CN115792442A - Data-driven comprehensive fault diagnosis method for direct-current switch cabinet for rail transit - Google Patents
Data-driven comprehensive fault diagnosis method for direct-current switch cabinet for rail transit Download PDFInfo
- Publication number
- CN115792442A CN115792442A CN202211473989.9A CN202211473989A CN115792442A CN 115792442 A CN115792442 A CN 115792442A CN 202211473989 A CN202211473989 A CN 202211473989A CN 115792442 A CN115792442 A CN 115792442A
- Authority
- CN
- China
- Prior art keywords
- detection unit
- switch cabinet
- characteristic
- characteristic detection
- direct
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention discloses a data-driven comprehensive fault diagnosis method for a rail transit direct-current switch cabinet, which comprises an intelligent measurement and control terminal, a monitoring host, a temperature characteristic detection unit, an electrical characteristic detection unit, a mechanical characteristic detection unit, an expert system and a neural network, and comprises the following steps: s1: a temperature characteristic detection unit, an electrical characteristic detection unit and a mechanical characteristic detection unit are arranged on a circuit breaker in a direct-current switch cabinet. The method comprises the steps of detecting the current of a brake separating coil, the current of a main loop, an arc voltage signal, the temperature of a moving contact and an impact vibration signal, extracting degradation characteristics and characteristic dimension reduction through a monitoring host to collected signal data characteristics, selecting a characteristic difference value m and a maximum error value n through generating a real-time characteristic curve and a reference characteristic curve, and judging the conditions of failure of the moving contact and abrasion of an iron core in the direct current switch cabinet through comparison of the characteristic difference value m and the maximum error value n.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to a data-driven comprehensive fault diagnosis method for a direct-current switch cabinet for rail transit.
Background
The DC switch cabinet in subway transformer substation includes 750V and 1500V voltage levels, and most of the switch cabinet equipment for subway engineering consists of 5 kinds of cabinet bodies or box bodies, including incoming line cabinet, feed line cabinet, negative pole cabinet, terminal cabinet and steel rail potential limiting device.
In order to ensure the normal operation of the direct current switch cabinet, the current transformation ratio protection, the good leakage protection, the direct current breaker failure protection, the heavy current tripping protection, the overcurrent protection, the double-side linked tripping protection and the automatic reclosing function are used for protection in the prior art to prevent major faults, however, when the direct current switch cabinet fails, a professional maintainer is required to overhaul, and the maintainer does not know the reason of the fault occurrence during overhaul, so that the fault occurrence needs to be detected and eliminated item by item, the consumed time is longer, the normal operation of a substation is influenced, and the data-driven rail alternating current general direct current switch cabinet comprehensive fault diagnosis method based on the data drive with good diagnosis and detection effects is provided for the problems of failure of a moving contact and the abrasion of an iron core.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a data-driven comprehensive fault diagnosis method for a direct-current switch cabinet for rail transit, and the method has the advantage of good diagnosis and detection effects.
In order to achieve the purpose, the invention provides the following technical scheme: the data-driven comprehensive fault diagnosis method for the direct current switch cabinet for the rail transit comprises an intelligent measurement and control terminal, a monitoring host, a temperature characteristic detection unit, an electrical characteristic detection unit, a mechanical characteristic detection unit, an expert system and a neural network, and comprises the following steps:
s1: a temperature characteristic detection unit, an electrical characteristic detection unit and a mechanical characteristic detection unit are arranged on a circuit breaker in a direct-current switch cabinet;
s2: the temperature characteristic detection unit, the electrical characteristic detection unit and the mechanical characteristic detection unit are electrically connected with the monitoring host, so that detected data can be transmitted to the monitoring host in time;
s3: the monitoring host computer extracts and analyzes the characteristics of the acquired signal data;
s4: and diagnosing the fault through the intelligent measurement and control terminal.
Preferably, the temperature characteristic detection unit detects the temperature characteristic through a temperature sensor, mainly the temperature of the moving contact; the electrical characteristic detection unit detects electrical characteristics, mainly comprising current and arc voltage, wherein the current is divided into opening coil current and main loop current; the mechanical characteristic detection unit mainly detects impact vibration.
Preferably, the extracting and analyzing of the signal data features in S3 sequentially includes extracting degradation features and feature dimension reduction, the extracting degradation features specifically includes transmitting the obtained signal data to an expert system, identifying and screening the degradation features by the expert system, and the feature dimension reduction specifically includes merging all the same features and close features in a certain time period, and removing extreme value features.
Preferably, the feature dimension reduction method adopts a feature combination, the feature combination adopts a minimum reconstruction error method, and the step of principal component analysis in the minimum reconstruction error method comprises the following steps:
calculating a dispersion matrix S: s = ∑ Σ k n ＝1(x k -m)(x k -m) t ；
Calculating the eigenvalue and eigenvector of S: se = λ e;
sorting the eigenvectors from large to small according to the corresponding eigenvalues;
the largest d' eigenvectors are selected as projection vectors e 1 ,e 2 ,...,e d′ Forming a matrix W of projections d x d, wherein the ith column is e i ；
For any d-dimensional sample x, the d' dimensional vector after dimensionality reduction by PCA is y = W t (x-m)。
Preferably, the intelligent measurement and control terminal adopts a neural network as an information processing system, and the intelligent measurement and control terminal performs double positioning on the fault through signal data when diagnosing the fault, matches the fault type in the database and acquires the fault position in the positioning system.
Preferably, the intelligent measurement and control terminal generates a real-time characteristic curve by using the signal data acquired and analyzed by the monitoring host, acquires a reference characteristic curve by using an expert system, compares the real-time characteristic curve with the reference characteristic curve by using a unit with time in the X direction as a unit in the normal working state, and determines a characteristic difference value between the reference characteristic curve and the real-time characteristic curve in the same unit time, wherein the characteristic difference value is marked as m;
obtaining the maximum error value which can exist through the expert system, recording the maximum error value as n, dividing the maximum error value into a stable threshold value and a warning threshold value according to the working condition, and recording the stable threshold value as n 1 Said warning threshold is denoted as n 2 ；
The formula of the fault diagnosis is as follows: m is more than n;
when m is equal to n 2 And then, the intelligent measurement and control terminal establishes a judgment database and moves the number of signals in unit time into the judgment database.
Compared with the prior art, the invention has the following beneficial effects:
the method comprises the steps of using a temperature characteristic detection unit, an electrical characteristic detection unit and a mechanical characteristic detection unit as detection devices of original sensing signals, detecting the current of a brake separating coil, the current of a main loop, an arc voltage signal, the temperature of a moving contact and an impact vibration signal, extracting degradation characteristics and characteristic dimension reduction of collected signal data characteristics through a monitoring host, reducing the number of prediction variables by adopting a minimum reconstruction error method, removing data noise, reducing algorithm operation overhead, selecting a characteristic difference value m and a maximum error value n by generating a real-time characteristic curve and a reference characteristic curve, judging the conditions of failure of the moving contact and abrasion of an iron core in a direct current switch cabinet by comparing the two, obtaining fault positions in a positioning system by matching fault types in a database, facilitating quick maintenance of maintainers, improving maintenance efficiency, and obtaining a warning threshold value n 2 And a warning threshold n 2 Comparing with the characteristic difference m, and when the characteristic difference m belongs to the warning threshold n 2 When the direct current switch cabinet is used, signals in unit time to which the characteristic difference m belongs are separately recorded in a row, comparison is facilitated, understanding of conditions of the direct current switch cabinet can be improved, and a prevention effect is achieved to a certain extent.
Drawings
FIG. 1 is a schematic diagram of the diagnostic process of the present invention.
Detailed Description
All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a technical scheme that: the data-driven comprehensive fault diagnosis method for the direct current switch cabinet for the rail transit comprises an intelligent measurement and control terminal, a monitoring host, a temperature characteristic detection unit, an electrical characteristic detection unit, a mechanical characteristic detection unit, an expert system and a neural network, and comprises the following steps:
s1: a temperature characteristic detection unit, an electrical characteristic detection unit and a mechanical characteristic detection unit are arranged on a circuit breaker in a direct-current switch cabinet;
s2: the temperature characteristic detection unit, the electrical characteristic detection unit and the mechanical characteristic detection unit are electrically connected with the monitoring host, so that detected data can be transmitted to the monitoring host in time;
s3: the monitoring host computer extracts and analyzes the characteristics of the acquired signal data;
s4: and diagnosing the fault through the intelligent measurement and control terminal.
The temperature characteristic detection unit detects the temperature characteristic through a temperature sensor, and the temperature characteristic is mainly the temperature of the moving contact; the electrical characteristic detection unit detects electrical characteristics, mainly comprising current and arc voltage, wherein the current is divided into opening coil current and main loop current; the mechanical characteristic detection unit mainly detects impact vibration; the working state of internal components can be known in time by detecting the working state data of the direct current switch cabinet, so that the timely feedback of the fault of the direct current switch cabinet is obtained through data analysis, and then the fault part can be quickly found by maintainers through positioning the fault, the overhauling efficiency is improved, the economic loss is reduced, the burning-out accident of an opening coil and a closing coil often occurs in a power system, when the electric equipment has an accident, if the circuit breaker refuses to move due to the disconnection of a switching-off loop of a high-voltage vacuum circuit breaker, the accident is enlarged, the overgrade switching-off is caused to cause large-area power failure, and even serious consequences such as burning-out of the electric equipment, fire disaster and the like are caused; the working state of the opening coil can be effectively known through the detection of the current of the opening coil, and when the current of the opening coil fluctuates, the situation can be known timely, so that the problem can be solved in a targeted manner; the electric arc is the phenomenon of instantaneous spark generated by the current passing through an insulating medium (such as air) in a normal state because the electric field is too strong and the gas is subjected to electric breakdown, the electric arc has concentrated energy and high temperature, and not only has great destructive effect on a contact, but also prolongs the time for breaking a circuit, and has great influence on a direct current switch cabinet; vibration and temperature are also important information for the working state of the reaction device, and the abnormality of the working condition is necessarily accompanied by the above problems.
The extracting and analyzing of the signal data features in the step S3 sequentially comprises extracting degradation features and feature dimension reduction, wherein the extracting degradation features specifically comprises transmitting the obtained signal data to an expert system, identifying and screening the degradation features through the expert system, and the feature dimension reduction specifically comprises merging all the same features and close features in a certain time period, and removing extreme value features; the degradation characteristics refer to characteristic situations of performance degradation, so the degradation characteristics need to be extracted, and the failure of equipment is often accompanied with the degradation of electronic components; the expert system is a computer intelligent program system with special knowledge and experience, generally adopts knowledge representation and knowledge reasoning technology in artificial intelligence to simulate complex problems which can be solved by field experts, and can effectively reduce the labor amount and improve the working efficiency by using the expert system.
The feature dimension reduction method adopts a feature combination, the feature combination adopts a minimum reconstruction error method, and the step of principal component analysis in the minimum reconstruction error method comprises the following steps:
calculating a dispersion matrix S: s = ∑ Σ k n ＝1(x k -m)(x k -m) t ；
Calculating the eigenvalue and eigenvector of S: se = λ e;
sorting the eigenvectors from large to small according to the corresponding eigenvalues;
the largest d' eigenvectors are selected as projection vectors e 1 ,e 2 ,...,e d′ Forming a matrix W of projections d x d, wherein the ith column is e i ；
For any d-dimensional sample x, the d' dimensional vector after dimensionality reduction by PCA is y = W t (x-m); the feature dimension reduction is to reduce the dimension of the features, and is to combine all the features, remove the combination, divide the feature dimension into two types, namely, feature combination and feature selection, the feature combination combines several features together to form a new feature, the feature selection is to select a subset of the existing feature set, and simultaneously, different training algorithms are provided for different training targets, generally, the method has the advantages of minimizing reconstruction errors, maximizing category separability, minimizing classification errors, retaining the projection of the most details and making the features independent to the maximum extent, and the minimized reconstruction errors are performed by adopting a principal component analysis algorithm; along with the continuous reduction of data dimensions, the space required by data storage is reduced, the calculation time is reduced, meanwhile, algorithms are easy to perform poorly on high-dimensional data, the algorithm usability can be improved by dimension reduction, the multiple collinearity problem can be solved by deleting redundant features, and the data visualization is facilitated.
The intelligent measurement and control terminal adopts a neural network as an information processing system, and the intelligent measurement and control terminal performs double positioning on the fault through signal data when diagnosing the fault, matches the fault type in a database and acquires the fault position in a positioning system; the neural network is an operation model and is formed by mutually connecting a large number of nodes (or called neurons), has a self-learning function, can provide prediction for a user in use, and carries out targeted maintenance before a fault occurs, so that accidents are avoided; the data association system has an association storage function, and can associate data, so that the overall usefulness degree of the data is improved; has the capability of searching an optimized solution at high speed. The optimal solution of a complex problem is often searched for by a large amount of calculation, and a feedback type artificial neural network designed for a certain problem is utilized to exert the high-speed calculation capability of a computer, so that the optimal solution can be quickly found, the calculation efficiency is improved, and the time is saved.
The intelligent measurement and control terminal generates a real-time characteristic curve by using signal data acquired and analyzed by a monitoring host, acquires a reference characteristic curve by using an expert system, compares the real-time characteristic curve with the reference characteristic curve by using a unit with time as X direction, and determines a characteristic difference value between the reference characteristic curve and the real-time characteristic curve in the same unit time, wherein the characteristic difference value is marked as m;
obtaining the maximum error value which can exist through the expert system, recording the maximum error value as n, dividing the maximum error value into a stable threshold value and a warning threshold value according to the working condition, and recording the stable threshold value as n 1 Said warning threshold is denoted as n 2 ；
The formula of the fault diagnosis is as follows: m is more than n;
when m is equal to n 2 Then, the intelligent measurement and control terminal establishes a judgment database and moves the number of signals in unit time into the judgment database; the obtained reference characteristic curve and the real-time characteristic curve can be curves left after the start stage is removed, and the purpose is that the influence of data in the start stage on judging whether the switch cabinet has a fault is small, so that the reference characteristic curve and the real-time characteristic curve can be removed to reduce data processing capacity, the reference characteristic curve can be obtained in advance and can be used when needed, the reference characteristic curve and the real-time characteristic curve are compared through a broken line graph, the difference between the reference characteristic curve and the real-time characteristic curve can be observed clearly, the whole working state of the direct-current switch cabinet can be known more conveniently, the prediction of the working condition of the direct-current switch cabinet is facilitated, and the data processing and comparison are facilitated; but by setting a warning threshold n 2 When compared with the characteristic difference m, the characteristic difference m belongs to the warning threshold n 2 When in use, the signal data in unit time is stored separately, thereby facilitating the statistics and analysis of the inferior working condition,the use effect is better.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. A data-driven comprehensive fault diagnosis method for a direct-current switch cabinet for rail transit comprises an intelligent measurement and control terminal, a monitoring host, a temperature characteristic detection unit, an electrical characteristic detection unit, a mechanical characteristic detection unit, an expert system and a neural network, and is characterized in that: the data-drive-based comprehensive fault diagnosis method for the direct-current switch cabinet for the rail transit comprises the following steps of:
s1: a temperature characteristic detection unit, an electrical characteristic detection unit and a mechanical characteristic detection unit are arranged on a circuit breaker in a direct-current switch cabinet;
s2: the temperature characteristic detection unit, the electrical characteristic detection unit and the mechanical characteristic detection unit are electrically connected with the monitoring host, so that detected data can be transmitted to the monitoring host in time;
s3: the monitoring host computer extracts and analyzes the characteristics of the acquired signal data;
s4: and diagnosing the fault through the intelligent measurement and control terminal.
2. The method for diagnosing the comprehensive fault of the direct-current switch cabinet for the rail transit based on the data driving as claimed in claim 1, is characterized in that: the temperature characteristic detection unit detects the temperature characteristic through a temperature sensor, and the temperature characteristic is mainly the temperature of the moving contact; the electrical characteristic detection unit detects electrical characteristics, mainly comprising current and arc voltage, wherein the current is divided into opening coil current and main loop current; the mechanical characteristic detection unit mainly detects impact vibration.
3. The method for diagnosing the comprehensive fault of the direct-current switch cabinet for the rail transit based on the data driving as claimed in claim 1, is characterized in that: the extraction and analysis of the signal data features in the step S3 sequentially includes extracting degradation features and feature dimension reduction, wherein the extracting degradation features specifically includes transmitting the obtained signal data to an expert system, identifying and screening the degradation features through the expert system, and the feature dimension reduction specifically includes merging all the same features and close features in a certain time period, and removing extreme value features.
4. The data-driven integrated fault diagnosis method for the direct-current switch cabinet for the rail transit according to claim 3, characterized in that: the feature dimension reduction method adopts feature combination, the feature combination adopts a minimum reconstruction error method, and the step of principal component analysis in the minimum reconstruction error method comprises the following steps:
calculating a dispersion matrix S: s = ∑ Σ k n ＝1(x k -m)(x k -m) t ；
Calculating the characteristic value and the characteristic vector of S: se = λ e;
sorting the eigenvectors from large to small according to the corresponding eigenvalues;
the largest d' eigenvectors are selected as projection vectors e 1 ,e 2 ,...,e d′ Forming a matrix W of projections d x d, wherein the ith column is e i ；
For any d-dimensional sample x, the d' dimensional vector after dimensionality reduction by PCA is y = W t (x-m)。
5. The method for diagnosing the comprehensive fault of the direct-current switch cabinet for the rail transit based on the data driving as claimed in claim 1, is characterized in that: the intelligent measurement and control terminal adopts a neural network as an information processing system, and the intelligent measurement and control terminal performs double positioning on the fault through signal data when diagnosing the fault, matches the fault type in the database and acquires the fault position in the positioning system.
6. The method for diagnosing the comprehensive fault of the direct-current switch cabinet for the rail transit based on the data driving as claimed in claim 1, is characterized in that: the intelligent measurement and control terminal generates a real-time characteristic curve by using the signal data acquired and analyzed by the monitoring host, acquires a reference characteristic curve by using an expert system, compares the real-time characteristic curve with the reference characteristic curve by using the unit with time as X direction, and determines the characteristic difference between the reference characteristic curve and the real-time characteristic curve in the same unit time, wherein the characteristic difference is marked as m;
obtaining the maximum error value which can exist through the expert system, recording the maximum error value as n, dividing the maximum error value into a stable threshold value and a warning threshold value according to the working condition, and recording the stable threshold value as n 1 Said warning threshold is denoted as n 2 ；
The formula of the fault diagnosis is as follows: m is more than n;
when m is equal to n 2 And then, the intelligent measurement and control terminal establishes a judgment database and moves the number of signals in unit time into the judgment database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211473989.9A CN115792442A (en) | 2022-11-23 | 2022-11-23 | Data-driven comprehensive fault diagnosis method for direct-current switch cabinet for rail transit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211473989.9A CN115792442A (en) | 2022-11-23 | 2022-11-23 | Data-driven comprehensive fault diagnosis method for direct-current switch cabinet for rail transit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115792442A true CN115792442A (en) | 2023-03-14 |
Family
ID=85440488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211473989.9A Pending CN115792442A (en) | 2022-11-23 | 2022-11-23 | Data-driven comprehensive fault diagnosis method for direct-current switch cabinet for rail transit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115792442A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117706258A (en) * | 2024-02-06 | 2024-03-15 | 广州尚航信息科技股份有限公司 | Fault detection system based on big data processing |
-
2022
- 2022-11-23 CN CN202211473989.9A patent/CN115792442A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117706258A (en) * | 2024-02-06 | 2024-03-15 | 广州尚航信息科技股份有限公司 | Fault detection system based on big data processing |
| CN117706258B (en) * | 2024-02-06 | 2024-05-10 | 广州尚航信息科技股份有限公司 | Fault detection system based on big data processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Razi-Kazemi et al. | Data Mining of Online Diagnosed Waveforms for Probabilistic Condition Assessment of SF $ _ {6} $ Circuit Breakers | |
| Strachan et al. | Providing decision support for the condition-based maintenance of circuit breakers through data mining of trip coil current signatures | |
| CN105703258B (en) | GIS switch equipment action state monitoring system and use method thereof | |
| CN205622133U (en) | GIS switchgear action state monitoring system | |
| CN115792442A (en) | Data-driven comprehensive fault diagnosis method for direct-current switch cabinet for rail transit | |
| Mehta et al. | Transformer diagnostics under dissolved gas analysis using Support Vector Machine | |
| CN117590223B (en) | Online monitoring system and method for circuit breaker | |
| CN106093771B (en) | A kind of circuit-breaker switching on-off coil current signal recognition methods | |
| Souahlia et al. | SVM-based decision for power transformers fault diagnosis using Rogers and Doernenburg ratios DGA | |
| CN108020781A (en) | A kind of circuit breaker failure diagnostic method | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| CN106772009B (en) | Breaker mechanic property analysis method based on divide-shut brake coil current waveform | |
| Shutenko et al. | Recognition of combined defects with high-temperature overheating based on the dissolved gas analysis | |
| Oleg et al. | Recognition of mid-temperature overheating in high-voltage power transformers by dissolved gas analysis | |
| CN111458630B (en) | Fault diagnosis method for high-voltage circuit breaker | |
| CN115728627B (en) | Electric moving and static contact fault pre-judging system | |
| CN115728628A (en) | On-line monitoring and early warning method and device for circuit breaker control loop fault | |
| CN115856611A (en) | High-voltage circuit breaker fault diagnosis method based on deep learning | |
| Brown et al. | Learning models of plant behavior for anomaly detection and condition monitoring | |
| CN115330046A (en) | Health state evaluation and service life prediction method for rail transit train vehicle-mounted high-voltage equipment | |
| Sahri et al. | Fault diagnosis of power transformer using optimally selected DGA features and SVM | |
| CN115575863A (en) | OLTC (on-line test) voiceprint signal identification method based on phase space trajectory diagram principle | |
| Gomathy et al. | IPSO based fault analysis in power transformer | |
| KR102436080B1 (en) | Method for status prediction of transformer based on oil filtering and apparatus for using the method | |
| KR102520724B1 (en) | Method for failure detection of circuit breaker and apparatus for performing the same |
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 |