Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-Encoder
With the increasing integration of non-linear electronic loads, the diagnosis and classification of power quality are becoming crucial for power grid signal management. This paper presents a novel diagnosis strategy based on unsupervised learning, namely residual denoising convolutional auto-encoder...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/16/7637 |
| _version_ | 1797524715316707328 |
|---|---|
| author | Jie Liu Qiu Tang Wei Qiu Jun Ma Yuhong Qin Biao Sun |
| author_facet | Jie Liu Qiu Tang Wei Qiu Jun Ma Yuhong Qin Biao Sun |
| author_sort | Jie Liu |
| collection | DOAJ |
| description | With the increasing integration of non-linear electronic loads, the diagnosis and classification of power quality are becoming crucial for power grid signal management. This paper presents a novel diagnosis strategy based on unsupervised learning, namely residual denoising convolutional auto-encoder (RDCA), which extracts features from the complex power quality disturbances (PQDs) automatically. Firstly, the time–frequency analysis is applied to isolate frequency domain information. Then, the RDCA with a weight residual structure is utilized to extract the useful features in the contaminated PQD data, where the performance is improved using the residual structure. A single-layer convolutional neural network (SCNN) with an added batch normalization layer is proposed to classify the features. Furthermore, combining with RDCA and SCNN, we further propose a classification framework to classify complex PQDs. To provide a reasonable interpretation of the RDCA, visual analysis is employed to gain insight into the model, leading to a better understanding of the features from different layers. The simulation and experimental tests are conducted to verify the practicability and robustness of the RDCA. |
| first_indexed | 2024-03-10T09:01:09Z |
| format | Article |
| id | doaj.art-3840c89ea9b74b2e9e1e69d7959fc389 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T09:01:09Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3840c89ea9b74b2e9e1e69d7959fc3892023-11-22T06:44:41ZengMDPI AGApplied Sciences2076-34172021-08-011116763710.3390/app11167637Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-EncoderJie Liu0Qiu Tang1Wei Qiu2Jun Ma3Yuhong Qin4Biao Sun5College of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaWith the increasing integration of non-linear electronic loads, the diagnosis and classification of power quality are becoming crucial for power grid signal management. This paper presents a novel diagnosis strategy based on unsupervised learning, namely residual denoising convolutional auto-encoder (RDCA), which extracts features from the complex power quality disturbances (PQDs) automatically. Firstly, the time–frequency analysis is applied to isolate frequency domain information. Then, the RDCA with a weight residual structure is utilized to extract the useful features in the contaminated PQD data, where the performance is improved using the residual structure. A single-layer convolutional neural network (SCNN) with an added batch normalization layer is proposed to classify the features. Furthermore, combining with RDCA and SCNN, we further propose a classification framework to classify complex PQDs. To provide a reasonable interpretation of the RDCA, visual analysis is employed to gain insight into the model, leading to a better understanding of the features from different layers. The simulation and experimental tests are conducted to verify the practicability and robustness of the RDCA.https://www.mdpi.com/2076-3417/11/16/7637automatic extracted featurespower quality disturbancesresidual denoising convolutional auto-encodersingle-layer convolutional neural network |
| spellingShingle | Jie Liu Qiu Tang Wei Qiu Jun Ma Yuhong Qin Biao Sun Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-Encoder Applied Sciences automatic extracted features power quality disturbances residual denoising convolutional auto-encoder single-layer convolutional neural network |
| title | Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-Encoder |
| title_full | Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-Encoder |
| title_fullStr | Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-Encoder |
| title_full_unstemmed | Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-Encoder |
| title_short | Automatic Power Quality Disturbance Diagnosis Based on Residual Denoising Convolutional Auto-Encoder |
| title_sort | automatic power quality disturbance diagnosis based on residual denoising convolutional auto encoder |
| topic | automatic extracted features power quality disturbances residual denoising convolutional auto-encoder single-layer convolutional neural network |
| url | https://www.mdpi.com/2076-3417/11/16/7637 |
| work_keys_str_mv | AT jieliu automaticpowerqualitydisturbancediagnosisbasedonresidualdenoisingconvolutionalautoencoder AT qiutang automaticpowerqualitydisturbancediagnosisbasedonresidualdenoisingconvolutionalautoencoder AT weiqiu automaticpowerqualitydisturbancediagnosisbasedonresidualdenoisingconvolutionalautoencoder AT junma automaticpowerqualitydisturbancediagnosisbasedonresidualdenoisingconvolutionalautoencoder AT yuhongqin automaticpowerqualitydisturbancediagnosisbasedonresidualdenoisingconvolutionalautoencoder AT biaosun automaticpowerqualitydisturbancediagnosisbasedonresidualdenoisingconvolutionalautoencoder |