CN110320467B - Low-voltage direct-current circuit breaker fault diagnosis method - Google Patents
Low-voltage direct-current circuit breaker fault diagnosis method Download PDFInfo
- Publication number
- CN110320467B CN110320467B CN201910530188.3A CN201910530188A CN110320467B CN 110320467 B CN110320467 B CN 110320467B CN 201910530188 A CN201910530188 A CN 201910530188A CN 110320467 B CN110320467 B CN 110320467B
- Authority
- CN
- China
- Prior art keywords
- circuit breaker
- low
- current circuit
- vibration signal
- fault
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- 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
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3277—Testing of circuit interrupters, switches or circuit-breakers of low voltage devices, e.g. domestic or industrial devices, such as motor protections, relays, rotation switches
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention discloses a fault diagnosis method for a low-voltage direct-current circuit breaker, which comprises the steps of obtaining a vibration signal of the low-voltage direct-current circuit breaker in the opening and closing action through a sensor technology, filtering the vibration signal through a signal processing technology, removing a trend term, denoising, extracting a normalized energy value of each frequency band of the vibration signal through a wavelet packet to serve as a characteristic quantity, finally utilizing a neural network Elman with local feedback to realize intelligent diagnosis of the state of the direct-current circuit breaker, and predicting the state and the residual life of the direct-current circuit breaker in longitudinal time; because the Elman neural network is provided with a local feedback part, the algorithm not only realizes fault identification, but also realizes state prediction, and therefore the method provides a basis for maintenance of the direct current circuit breaker.
Description
Technical Field
The invention belongs to the field of monitoring and diagnosing the state of electric equipment of a direct current power system, and particularly relates to a state monitoring and fault diagnosing method of a low-voltage direct current circuit breaker.
Background
Compared with alternating current power distribution, direct current power distribution has the advantages of large transmission capacity, high power supply reliability, good electric energy quality and the like, and the direct current power distribution technology is adopted in the fields of spaceflight, ships, rail transit, new energy distributed power generation and the like at present. The low-voltage direct-current circuit breaker is used as the most critical switch equipment in a direct-current power distribution system, plays the control role of breaking a closed system and the protection role of ensuring the safe and reliable operation of a power distribution network, and therefore the stable operation of the direct-current power distribution system is directly influenced by the state of the direct-current circuit breaker.
The low-voltage direct-current circuit breaker is used as an electrical device, has a plurality of mechanical components, and is difficult to directly observe the state of the circuit breaker from the appearance so as to evaluate whether the circuit breaker is degraded or failed. Through statistics of related organizations at home and abroad, more than 70% of faults of the circuit breaker are found to be mechanical faults. Whereas previous related research has focused primarily on monitoring and diagnosis of high voltage circuit breakers.
Therefore, a method for on-line monitoring and fault diagnosis of a distribution-side low-voltage direct-current circuit breaker is needed, which can evaluate the state of the low-voltage direct-current circuit breaker and realize fault diagnosis and predictive maintenance of the low-voltage direct-current circuit breaker. This is very significant for improving the reliability of low voltage dc circuit breakers and for implementing full life cycle management of predictive maintenance strategies.
Disclosure of Invention
In view of the shortcomings of the prior art, the invention aims to provide a method for fault diagnosis according to a vibration signal of a low-voltage direct-current circuit breaker.
The technical scheme adopted by the invention for solving the technical problems is as follows: a low-voltage direct-current circuit breaker fault diagnosis method comprises the steps of selecting a vibration sensor, measuring vibration signals generated by the low-voltage direct-current circuit breaker in the switching-on and switching-off process, extracting characteristic quantities of the vibration signals through a proper vibration signal preprocessing and processing method, reducing dimensions of the characteristic quantities, inputting the characteristic quantities into a neural network Elman with a local feedback function after training of a test sample, and achieving fault diagnosis and prediction of the state of the low-voltage direct-current circuit breaker.
The further implementation steps comprise:
(1) selecting proper vibration sensor to collect vibration signal in the switching-on and switching-off process of low-voltage DC circuit breakerx(n) And transmitted to an upper computer through a communication board;
(2) will signalx(n) Obtaining signals by designed low-pass filteringx 1(n)；
(3) Processing the signal by fitting a polynomial using a least squares methodx 1(n) Obtaining the vibration signal with the trend term removedx 2(n)；
(4) Applying heuristic wavelet soft threshold denoising method to signalx 2(n) Obtaining signals after wavelet denoisingx 3(n)；
(5) Processing signals in full frequency band by using two-layer wavelet packet decomposition algorithmx 3(n) The wavelet basis function is db10, and the energy ratio of each frequency band is obtained through normalization processingT=[t 1 t 2 t 3 t 4]；
(6) According to the sensor range and the low-pass filter cut-off frequency fcTIs subjected to dimensionality reduction to obtainT j ；
(7) Will beT j Inputting the fault pattern into an Elman neural network for fault pattern recognition, diagnosing the fault of the low-voltage direct-current circuit breaker, and obtaining a diagnosis result: if the fault or the serious degradation occurs, stopping the machine for maintenance, otherwise, continuously acquiring a vibration signal;
(8) and (4) repeatedly executing the steps (2) to (6) under the condition that a stop instruction is not obtained, and otherwise, exiting the running state.
Further, in the case of a liquid crystal display,
the sensor selected in the step (1) requires no information loss in the full time domain range of the vibration signal, meets the measuring range condition, and has high sensitivity and wide measuring frequency range.
The filter selected in the step (2) is required to effectively remove the interference of the original vibration signal, and blindness of randomly selecting the cut-off frequency is avoided.
And (4) denoising the vibration signal by adopting a wavelet soft threshold denoising method, and selecting a threshold value by adopting a heuristic threshold value estimation method so as to realize the optimal estimation of the threshold value.
And (5) extracting the characteristic quantity of the vibration signal by adopting a wavelet packet decomposition algorithm, and analyzing the vibration signal in a full frequency band.
And (4) the effective range of the signal in the step (6) is influenced by the cut-off frequency, the characteristic quantity of the signal higher than the cut-off frequency of the low-pass filter is removed, the effective characteristic quantity is left, and the dimension of the characteristic quantity is reduced. Wherein the meridian tropism is removedObtaining the preprocessed vibration signals by a potential item and heuristic wavelet soft threshold denoising method, and respectively obtaining the values of the energy of four frequency bands in the total energy through two layers of wavelet packet decompositionT=[t 1 t 2 t 3 t 4]Removing two characteristic quantities of high frequency band by sensor frequency range and cut-off frequency of low-pass filterT j =[t 1 t 2]And realizing the characteristic quantity dimension reduction processing.
The method for acquiring the training sample in the step (7) comprises the following steps: (71) measuring vibration signals when faults are simulated under test conditions, and simulating faults such as undervoltage or overvoltage of a switching-on/off coil, clamping stagnation of the switching-on/off coil and aging of the switching-on/off coil; (72) measuring opening and closing vibration signals in a service life test, wherein the data reflect the characteristics of the circuit breaker along with the longitudinal change of a time axis; (73) and measuring the opening and closing vibration signals in the actual working condition.
Measuring vibration signals under six simulation conditions of normal closing, normal opening, under-voltage of a closing coil to 180V, under-voltage of the closing coil to 160V, aging of the closing coil, clamping stagnation of the closing coil and the like, testing multiple groups of data under each simulation condition, measuring vibration signals in a circuit breaker life test and in actual operation, extracting effective characteristic quantities by adopting the steps, randomly dividing the effective characteristic quantities into training samples and testing samples, inputting the training samples into an Elman neural network for learning, and inputting the testing samples into the learned neural network to obtain a diagnosis result.
The invention has the beneficial effects that: the method comprises the steps of obtaining vibration signals of the low-voltage direct-current circuit breaker in opening and closing actions through a sensor technology, filtering the vibration signals through a signal processing technology, removing trend terms, denoising, extracting normalized energy values of all frequency bands of the vibration signals through wavelet packets to serve as characteristic quantities, finally utilizing a neural network Elman with local feedback to achieve intelligent diagnosis of the state of the direct-current circuit breaker, predicting the state and the residual life of the direct-current circuit breaker in longitudinal time, and providing a basis for maintenance of the direct-current circuit breaker.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a block diagram of the present invention;
FIG. 3 is a low pass filtered vibration signal;
FIG. 4 is a FFT spectrum of a filtered vibration signal;
FIG. 5 is a normalized energy spectrum histogram of a vibration signal during a normal closing operation extracted by a two-layer wavelet packet decomposition algorithm;
fig. 6 is a block diagram of the Elman neural network employed.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The low-voltage direct-current circuit breaker is a key device in a direct-current power supply and distribution system, such as a direct-current circuit breaker in a subway traction direct-current power supply system. When the circuit breaker works daily, the on-off of a primary circuit is controlled by frequent switching on and off, and the state and the service life of the low-voltage direct-current circuit breaker can be influenced by frequent switching on and off. The traditional method for checking the state of the circuit breaker has the problems of under-maintenance and over-maintenance due to regular maintenance.
The invention designs a method for fault diagnosis according to a vibration signal of a low-voltage direct-current circuit breaker, which can be realized by the following steps:
and selecting a vibration sensor with a range meeting requirement, high sensitivity and a wide frequency range, and measuring to obtain a vibration signal without information loss of the low-voltage direct-current circuit breaker in the opening and closing actions.
A low-pass filter is designed, so that the interference of an original vibration signal is effectively removed, and the blindness of randomly selecting a cut-off frequency is avoided.
The cut-off frequency fc of the low-pass filtering should be selected considering 2 points: 1 is the frequency range f of the vibration sensor, 2 is the FFT spectrum analysis of the vibration signal; the cut-off frequency fc of the low-pass filter is determined according to 1, 2.
And after the feature vector is obtained by wavelet packet processing, further obtaining the effective feature quantity by dimension reduction processing.
The method for acquiring the training sample comprises the following steps: 1, measuring a vibration signal when simulating faults under test conditions, and simulating the faults such as undervoltage or overvoltage of a switching-on/off coil, clamping stagnation of the switching-on/off coil and aging of the switching-on/off coil; 2, measuring the opening and closing vibration signals in a service life test, wherein the data reflects the characteristics of the circuit breaker along with the longitudinal change of a time axis, and 3, measuring the opening and closing vibration signals in an actual working condition.
The training samples comprise simulated fault data, actual operation data and life test data which can occur, and the sample data can be used for fault mode identification and fault prediction.
The Elman neural network is a local regression network, can memorize the past state and realize state prediction, is applied to a breaker fault diagnosis system, can realize not only breaker fault mode identification, but also state prediction, predicts the state which does not have faults but is seriously degraded, and converts the timing maintenance of the low-voltage direct-current breaker into predictive maintenance.
The object of the invention is achieved by combining the attached figure 1:
(1) selecting a proper vibration sensor to collect vibration signals in the switching-on and switching-off process of the low-voltage direct-current circuit breakerx(n) And transmitted to an upper computer through a communication board.
(2) Will be provided withx(n) Obtaining signals by designed low-pass filteringx 1(n)。
(3) Method processing for fitting polynomial using least squaresx 1(n) Obtaining the vibration signal after removing the trend itemx 2(n)。
(4) Obtaining signals by adopting heuristic wavelet soft threshold denoising methodx 3(n)。
(5) Processing in full frequency band by adopting two-layer wavelet packet decomposition algorithmx 3(n) The wavelet basis function is db10, and the energy ratio of each frequency band is obtained through normalization processingT=[t 1 t 2 t 3 t 4]。
(6) According to the sensor range and the low-pass filter cut-off frequency fcTIs subjected to dimensionality reduction to obtainT j 。
(6) Will be provided withT j And inputting the fault pattern into an Elman neural network for fault pattern recognition, and diagnosing the fault of the low-voltage direct-current circuit breaker. If the vibration signal is in failure or seriously degraded, the machine is stopped for maintenance, and otherwise, the vibration signal is continuously acquired.
(7) And (4) repeatedly executing the steps (2) to (6) under the condition that a stop instruction is not obtained, and otherwise, exiting the running state.
A vibration sensor meeting the requirements of measuring range, high sensitivity and wide frequency range is selected through comparison, the type is ADXL1004, the measuring range is +/-500 g, the sensitivity is 10mV/g, and the frequency range is 1-24000 Hz.
Analyzing the FFT frequency spectrum of the vibration signal and combining the frequency range of the ADXL1004 sensor, a low-pass filter with fc =30kHz is designed to filter the original vibration signal.
Then obtaining preprocessed vibration signals through a trend removing item and a heuristic wavelet soft threshold denoising method, and obtaining the values of the energy of the four frequency bands in the total energy through two layers of wavelet packet decomposition respectivelyT=[t 1 t 2 t 3 t 4]Removing two characteristic quantities of high frequency band by sensor frequency range and cut-off frequency of low-pass filterT j =[t 1 t 2]And realizing the characteristic quantity dimension reduction processing.
Vibration signals were measured for six simulation cases: normal closing 1, normal opening 2, 3 under-voltage of a closing coil to 180V, under-voltage of a 4 closing coil to 160V, aging of a 5 closing coil (the closing coil is connected with a 6 omega resistor in series), and clamping of the 6 closing coil. And testing multiple groups of data for each simulated condition, measuring vibration signals in the service life test and the actual operation of the circuit breaker, extracting effective characteristic quantities by adopting the steps, randomly dividing the effective characteristic quantities into training samples and testing samples, inputting the training samples into an Elman neural network for learning, and inputting the testing samples into the learned neural network to obtain a diagnosis result.
As can be seen from fig. 2, the vibration sensor has a small measuring range, which may cause an over-measuring range, and the low sensitivity may cause information loss in the acquired signal.
Fig. 3 and 4 are waveforms of the vibration signal before and after filtering and a Fast Fourier (FFT) spectrum. Comparing fig. 3 and fig. 4, it can be seen that the high frequency noise of the vibration signal is reduced much after the low pass filtering.
FIG. 5 is a two-layer wavelet packet decomposition normalized energy spectrum histogram during normal closing; as can be seen from fig. 3 and 4: the energy occupation ratio in a high frequency band is very small, and characteristic quantity dimension reduction processing is needed.
Fig. 6 is a block diagram of an Elman neural network, which mainly includes an input layer, an output layer, and a hidden layer. It features local feedback and time predicting function. For the fault diagnosis of the low-voltage direct-current circuit breaker, the vibration signal characteristic quantities are longitudinally compared on a time axis, so that the fault mode identification and the state prediction of the low-voltage direct-current circuit breaker are predicted, and the full life cycle management of the low-voltage direct-current circuit breaker is further realized.
The above-described embodiments are merely illustrative of the principles and effects of the present invention, and some embodiments may be applied, and it will be apparent to those skilled in the art that various changes and modifications may be made without departing from the inventive concept of the present invention, and these embodiments are within the scope of the present invention.
Claims (4)
1. A fault diagnosis method for a low-voltage direct-current circuit breaker is characterized by comprising the following steps: the implementation steps comprise:
(1) selecting proper vibration sensor to collect vibration signal in the switching-on and switching-off process of low-voltage DC circuit breakerx(n) And transmitted to an upper computer through a communication board;
(2) will signalx(n) Obtaining the signal by low-pass filteringx 1(n)；
(3) Processing the signal by fitting a polynomial using a least squares methodx 1(n) Obtaining the vibration signal with the trend term removedx 2(n)；
(4) Applying heuristic wavelet soft threshold denoising method to signalx 2(n) Obtaining signals after wavelet denoisingx 3(n) Selecting a threshold value by adopting a heuristic threshold value estimation method so as to realize the optimal estimation of the threshold value;
(5) extracting vibration signal characteristic quantity by adopting a two-layer wavelet packet decomposition algorithm, analyzing the vibration signal in full frequency band, and processing the signalx 3(n) The wavelet basis function is db10, and the energy ratio of each frequency band is obtained through normalization processingT=[t 1 t 2 t 3 t 4]；
(6) According to the sensor range and the low-pass filter cut-off frequency fcTIs subjected to dimensionality reduction to obtainT j Obtaining preprocessed vibration signals by a trend removing item and a heuristic wavelet soft threshold denoising method, and respectively obtaining the value of the energy of four frequency bands in the total energy through two layers of wavelet packet decompositionT=[t 1 t 2 t 3 t 4]Removing two characteristic quantities of high frequency band by sensor frequency range and cut-off frequency of low-pass filterT j =[t 1 t 2]Realizing the characteristic quantity dimension reduction processing;
(7) will beT j Inputting the fault pattern into an Elman neural network for fault pattern recognition, diagnosing the fault of the low-voltage direct-current circuit breaker, and obtaining a diagnosis result: if the fault or the serious degradation occurs, stopping the machine for maintenance, otherwise, continuously acquiring a vibration signal, wherein the method for acquiring the training sample comprises the following steps:
(71) measuring vibration signals when faults are simulated under test conditions, and simulating faults such as undervoltage or overvoltage of a switching-on/off coil, clamping stagnation of the switching-on/off coil and aging of the switching-on/off coil;
(72) measuring opening and closing vibration signals in a service life test, wherein the data reflect the characteristics of the circuit breaker along with the longitudinal change of a time axis;
(73) measuring an opening and closing vibration signal in an actual working condition;
(8) and (4) repeatedly executing the steps (2) to (6) under the condition that a stop instruction is not obtained, and otherwise, exiting the running state.
2. The method for diagnosing the fault of the low-voltage direct-current circuit breaker according to claim 1, wherein the sensor selected in the step (1) requires no missing information in the full time domain range of the vibration signal, meets the range condition, and has high sensitivity and wide measurement frequency range.
3. The method for diagnosing the fault of the low-voltage direct-current circuit breaker according to claim 1, wherein the filter selected in the step (2) is required to effectively remove the interference of an original vibration signal and avoid blindness of randomly selecting a cut-off frequency.
4. The method for diagnosing the fault of the low-voltage direct-current circuit breaker according to claim 1, wherein vibration signals under six simulation conditions of normal closing, normal opening, under-voltage of a closing coil to 180V, under-voltage of the closing coil to 160V, aging of the closing coil, clamping stagnation of the closing coil and the like are measured in the step (7), multiple groups of data are tested for each simulation condition, the vibration signals in a circuit breaker service life test and actual operation are measured, effective characteristic quantities are extracted by adopting the steps, the effective characteristic quantities are randomly divided into training samples and test samples, the training samples are input into an Elman neural network for learning, and the test samples are input into the learned neural network to obtain a diagnosis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910530188.3A CN110320467B (en) | 2019-06-19 | 2019-06-19 | Low-voltage direct-current circuit breaker fault diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910530188.3A CN110320467B (en) | 2019-06-19 | 2019-06-19 | Low-voltage direct-current circuit breaker fault diagnosis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110320467A CN110320467A (en) | 2019-10-11 |
| CN110320467B true CN110320467B (en) | 2021-11-09 |
Family
ID=68120976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910530188.3A Active CN110320467B (en) | 2019-06-19 | 2019-06-19 | Low-voltage direct-current circuit breaker fault diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110320467B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110926778B (en) * | 2019-11-29 | 2021-08-20 | 国网天津市电力公司电力科学研究院 | Mechanical fault diagnosis method for gas insulated switchgear assembly based on abnormal vibration |
| CN111157882A (en) * | 2019-12-26 | 2020-05-15 | 华电电力科学研究院有限公司 | Method for monitoring closing and opening states of generator outlet circuit breaker |
| CN111289800B (en) * | 2020-03-05 | 2022-04-26 | 国网安徽省电力有限公司 | Small-resistance vibration monitoring method based on generalized regression neural network |
| CN111781494B (en) * | 2020-07-09 | 2021-04-20 | 西安交通大学 | Improved automatic on-line detection method and device for mechanical characteristics of circuit breaker |
| CN112345213A (en) * | 2020-09-18 | 2021-02-09 | 华能河南中原燃气发电有限公司 | Low-voltage direct-current circuit breaker mechanical fault diagnosis method |
| CN112947374A (en) * | 2021-02-09 | 2021-06-11 | 上海海事大学 | Intelligent self-healing control method for electric propulsion of regional distribution ship |
| CN113466679B (en) * | 2021-05-17 | 2024-01-05 | 浙江工业大学 | Circuit breaker service life estimation method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1616196A4 (en) * | 2003-04-03 | 2009-05-20 | Univ Virginia | Method and system for the derivation of human gait characteristics and detecting falls passively from floor vibrations |
| CN103048137A (en) * | 2012-12-20 | 2013-04-17 | 北京航空航天大学 | Fault diagnosis method of rolling bearing under variable working conditions |
| CN103308292A (en) * | 2013-05-16 | 2013-09-18 | 国家电网公司 | Vacuum breaker mechanical state detecting method based on vibration signal analysis |
| CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
| CN109061463A (en) * | 2018-09-29 | 2018-12-21 | 华南理工大学 | A kind of monitoring of mechanical state of high-voltage circuit breaker and method for diagnosing faults |
-
2019
- 2019-06-19 CN CN201910530188.3A patent/CN110320467B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1616196A4 (en) * | 2003-04-03 | 2009-05-20 | Univ Virginia | Method and system for the derivation of human gait characteristics and detecting falls passively from floor vibrations |
| CN103048137A (en) * | 2012-12-20 | 2013-04-17 | 北京航空航天大学 | Fault diagnosis method of rolling bearing under variable working conditions |
| CN103308292A (en) * | 2013-05-16 | 2013-09-18 | 国家电网公司 | Vacuum breaker mechanical state detecting method based on vibration signal analysis |
| CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
| CN109061463A (en) * | 2018-09-29 | 2018-12-21 | 华南理工大学 | A kind of monitoring of mechanical state of high-voltage circuit breaker and method for diagnosing faults |
Non-Patent Citations (1)
| Title |
|---|
| "低压断路器振动特性分析与合闸同期性研究";缪希仁 等;《电工技术学报》;20130630;第28卷(第6期);第81-85页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110320467A (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110320467B (en) | Low-voltage direct-current circuit breaker fault diagnosis method | |
| Razi-Kazemi et al. | Condition monitoring of high voltage circuit breakers: past to future | |
| CN106597231B (en) | GIS fault detection system and method based on Multi-source Information Fusion and deep learning network | |
| Schichler et al. | Risk assessment on defects in GIS based on PD diagnostics | |
| Bollen et al. | Bridging the gap between signal and power | |
| CN105868770B (en) | A kind of Fault Diagnosis for HV Circuit Breakers method based on unsupervised learning model | |
| Idrees et al. | Fuzzy logic based calculation and analysis of health index for power transformer installed in grid stations | |
| CN107884711A (en) | Breaker method of testing and terminal | |
| CN202404166U (en) | On-line monitoring system for vibration performance of transformer | |
| CN106959394B (en) | A kind of high-voltage large-capacity STATCOM state evaluating method and system | |
| CN108828406A (en) | The fault recognition method and its system of non-intrusion type user power utilization | |
| CN109444690B (en) | Test method for simulating internal insulation defect discharge of transformer | |
| CN106597196A (en) | State monitoring and intelligent diagnosis and analysis system and method for power transmission and transformation equipment | |
| CN107728509A (en) | A kind of breaker mechanic property on-line expert diagnostic system based on Multidimensional Data Model | |
| CN103901318B (en) | The method of positioning both ground failure and insulation degraded condition in energy conversion system | |
| CN113960463A (en) | On-load tap-changer on-line monitoring and fault diagnosis method for voltage regulating transformer | |
| Faisal et al. | Power quality diagnosis using time frequency analysis and rule based techniques | |
| CN104122473A (en) | Online monitoring method for states of secondary device of distribution network | |
| CN117007901A (en) | Joint fault diagnosis method and system based on power transmission line topology | |
| Montanari | Envisaging links between fundamental research in electrical insulation and electrical asset management | |
| CN105629144A (en) | High voltage switchgear partial discharge diagnosis method and system based on fingerprint database | |
| Adami et al. | New approach to improve high-voltage transmission line reliability | |
| CN111722060B (en) | Distribution line early fault severity evaluation method based on waveform characteristics | |
| Kwong et al. | From Great to Excellence: Approaching to Total Condition Based Management of Power Transformer under Smart Grid Operations | |
| Ren et al. | Transformer fault analysis based on Bayesian networks and importance measures |
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 |