2 by with door L1, if signal G1
Identical with signal G2, then with door L1 outputs 1, if signal G1 is different from signal G2, the output that L1 exports 0, L1 is led to signal G1
It crosses with door L4, which means that when signal L1 is 0, the output of L4 is also 0, and when L1 is 1, the output of L4 is signal G1, with
The output of door L4, L5 and L6 together as or door L7 input, three independent analysis results, by logical unit, such as
Fruit is wherein consistent there are two malfunction, then malfunction G exports the malfunction, if three fault-signals are different,
Then malfunction output is 0, this illustrates that algorithm is undesirable or the failure is not in the range of fault diagnosis, can be by three
Fault-signal all exports, and technical staff is supplied to be analyzed.
The data of four groups of different conditions is selected to test system, first group be generator normal operation when data,
Second group be stator terminal three-phase shortcircuit when data, third group be Exciting Windings for Transverse Differential Protection short circuit when data, the 4th group be Exciting Windings for Transverse Differential Protection
Data when short-circuit.
The malfunction being obtained is input to logical unit, finally obtains malfunction, as shown in table 1:
Table 1
Finally illustrate, although describing the present invention according to the embodiment of limited quantity, benefit from above description,
It will be understood by those skilled in the art that in the scope of the present invention thus described, it can be envisaged that other embodiments.
Additionally, it should be noted that the language used in this specification primarily to readable and introduction purpose and select rather than
It is selected to explain or limit subject of the present invention.Therefore, without departing from the scope of the appended claims and objective
In the case of, for those skilled in the art, many modifications and changes are obvious.For this hair
Bright range, the disclosure done to the present invention is illustrative and not restrictive, and the scope of the present invention is by appended claims
Book limits.
Claims (6)
1. a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults, which is characterized in that include the following steps:
Step (1) acquires the rotor voltage signal of asynchronization super-pressure synchronous generator, stator voltage sig and stator current letter
Number;
Step (2) carries out wavelet packet analysis, obtains each son of rotor voltage signal, stator voltage sig and stator current signal
The energy value feature vector of frequency band;
Step (3) builds neural network W1, neural network W2 and neural network W3;The rotor voltage that wavelet packet analysis is extracted
Input vector of the energy value feature vector of signal as neural network W1 is trained and exports malfunction G1;By small echo
Input vector of the energy value feature vector of the stator voltage sig of packet analysis extraction as neural network W2, is trained and defeated
The state that is out of order G2;Using the energy value feature vector of the stator current signal of wavelet packet analysis extraction as the defeated of neural network W3
Incoming vector is trained and exports malfunction G3;
Step (4), construction logic arithmetic element, by malfunction G1, malfunction G2 and malfunction G3 as logical operation
The input of unit, logical unit output malfunction G.
2. a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults according to claim 1, feature exist
In, the wavelet packet analysis is included to rotor voltage signal, and stator voltage sig and stator current signal carry out denoising, decompose,
Reconstruct and extraction wavelet-packet energy value.
3. a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults according to claim 2, feature exist
In,
The wavelet packet analysis method uses db4 wavelet functions signal and carries out three layers of WAVELET PACKET DECOMPOSITION, and it is each to obtain third layer
The wavelet-packet energy value of sub-band.
4. a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults according to Claims 2 or 3, feature
It is, the wavelet-packet energy value composition energy value feature vector T={ E0, E1, E2, E3, E4, E5, E6, E7 } is used for
The input of neural network.
5. a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults according to claim 1, feature exist
In,
The neural network W1, neural network W2 and neural network W3 are hidden comprising input layer using 3 layers of BP neural network
Containing layer and output layer, the neuron node number of input layer is 8, and the neuron node number of output layer is 3, hidden layer neuron node
Number meets:Wherein h is hidden layer neuron number of nodes, and n is input layer number of nodes, and m is output
Layer neuron node number, a is regulating constant, between the value range of a is 1 to 10.
6. a kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults according to claim 5, feature exist
In the neural network W1, neural network W2 and neural network W3 are using Levenberg-Marquardt algorithms, hidden layer
Neuron selects S types tangent function as activation primitive, and output layer neuron selects S types logarithmic function as activation primitive.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810023214.9A CN108196161A (en) | 2018-01-10 | 2018-01-10 | A kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810023214.9A CN108196161A (en) | 2018-01-10 | 2018-01-10 | A kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108196161A true CN108196161A (en) | 2018-06-22 |
Family
ID=62588634
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810023214.9A Pending CN108196161A (en) | 2018-01-10 | 2018-01-10 | A kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108196161A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110542851A (en) * | 2019-08-29 | 2019-12-06 | 广州供电局有限公司 | Fault diagnosis method and device for circuit breaker operating mechanism, computer and storage medium |
CN112270273A (en) * | 2020-10-30 | 2021-01-26 | 湘潭大学 | Wind driven generator fault part identification method based on GCN and WPT-MD |
CN113064027A (en) * | 2021-03-03 | 2021-07-02 | 南方电网调峰调频发电有限公司 | Insulation testing method before unit starting and electronic equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101697079A (en) * | 2009-09-27 | 2010-04-21 | 华中科技大学 | Blind system fault detection and isolation method for real-time signal processing of spacecraft |
CN102636742A (en) * | 2012-05-15 | 2012-08-15 | 长沙河野电气科技有限公司 | Large-scale analogue circuit fault diagnosis method based on wavelet neural network |
CN103364683A (en) * | 2013-07-01 | 2013-10-23 | 东南大学 | Method for detecting open-circuit fault of inverter circuit |
CN103728514A (en) * | 2013-12-30 | 2014-04-16 | 北京京诚瑞达电气工程技术有限公司 | Fault diagnosis method for low-voltage frequency converter |
CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
CN104318485A (en) * | 2014-09-30 | 2015-01-28 | 上海电力学院 | Power transmission line fault identification method based on nerve network and fuzzy logic |
CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
CN105158647A (en) * | 2015-10-10 | 2015-12-16 | 国家电网公司 | Single station end fault diagnosis and auxiliary decisionmaking method based on power supply monitoring system |
CN105929816A (en) * | 2016-05-30 | 2016-09-07 | 北京天鸿同信科技有限公司 | Boolean algorithm-based industrial control system fault diagnosis method |
-
2018
- 2018-01-10 CN CN201810023214.9A patent/CN108196161A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101697079A (en) * | 2009-09-27 | 2010-04-21 | 华中科技大学 | Blind system fault detection and isolation method for real-time signal processing of spacecraft |
CN102636742A (en) * | 2012-05-15 | 2012-08-15 | 长沙河野电气科技有限公司 | Large-scale analogue circuit fault diagnosis method based on wavelet neural network |
CN103364683A (en) * | 2013-07-01 | 2013-10-23 | 东南大学 | Method for detecting open-circuit fault of inverter circuit |
CN103728514A (en) * | 2013-12-30 | 2014-04-16 | 北京京诚瑞达电气工程技术有限公司 | Fault diagnosis method for low-voltage frequency converter |
CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
CN104318485A (en) * | 2014-09-30 | 2015-01-28 | 上海电力学院 | Power transmission line fault identification method based on nerve network and fuzzy logic |
CN104502795A (en) * | 2014-11-26 | 2015-04-08 | 国家电网公司 | Intelligent fault diagnosis method suitable for microgrid |
CN105158647A (en) * | 2015-10-10 | 2015-12-16 | 国家电网公司 | Single station end fault diagnosis and auxiliary decisionmaking method based on power supply monitoring system |
CN105929816A (en) * | 2016-05-30 | 2016-09-07 | 北京天鸿同信科技有限公司 | Boolean algorithm-based industrial control system fault diagnosis method |
Non-Patent Citations (1)
Title |
---|
忻尚芝: "《电工与电子技术》", 北京:中国计量出版社 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110542851A (en) * | 2019-08-29 | 2019-12-06 | 广州供电局有限公司 | Fault diagnosis method and device for circuit breaker operating mechanism, computer and storage medium |
CN112270273A (en) * | 2020-10-30 | 2021-01-26 | 湘潭大学 | Wind driven generator fault part identification method based on GCN and WPT-MD |
CN113064027A (en) * | 2021-03-03 | 2021-07-02 | 南方电网调峰调频发电有限公司 | Insulation testing method before unit starting and electronic equipment |
CN113064027B (en) * | 2021-03-03 | 2022-04-29 | 南方电网调峰调频发电有限公司 | Insulation testing method before unit starting and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Saleh et al. | Implementing and testing $ d $–$ q $ WPT-based digital protection for microgrid systems | |
de Jesus Rangel-Magdaleno et al. | FPGA-based broken bars detection on induction motors under different load using motor current signature analysis and mathematical morphology | |
CN108196161A (en) | A kind of asynchronization super-pressure Synchronous Generator after Loss-of-Excitation method for diagnosing faults | |
CN110146812A (en) | A kind of Method of Motor Fault Diagnosis based on the study of characteristic node increment type width | |
CN103294849B (en) | Based on the Fault Diagnosis of AC Electric Machine model construction method of RBF neural | |
CN106324502A (en) | Asynchronous motor fault analysis method based on wavelet | |
Liu et al. | Fault diagnosis of shipboard medium-voltage DC power system based on machine learning | |
Rangel-Magdaleno et al. | Broken bars detection on induction motor using MCSA and mathematical morphology: An experimental study | |
Cherif et al. | Stator inter turns fault detection using discrete wavelet transform | |
Cui et al. | Generator rotating rectifier fault detection method based on stacked auto-encoder | |
CN113030789A (en) | Series arc fault diagnosis and line selection method based on convolutional neural network | |
CN111123104A (en) | Permanent magnet motor winding fault diagnosis method without prior knowledge | |
Bessam et al. | A novel method for induction motors stator inter-turn short circuit fault diagnosis based on wavelet energy and neural network | |
Ozgonenel et al. | A wavelet power based algorithm for synchronous generator protection | |
Ngaopitakkul et al. | Application of probabilistic neural network with transmission and distribution protection schemes for classification of fault types on radial, loop, and underground structures | |
Saddam et al. | Squirrel cage induction motor under stator and rotor bars faults modeling and diagnosis | |
Kumar et al. | Stator inter-turn fault diagnosis and fault location in synchronous generator using dual extended Kalman filter and linear regression analysis | |
Ibrahim et al. | Broken bar fault detection based on the discrete wavelet transform and artificial neural network | |
Nazemi et al. | A secure and sensitive wavelet transform based technique for stator fault detection in the cases of line‐connected and inverter‐fed induction machines | |
Halder et al. | Stator inter-turn fault diagnosis in permanent magnet synchronous motor | |
Khezzar et al. | Accurate modelling of cage induction machine with analytical evaluation of inductances | |
Nadarajan et al. | Feasibility analysis of auxiliary winding for condition monitoring of wound field brushless synchronous generators | |
Ilhem et al. | Automatic fault diagnosis of fault tolerant power converter for switched reluctance motor based on time-frequency technique | |
Djagarov et al. | Simulating a Inter Turn Fault by Asymmetric Induction Motor Model | |
Mazzoletti et al. | Online detection of interturn short-circuit fault in induction motor based on 5th harmonic current tracking using Vold-Kalman filter |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |