Fault Diagnosis Method of Smart Meters Based on DBN-CapsNet
Rapid and accurate fault diagnosis of smart meters can greatly improve the operational and maintenance ability of power systems. Focusing on the historical fault data information of smart meters, a fault diagnosis model of smart meters based on an improved capsule network (CapsNet) is proposed. Firs...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/10/1603 |
| _version_ | 1797500307841744896 |
|---|---|
| author | Juan Zhou Zonghuan Wu Qiang Wang Zhonghua Yu |
| author_facet | Juan Zhou Zonghuan Wu Qiang Wang Zhonghua Yu |
| author_sort | Juan Zhou |
| collection | DOAJ |
| description | Rapid and accurate fault diagnosis of smart meters can greatly improve the operational and maintenance ability of power systems. Focusing on the historical fault data information of smart meters, a fault diagnosis model of smart meters based on an improved capsule network (CapsNet) is proposed. First, we count the sample size of each fault type, and a mixed sampling method combining undersampling and oversampling is used to solve the problem of distribution imbalance of sample size. The one-hot encoding method is adopted to solve the problem of the fault samples containing more discrete and disordered data. Then, the strong adaptive feature extraction capability and nonlinear mapping capability of the deep belief network (DBN) are utilized to improve the single convolution layer feature extraction part of a traditional capsule network; DBN can also address the problem of high data dimensions and sparse data due to one-hot encoding. The important features and key information of the input sample are extracted and used as the input of the primary capsule layer, and the dynamic routing algorithm is used to construct the digital capsule. Finally, the results of experiments show that the improved capsule network model can effectively improve the accuracy of diagnosis and shorten the training time. |
| first_indexed | 2024-03-10T03:00:01Z |
| format | Article |
| id | doaj.art-78470da445b44c03bf6e40626db398fb |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T03:00:01Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-78470da445b44c03bf6e40626db398fb2023-11-23T10:47:37ZengMDPI AGElectronics2079-92922022-05-011110160310.3390/electronics11101603Fault Diagnosis Method of Smart Meters Based on DBN-CapsNetJuan Zhou0Zonghuan Wu1Qiang Wang2Zhonghua Yu3College of Quality & Safety Engineering, China Jiliang University, Hangzhou 310018, ChinaCollege of Quality & Safety Engineering, China Jiliang University, Hangzhou 310018, ChinaCollege of Quality & Safety Engineering, China Jiliang University, Hangzhou 310018, ChinaSchool of Mechanical Engineering, Zhejiang University, Hangzhou 310027, ChinaRapid and accurate fault diagnosis of smart meters can greatly improve the operational and maintenance ability of power systems. Focusing on the historical fault data information of smart meters, a fault diagnosis model of smart meters based on an improved capsule network (CapsNet) is proposed. First, we count the sample size of each fault type, and a mixed sampling method combining undersampling and oversampling is used to solve the problem of distribution imbalance of sample size. The one-hot encoding method is adopted to solve the problem of the fault samples containing more discrete and disordered data. Then, the strong adaptive feature extraction capability and nonlinear mapping capability of the deep belief network (DBN) are utilized to improve the single convolution layer feature extraction part of a traditional capsule network; DBN can also address the problem of high data dimensions and sparse data due to one-hot encoding. The important features and key information of the input sample are extracted and used as the input of the primary capsule layer, and the dynamic routing algorithm is used to construct the digital capsule. Finally, the results of experiments show that the improved capsule network model can effectively improve the accuracy of diagnosis and shorten the training time.https://www.mdpi.com/2079-9292/11/10/1603capsule networkdeep belief networkfault diagnosissmart meter |
| spellingShingle | Juan Zhou Zonghuan Wu Qiang Wang Zhonghua Yu Fault Diagnosis Method of Smart Meters Based on DBN-CapsNet Electronics capsule network deep belief network fault diagnosis smart meter |
| title | Fault Diagnosis Method of Smart Meters Based on DBN-CapsNet |
| title_full | Fault Diagnosis Method of Smart Meters Based on DBN-CapsNet |
| title_fullStr | Fault Diagnosis Method of Smart Meters Based on DBN-CapsNet |
| title_full_unstemmed | Fault Diagnosis Method of Smart Meters Based on DBN-CapsNet |
| title_short | Fault Diagnosis Method of Smart Meters Based on DBN-CapsNet |
| title_sort | fault diagnosis method of smart meters based on dbn capsnet |
| topic | capsule network deep belief network fault diagnosis smart meter |
| url | https://www.mdpi.com/2079-9292/11/10/1603 |
| work_keys_str_mv | AT juanzhou faultdiagnosismethodofsmartmetersbasedondbncapsnet AT zonghuanwu faultdiagnosismethodofsmartmetersbasedondbncapsnet AT qiangwang faultdiagnosismethodofsmartmetersbasedondbncapsnet AT zhonghuayu faultdiagnosismethodofsmartmetersbasedondbncapsnet |