Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear
The analysis of partial discharge (PD) signals has been identified as a standard diagnostic tool for monitoring the condition of different electrical apparatuses. This study proposes an approach to detecting PD patterns in gas-insulated switchgear (GIS) using a long short-term memory (LSTM) recurren...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/11/5/1202 |
| _version_ | 1798038271890030592 |
|---|---|
| author | Minh-Tuan Nguyen Viet-Hung Nguyen Suk-Jun Yun Yong-Hwa Kim |
| author_facet | Minh-Tuan Nguyen Viet-Hung Nguyen Suk-Jun Yun Yong-Hwa Kim |
| author_sort | Minh-Tuan Nguyen |
| collection | DOAJ |
| description | The analysis of partial discharge (PD) signals has been identified as a standard diagnostic tool for monitoring the condition of different electrical apparatuses. This study proposes an approach to detecting PD patterns in gas-insulated switchgear (GIS) using a long short-term memory (LSTM) recurrent neural network (RNN). The proposed method uses phase-resolved PD (PRPD) signals as input, extracts low-level features, and finally, classifies faults in GIS. In the proposed method, LSTM networks can learn temporal dependencies directly from PRPD signals. Most existing models use support vector machines (SVMs) and mainly focus on improving feature representation and extraction manually to analyze PRPD signals. However, the proposed model captures important temporal features with the help of its low-level feature extraction capability from raw inputs. It outperforms conventional SVMs and achieves 96.74% classification accuracy for PRPDs in GIS. |
| first_indexed | 2024-04-11T21:37:55Z |
| format | Article |
| id | doaj.art-caa2f4aeca154943a2c59b3ff9855e25 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T21:37:55Z |
| publishDate | 2018-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-caa2f4aeca154943a2c59b3ff9855e252022-12-22T04:01:41ZengMDPI AGEnergies1996-10732018-05-01115120210.3390/en11051202en11051202Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated SwitchgearMinh-Tuan Nguyen0Viet-Hung Nguyen1Suk-Jun Yun2Yong-Hwa Kim3Department of Electronic Engineering, Myongji University, Yongin 449-728, KoreaDepartment of Electronic Engineering, Myongji University, Yongin 449-728, KoreaPrevention Diagnosis Team, Genad System, Naju 58296, KoreaDepartment of Electronic Engineering, Myongji University, Yongin 449-728, KoreaThe analysis of partial discharge (PD) signals has been identified as a standard diagnostic tool for monitoring the condition of different electrical apparatuses. This study proposes an approach to detecting PD patterns in gas-insulated switchgear (GIS) using a long short-term memory (LSTM) recurrent neural network (RNN). The proposed method uses phase-resolved PD (PRPD) signals as input, extracts low-level features, and finally, classifies faults in GIS. In the proposed method, LSTM networks can learn temporal dependencies directly from PRPD signals. Most existing models use support vector machines (SVMs) and mainly focus on improving feature representation and extraction manually to analyze PRPD signals. However, the proposed model captures important temporal features with the help of its low-level feature extraction capability from raw inputs. It outperforms conventional SVMs and achieves 96.74% classification accuracy for PRPDs in GIS.http://www.mdpi.com/1996-1073/11/5/1202fault diagnosisgas-insulated switchgear (GIS)long short-term memory (LSTM)partial dischargesrecurrent neural network (RNN) |
| spellingShingle | Minh-Tuan Nguyen Viet-Hung Nguyen Suk-Jun Yun Yong-Hwa Kim Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear Energies fault diagnosis gas-insulated switchgear (GIS) long short-term memory (LSTM) partial discharges recurrent neural network (RNN) |
| title | Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear |
| title_full | Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear |
| title_fullStr | Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear |
| title_full_unstemmed | Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear |
| title_short | Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear |
| title_sort | recurrent neural network for partial discharge diagnosis in gas insulated switchgear |
| topic | fault diagnosis gas-insulated switchgear (GIS) long short-term memory (LSTM) partial discharges recurrent neural network (RNN) |
| url | http://www.mdpi.com/1996-1073/11/5/1202 |
| work_keys_str_mv | AT minhtuannguyen recurrentneuralnetworkforpartialdischargediagnosisingasinsulatedswitchgear AT viethungnguyen recurrentneuralnetworkforpartialdischargediagnosisingasinsulatedswitchgear AT sukjunyun recurrentneuralnetworkforpartialdischargediagnosisingasinsulatedswitchgear AT yonghwakim recurrentneuralnetworkforpartialdischargediagnosisingasinsulatedswitchgear |