CN114355184B - Online learning-based high-voltage circuit breaker state monitoring and early warning method - Google Patents
Online learning-based high-voltage circuit breaker state monitoring and early warning method Download PDFInfo
- Publication number
- CN114355184B CN114355184B CN202210009459.2A CN202210009459A CN114355184B CN 114355184 B CN114355184 B CN 114355184B CN 202210009459 A CN202210009459 A CN 202210009459A CN 114355184 B CN114355184 B CN 114355184B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- circuit breaker
- voltage circuit
- module
- state
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000013500 data storage Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 21
- 238000010801 machine learning Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 8
- 238000005299 abrasion Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Abstract
The invention discloses a high-voltage circuit breaker state monitoring and early warning method based on online learning, wherein an early warning system comprises a data acquisition module for acquiring operation state parameters of a high-voltage circuit breaker; the timing module, the data storage module, the monitoring module, the high-voltage circuit breaker operation state parameter that the monitoring module receives that the data acquisition module gathers and corresponding acquisition time, set up the characteristic vector of the high-voltage circuit breaker operation state parameter, predict through the model that trains, and store the high-voltage circuit breaker operation state parameter in the data storage module; the online learning module is connected with the monitoring module and updates the monitoring model; and the operation detection terminal module is connected with the monitoring module and used for receiving and displaying the monitoring result from the monitoring module. The system has the advantages of simple structure, reasonable design, convenient realization, good use effect and convenient popularization and use, can be effectively applied to the state monitoring of the high-voltage circuit breaker, ensures that the monitoring is more comprehensive and perfect, and has high precision.
Description
Technical Field
The invention belongs to the technical field of intelligent power grids, and particularly relates to a high-voltage circuit breaker state monitoring and early warning method based on online learning.
Background
In a grid transmission line, the reliability of a high voltage circuit breaker is directly related to the safety of the overall operation of the power system. It is counted that approximately 40% to 60% of the faults are caused by high voltage circuit breakers. Each switch of the high-voltage circuit breaker causes certain abrasion to the contact point; meanwhile, the mechanical action of the operating mechanism also enables the mechanical structure of the high-voltage circuit breaker to have a certain service life, and once the service life limit is reached, the circuit breaker can be broken down or accident can be caused. Therefore, the operation state and reliability of the high-voltage circuit breaker need to be monitored and pre-warned by a proper method.
The number of the running state parameter values of the high-voltage circuit breaker is large, the running state parameter values are complex and changeable along with time, and the smoothness is poor, but in the prior art, the state of the high-voltage circuit breaker is monitored and early-warned usually by adopting a traditional machine learning method, for example, a prediction model is obtained by adopting batch learning or offline learning, namely, all training data of the high-voltage circuit breaker are obtained at one time, threshold judgment early-warning is carried out according to the training model, and the model is rarely updated after the construction is completed. However, due to the numerous operating state parameters of the high-voltage circuit breaker, it is impossible to obtain all data at once at the early stage of the establishment of the predictive model, and the prediction accuracy of the predictive model is necessarily insufficient due to the nonlinearity of the operating state data.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a high-voltage breaker state monitoring and early warning system based on online learning, which has the advantages of simple system structure, reasonable design and convenient realization; by combining a monitoring and early warning method, abnormal state change can be found and reminded by constructing a characteristic vector of the high-voltage circuit breaker and predicting through a model obtained through training; meanwhile, an online learning module is designed, when working state errors obtained by monitoring the working state of the high-voltage circuit breaker and the state monitoring model are large, the monitoring model is updated, so that the monitoring is more comprehensive and complete, and the accuracy is improved. The invention can be effectively applied to the state monitoring of the high-voltage circuit breaker, has good use effect and is convenient for popularization and use.
In order to solve the technical problems, the invention adopts the following technical scheme: a high-voltage circuit breaker state monitoring and early warning system based on online learning comprises a data acquisition module for acquiring operation state parameters of a high-voltage circuit breaker; the timing module records the time for the data acquisition module to acquire the operation state parameters of the high-voltage circuit breaker; the data storage module is used for storing the collected high-voltage breaker operation state parameters and the corresponding collection time; the timing module and the data storage module are connected with the monitoring module; the monitoring module receives the high-voltage circuit breaker operation state parameters acquired by the data acquisition module and the corresponding acquisition time, establishes a feature vector of the high-voltage circuit breaker operation state parameters, and predicts through a model obtained through training; storing the operation state parameters of the high-voltage circuit breaker in a data storage module; the online learning module is connected with the monitoring module and updates the monitoring model; and the operation detection terminal module is connected with the monitoring module and used for receiving and displaying the monitoring result from the monitoring module.
According to the high-voltage circuit breaker state monitoring and early warning system based on online learning, the high-voltage circuit breaker operation state parameters comprise contact operation state parameters and mechanical structure operation state parameters.
According to the high-voltage circuit breaker state monitoring and early warning system based on online learning, the contact working state parameters and the mechanical structure working state parameters comprise original state parameters and newly-added state parameters.
According to the high-voltage circuit breaker state monitoring and early warning system based on online learning, the data acquisition module is arranged on the high-voltage circuit breaker, and the timing module, the data storage module, the monitoring module and the online learning module are all arranged nearby the high-voltage circuit breaker.
According to the high-voltage circuit breaker state monitoring and early warning system based on online learning, the operation detection terminal module is installed in a transformer substation control room.
The invention also discloses a high-voltage circuit breaker state monitoring and early warning method based on online learning, which adopts the system, and comprises the following steps:
step one, collecting training data;
the data acquisition module acquires original state parameters of the high-voltage circuit breaker;
step two, establishing a feature vector;
the monitoring module establishes a characteristic vector according to the original state parameters of the high-voltage circuit breaker and the corresponding acquisition time;
training a monitoring model;
the monitoring module trains the machine learning model according to the feature vector, and builds a state monitoring model of the high-voltage circuit breaker;
step four, periodically picking up and detecting the state of the high-voltage circuit breaker;
the operation and detection personnel periodically and on-site detect the working state of the high-voltage circuit breaker;
step five, updating a data acquisition module;
when the working state error of the high-voltage circuit breaker which is periodically picked and inspected and the working state error obtained by monitoring the state monitoring model are larger, updating the data acquisition module and adding state parameters;
step six, updating the monitoring model;
the online learning module updates the monitoring model according to the original state parameters and the newly added state parameters;
step seven, monitoring and early warning the state of the high-voltage circuit breaker;
and adopting the updated monitoring model to monitor and pre-warn the state of the high-voltage circuit breaker, transmitting the monitoring result to the operation and detection terminal module, and notifying operation and detection personnel.
In the above-mentioned method for monitoring and early warning of high voltage breaker state based on online learning, the specific process of updating the monitoring model by the online learning module according to the original state parameter and the newly added state parameter includes:
step 601, extracting information from original state parameters;
step 602, transferring the extracted information to a new monitoring task;
and 603, updating the monitoring model by combining the newly added state parameters.
The specific process of extracting information from the original state parameters in step 601 is as follows:
wherein L is a Lagrangian function,representing one sample of the original state parameters, N s C is the number of samples of the original state parameter s E R is regularized parameter acting on original state parameter sample, < >>Training error for kth original state parameter sample, w s The output weight of the original monitoring task is obtained.
The specific process of transferring the extracted information to the new monitoring model in step 602 is as follows:
wherein ,representing one sample of the newly added state parameters, N t C is the number of samples of the newly added state parameter t E R is regularization parameter acting on newly added state parameter sample,/E>Training error for kth newly added state parameter sample, w t And (6) outputting weights for new monitoring tasks, wherein mu is a penalty parameter.
In the above-mentioned method for monitoring and early warning of high voltage breaker state based on online learning, in step 602, the specific process of updating the monitoring model by combining the newly added state parameters is as follows:
wherein ,we And outputting the weight for the updated monitoring model.
Compared with the prior art, the invention has the following advantages: the system has the advantages of simple structure, reasonable design and convenient realization; by combining a monitoring and early warning method, abnormal state change can be found and reminded by constructing a characteristic vector of the high-voltage circuit breaker and predicting through a model obtained through training; meanwhile, an online learning module is designed, when working state errors obtained by monitoring the working state of the high-voltage circuit breaker and the state monitoring model are large, the monitoring model is updated, so that the monitoring is more comprehensive and complete, and the accuracy is improved. The invention can be effectively applied to the state monitoring of the high-voltage circuit breaker, has good use effect and is convenient for popularization and use.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a block diagram of the system components of the present invention;
fig. 2 is a flow chart of the method of the present invention.
Reference numerals illustrate:
1-a data acquisition module; 2-a timing module; 3-a data storage module;
4, a monitoring module; 5-an online learning module; and 6, a fortune checking terminal module.
Detailed Description
As shown in FIG. 1, the high-voltage circuit breaker state monitoring and early warning system based on online learning comprises a data acquisition module 1 for acquiring the operation state parameters of the high-voltage circuit breaker; the timing module 2 records the time for the data acquisition module 1 to acquire the operation state parameters of the high-voltage circuit breaker; the data storage module 3 is used for storing the collected high-voltage breaker operation state parameters and the corresponding collection time; the monitoring module 4, the said data acquisition module 1 is connected with input end of the monitoring module 4, the said timing module 2 and data storage module 3 are all connected with monitoring module 4; the monitoring module 4 receives the high-voltage circuit breaker operation state parameters acquired by the data acquisition module 1 and the corresponding acquisition time, establishes a feature vector of the high-voltage circuit breaker operation state parameters, and predicts through a model obtained through training; and storing the high-voltage circuit breaker operation state parameters in the data storage module 3; the online learning module 5 is connected with the monitoring module 4 and updates the monitoring model; and the operation detection terminal module 6 is connected with the monitoring module 4 and receives and displays the monitoring result from the monitoring module 4.
In this embodiment, the operating state parameters of the high-voltage circuit breaker include a contact operating state parameter and a mechanical structure operating state parameter.
In specific implementation, the operating state parameters of the high-voltage circuit breaker are numerous, such as the operating state parameters of the contact include time characteristics, speed characteristics, breaking characteristics and gas characteristics; the working state parameters of the mechanical structure comprise abrasion degree, looseness, deformation and the like.
In this embodiment, the contact working state parameter and the mechanical structure working state parameter both include an original state parameter and an added state parameter.
In the specific implementation, the operating state parameters of the high-voltage circuit breaker are numerous, different parameters need to be acquired by using different sensors, the data acquisition is not realistic, too many data types are unfavorable for training and establishing a monitoring model, therefore, partial parameters with larger influence on the operation of the high-voltage circuit breaker are generally selected for acquisition, and the state parameters acquired by initially establishing the monitoring model are used as the original state parameters; when the accuracy of the initially established monitoring model is reduced along with the accumulation of time, the running state parameters of the high-voltage circuit breaker need to be increased to improve the monitoring accuracy, and the newly increased parameters are used as newly increased state parameters.
In this embodiment, the data acquisition module 1 is installed on a high-voltage circuit breaker, and the timing module 2, the data storage module 3, the monitoring module 4 and the online learning module 5 are all installed near the high-voltage circuit breaker.
In specific implementation, the data acquisition module 1 comprises a plurality of types of sensors installed on a high-voltage circuit breaker, and the timing module 2, the data storage module 3, the monitoring module 4 and the online learning module 5 are installed in a box in a concentrated manner.
In this embodiment, the operation detection terminal module 6 is installed in a substation control room.
In specific implementation, the operation and detection terminal module 6 is installed in a substation control room, so that operation and detection personnel can conveniently watch the operation and detection terminal module.
As shown in fig. 2, the high-voltage circuit breaker state monitoring and early warning method based on online learning of the invention comprises the following steps:
step one, collecting training data;
the data acquisition module 1 acquires original state parameters of the high-voltage circuit breaker;
step two, establishing a feature vector;
the monitoring module 4 establishes a characteristic vector according to the original state parameters of the high-voltage circuit breaker and the corresponding acquisition time;
training a monitoring model;
the monitoring module 4 trains the machine learning model according to the feature vector, and builds a state monitoring model of the high-voltage circuit breaker;
step four, periodically picking up and detecting the state of the high-voltage circuit breaker;
the operation and detection personnel periodically and on-site detect the working state of the high-voltage circuit breaker;
step five, updating the data acquisition module 1;
when the working state error of the high-voltage circuit breaker which is periodically picked and inspected and the working state error obtained by monitoring the state monitoring model are larger, updating the data acquisition module 1 and adding state parameters newly;
in specific implementation, when the accuracy of the initially established monitoring model is reduced along with the accumulation of time, new operating state parameters of the high-voltage circuit breaker need to be added to improve the monitoring accuracy, for example, when the monitoring model is initially established, the data acquisition module 1 acquires time characteristics of contacts, abrasion of mechanical structures and the like, and when the working state error between the periodically acquired high-voltage circuit breaker working state and the working state obtained by monitoring the state monitoring model is larger, a sensor can be additionally arranged to increase the working state parameters of the high-voltage circuit breaker, such as electrical characteristics, vibration characteristics and the like.
Step six, updating the monitoring model;
the online learning module 5 updates the monitoring model according to the original state parameters and the newly added state parameters;
in the specific implementation, the online learning module 5 updates the monitoring model according to the original state parameters and the newly added state parameters, so that the model update is very efficient, and a large amount of time can be saved; whereas conventional offline learning requires training the model from scratch based on all current data, which is equivalent to discarding the original state parameters.
Step seven, monitoring and early warning the state of the high-voltage circuit breaker;
and adopting the updated monitoring model to monitor and pre-warn the state of the high-voltage circuit breaker, transmitting the monitoring result to the operation and detection terminal module 6, and notifying operation and detection personnel.
In this embodiment, the specific process of updating the monitoring model by the online learning module 5 according to the original state parameter and the newly added state parameter in the sixth step includes:
step 601, extracting information from original state parameters;
step 602, transferring the extracted information to a new monitoring task;
and 603, updating the monitoring model by combining the newly added state parameters.
In this embodiment, the specific process of extracting information from the original state parameters in step 601 is as follows:
wherein L is a Lagrangian function,representing one sample of the original state parameters, N s C is the number of samples of the original state parameter s E R is regularized parameter acting on original state parameter sample, < >>Training error for kth original state parameter sample, w s The output weight of the original monitoring task is obtained.
In this embodiment, the specific process of transferring the extracted information to the new monitoring model in step 602 is as follows:
wherein ,representing one sample of the newly added state parameters, N t C is the number of samples of the newly added state parameter t E R is regularization parameter acting on newly added state parameter sample,/E>Training error for kth newly added state parameter sample, w t And (6) outputting weights for new monitoring tasks, wherein mu is a penalty parameter.
In this embodiment, in step 602, the specific process of updating the monitoring model is as follows:
wherein ,we And outputting the weight for the updated monitoring model.
In specific implementation, the output weight is obtained through least square solution of the minimum norm.
The foregoing description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and any simple modification, variation and equivalent structural changes made to the above embodiment according to the technical substance of the present invention still fall within the scope of the technical solution of the present invention.
Claims (5)
1. A high-voltage circuit breaker state monitoring and early warning method based on online learning adopts a monitoring and early warning system, wherein the system comprises a data acquisition module for acquiring the operation state parameters of the high-voltage circuit breaker; the timing module records the time for the data acquisition module to acquire the operation state parameters of the high-voltage circuit breaker; the data storage module is used for storing the collected high-voltage breaker operation state parameters and the corresponding collection time; the timing module and the data storage module are connected with the monitoring module; the monitoring module receives the high-voltage circuit breaker operation state parameters acquired by the data acquisition module and the corresponding acquisition time, establishes a feature vector of the high-voltage circuit breaker operation state parameters, and predicts through a model obtained through training; storing the operation state parameters of the high-voltage circuit breaker in a data storage module; the online learning module is connected with the monitoring module and updates the monitoring model; the operation detection terminal module is connected with the monitoring module and used for receiving and displaying the monitoring result from the monitoring module; characterized in that the method comprises the steps of:
step one, collecting training data;
the data acquisition module acquires original state parameters of the high-voltage circuit breaker;
step two, establishing a feature vector;
the monitoring module establishes a characteristic vector according to the original state parameters of the high-voltage circuit breaker and the corresponding acquisition time;
training a monitoring model;
the monitoring module trains the machine learning model according to the feature vector, and builds a state monitoring model of the high-voltage circuit breaker;
step four, periodically picking up and detecting the state of the high-voltage circuit breaker;
the operation and detection personnel periodically and on-site detect the working state of the high-voltage circuit breaker;
step five, updating a data acquisition module;
when the working state error of the high-voltage circuit breaker which is periodically picked and inspected and the working state error obtained by monitoring the state monitoring model are larger, updating the data acquisition module and adding state parameters;
step six, updating the monitoring model;
the online learning module updates the monitoring model according to the original state parameter and the newly added state parameter, and specifically comprises the following steps:
step 601, extracting information from original state parameters;
wherein L is a Lagrangian function,representing one sample of the original state parameters, N s C is the number of samples of the original state parameter s E R is regularized parameter acting on original state parameter sample, < >>Training error for kth original state parameter sample, w s The output weight of the original monitoring task is given;
step 602, transferring the extracted information to a new monitoring task;
wherein ,representing one sample of the newly added state parameters, N t C is the number of samples of the newly added state parameter t E R is regularization parameter acting on newly added state parameter sample,/E>Training error for kth newly added state parameter sample, w t The output weight of the new monitoring task is given, and mu is a punishment parameter;
step 603, updating the monitoring model by combining the newly added state parameters;
wherein ,we The output weight of the updated monitoring model is obtained;
step seven, monitoring and early warning the state of the high-voltage circuit breaker;
and adopting the updated monitoring model to monitor and pre-warn the state of the high-voltage circuit breaker, transmitting the monitoring result to the operation and detection terminal module, and notifying operation and detection personnel.
2. The high-voltage circuit breaker state monitoring and early warning method based on online learning according to claim 1 is characterized in that: the high-voltage circuit breaker operating state parameters comprise contact operating state parameters and mechanical structure operating state parameters.
3. The high-voltage circuit breaker state monitoring and early warning method based on online learning according to claim 2 is characterized in that: the contact working state parameters and the mechanical structure working state parameters comprise original state parameters and newly-added state parameters.
4. The high-voltage circuit breaker state monitoring and early warning method based on online learning according to claim 1 is characterized in that: the data acquisition module is installed on the high-voltage circuit breaker, and the timing module, the data storage module, the monitoring module and the online learning module are all installed near the high-voltage circuit breaker.
5. The high-voltage circuit breaker state monitoring and early warning method based on online learning according to claim 1 is characterized in that: and the operation detection terminal module is arranged in a transformer substation control room.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009459.2A CN114355184B (en) | 2022-01-05 | 2022-01-05 | Online learning-based high-voltage circuit breaker state monitoring and early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009459.2A CN114355184B (en) | 2022-01-05 | 2022-01-05 | Online learning-based high-voltage circuit breaker state monitoring and early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114355184A CN114355184A (en) | 2022-04-15 |
| CN114355184B true CN114355184B (en) | 2023-09-26 |
Family
ID=81108084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210009459.2A Active CN114355184B (en) | 2022-01-05 | 2022-01-05 | Online learning-based high-voltage circuit breaker state monitoring and early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114355184B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103487749A (en) * | 2013-09-18 | 2014-01-01 | 国家电网公司 | On-line monitoring and diagnosing system and method for mechanical state of high-voltage circuit breaker |
| CN106019138A (en) * | 2016-07-25 | 2016-10-12 | 深圳供电局有限公司 | Online diagnosis method for mechanical fault of high-voltage circuit breaker |
| CN109270442A (en) * | 2018-08-21 | 2019-01-25 | 西安工程大学 | High-voltage circuitbreaker fault detection method based on DBN-GA neural network |
| CN109858553A (en) * | 2019-01-31 | 2019-06-07 | 深圳市赛梅斯凯科技有限公司 | Monitoring model update method, updating device and the storage medium of driving condition |
| CN110308396A (en) * | 2019-07-03 | 2019-10-08 | 华人运通(江苏)技术有限公司 | Battery status monitoring method, edge processor, system and storage medium |
| CN111612128A (en) * | 2020-05-14 | 2020-09-01 | 国网江苏省电力有限公司电力科学研究院 | Active early warning method and device for SF6 high-voltage circuit breaker state |
| CN111680848A (en) * | 2020-07-27 | 2020-09-18 | 中南大学 | Battery life prediction method based on prediction model fusion and storage medium |
| CN112200032A (en) * | 2020-09-28 | 2021-01-08 | 辽宁石油化工大学 | Attention mechanism-based high-voltage circuit breaker mechanical state online monitoring method |
| CN112611936A (en) * | 2020-11-27 | 2021-04-06 | 云南大学 | Distribution network transformer fault dynamic detection and classification system based on edge calculation |
| CN113009212A (en) * | 2021-01-29 | 2021-06-22 | 上海工程技术大学 | System and method for intelligently monitoring state of lightning arrester of power distribution network based on Internet of things |
| CN113341347A (en) * | 2021-06-02 | 2021-09-03 | 云南大学 | Dynamic fault detection method for distribution transformer based on AOELM |
| EP3876061A1 (en) * | 2020-03-06 | 2021-09-08 | Robert Bosch GmbH | Method for validation and selection on machine learning based models for monitoring the state of a machine |
-
2022
- 2022-01-05 CN CN202210009459.2A patent/CN114355184B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103487749A (en) * | 2013-09-18 | 2014-01-01 | 国家电网公司 | On-line monitoring and diagnosing system and method for mechanical state of high-voltage circuit breaker |
| CN106019138A (en) * | 2016-07-25 | 2016-10-12 | 深圳供电局有限公司 | Online diagnosis method for mechanical fault of high-voltage circuit breaker |
| CN109270442A (en) * | 2018-08-21 | 2019-01-25 | 西安工程大学 | High-voltage circuitbreaker fault detection method based on DBN-GA neural network |
| CN109858553A (en) * | 2019-01-31 | 2019-06-07 | 深圳市赛梅斯凯科技有限公司 | Monitoring model update method, updating device and the storage medium of driving condition |
| CN110308396A (en) * | 2019-07-03 | 2019-10-08 | 华人运通(江苏)技术有限公司 | Battery status monitoring method, edge processor, system and storage medium |
| EP3876061A1 (en) * | 2020-03-06 | 2021-09-08 | Robert Bosch GmbH | Method for validation and selection on machine learning based models for monitoring the state of a machine |
| CN111612128A (en) * | 2020-05-14 | 2020-09-01 | 国网江苏省电力有限公司电力科学研究院 | Active early warning method and device for SF6 high-voltage circuit breaker state |
| CN111680848A (en) * | 2020-07-27 | 2020-09-18 | 中南大学 | Battery life prediction method based on prediction model fusion and storage medium |
| CN112200032A (en) * | 2020-09-28 | 2021-01-08 | 辽宁石油化工大学 | Attention mechanism-based high-voltage circuit breaker mechanical state online monitoring method |
| CN112611936A (en) * | 2020-11-27 | 2021-04-06 | 云南大学 | Distribution network transformer fault dynamic detection and classification system based on edge calculation |
| CN113009212A (en) * | 2021-01-29 | 2021-06-22 | 上海工程技术大学 | System and method for intelligently monitoring state of lightning arrester of power distribution network based on Internet of things |
| CN113341347A (en) * | 2021-06-02 | 2021-09-03 | 云南大学 | Dynamic fault detection method for distribution transformer based on AOELM |
Non-Patent Citations (1)
| Title |
|---|
| 融合实测数据的配网断路器投切暂态过电压建模方法;袁涛 等;高电压技术;第47卷(第05期);1555-1565 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114355184A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109765883A (en) | Distribution power automation terminal evaluation of running status and method for diagnosing faults | |
| CN111669123B (en) | Method and device for fault diagnosis of photovoltaic string | |
| CN112069930A (en) | Vibration signal processing method and device for improving GIS equipment fault diagnosis accuracy | |
| CN108418304B (en) | Transformer substation secondary circuit state monitoring method, device and system | |
| CN112884070A (en) | High-voltage switch fault diagnosis method based on transfer learning | |
| CN115343623B (en) | Online detection method and device for faults of electrochemical energy storage battery | |
| CN115544140A (en) | Photovoltaic power station performance detection system and method based on artificial intelligence | |
| CN116029699A (en) | Power information system based on data twinning and operation and maintenance method | |
| CN114370380A (en) | Wind turbine generator fault diagnosis method considering meteorological factors | |
| CN115877198A (en) | Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation | |
| CN114355184B (en) | Online learning-based high-voltage circuit breaker state monitoring and early warning method | |
| CN114821852A (en) | Power grid defect depth identification inspection robot control system based on characteristic pyramid | |
| CN114215705A (en) | Wind turbine generator fault early warning method and system | |
| CN114154728A (en) | Fault prediction method and device, electronic equipment and storage medium | |
| CN112129893B (en) | Online calibration method for CO sensor of battery thermal runaway monitoring system | |
| CN116614177B (en) | Optical fiber state multidimensional parameter monitoring system | |
| Brown et al. | Learning models of plant behavior for anomaly detection and condition monitoring | |
| CN113256959A (en) | Industrial data acquisition terminal test system | |
| CN115632379A (en) | Multi-way detection arc light protection system for vcs isolating switch box | |
| CN115270982A (en) | Switch cabinet fault prediction method based on multi-data neural network | |
| CN114114001A (en) | GIS equipment disconnecting switch mechanical state monitoring method and system | |
| CN114035032A (en) | Airplane alternating current contactor full-life experiment platform and characteristic parameter extraction method | |
| JP7158187B2 (en) | POWER SYSTEM MONITORING DEVICE AND POWER SYSTEM MONITORING METHOD | |
| CN112883639A (en) | GIS equipment service life prediction device and method based on machine learning | |
| CN115277079B (en) | Power terminal information attack monitoring method and system |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ge Lei Inventor after: Zhang Yu Inventor after: Ding Shuyin Inventor after: Wang Ting Inventor after: Wan Xinqiang Inventor after: Li Xiaomeng Inventor after: Zhu Jianwei Inventor after: Xu Cheng Inventor after: Wang Dangbang Inventor after: Wu Mingxi Inventor after: Tang Qian Inventor after: Hu Hongsheng Inventor before: Ge Lei Inventor before: Wang Ting Inventor before: Xu Cheng Inventor before: Zhu Jianwei |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |