Utilizing different types of deep learning models for classification of series arc in photovoltaics systems
In this paper, a new hybrid method of change detection and classification is proposed for precise detection and classification of series arc faults (SAFs) in photovoltaic systems. An artificial neural network (ANN) structure is applied for change detection at the first stage, which is then incorpora...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier Ltd
2021
|
| Subjects: |
| _version_ | 1796865804586713088 |
|---|---|
| author | Omran, Alaa Hamza Mat Said, Dalila Hussin, Siti Maherah Abdulhussain, Sadiq H. Samet, Haidar |
| author_facet | Omran, Alaa Hamza Mat Said, Dalila Hussin, Siti Maherah Abdulhussain, Sadiq H. Samet, Haidar |
| author_sort | Omran, Alaa Hamza |
| collection | ePrints |
| description | In this paper, a new hybrid method of change detection and classification is proposed for precise detection and classification of series arc faults (SAFs) in photovoltaic systems. An artificial neural network (ANN) structure is applied for change detection at the first stage, which is then incorporated together with four different convolutional neural network (CNN) models with various dimensions as classifiers for the discrimination of SAFs at the second stage. The models used in the proposed method are 1D CNN, 2D CNN, 3D CNN, and 2D-based images. A comparison of the proposed approach and the state-of-the-art methods has been carried out in terms of accuracy and computational complexity. For a thorough evaluation of the proposed method's performance, studies have been conducted in both simulation and practice, considering various possible scenarios which may emerge. To such an aim, alongside the records from actual measurements in practice, nine models of SAF are also employed for simulation. The results show that the proposed method satisfies principle criteria such as reliability, fault classification error, overfitting, and vanishing solutions. |
| first_indexed | 2024-03-05T21:02:40Z |
| format | Article |
| id | utm.eprints-94348 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T21:02:40Z |
| publishDate | 2021 |
| publisher | Elsevier Ltd |
| record_format | dspace |
| spelling | utm.eprints-943482022-03-31T15:34:30Z http://eprints.utm.my/94348/ Utilizing different types of deep learning models for classification of series arc in photovoltaics systems Omran, Alaa Hamza Mat Said, Dalila Hussin, Siti Maherah Abdulhussain, Sadiq H. Samet, Haidar TK Electrical engineering. Electronics Nuclear engineering In this paper, a new hybrid method of change detection and classification is proposed for precise detection and classification of series arc faults (SAFs) in photovoltaic systems. An artificial neural network (ANN) structure is applied for change detection at the first stage, which is then incorporated together with four different convolutional neural network (CNN) models with various dimensions as classifiers for the discrimination of SAFs at the second stage. The models used in the proposed method are 1D CNN, 2D CNN, 3D CNN, and 2D-based images. A comparison of the proposed approach and the state-of-the-art methods has been carried out in terms of accuracy and computational complexity. For a thorough evaluation of the proposed method's performance, studies have been conducted in both simulation and practice, considering various possible scenarios which may emerge. To such an aim, alongside the records from actual measurements in practice, nine models of SAF are also employed for simulation. The results show that the proposed method satisfies principle criteria such as reliability, fault classification error, overfitting, and vanishing solutions. Elsevier Ltd 2021-12 Article PeerReviewed Omran, Alaa Hamza and Mat Said, Dalila and Hussin, Siti Maherah and Abdulhussain, Sadiq H. and Samet, Haidar (2021) Utilizing different types of deep learning models for classification of series arc in photovoltaics systems. Computers and Electrical Engineering, 96 . ISSN 0045-7906 http://dx.doi.org/10.1016/j.compeleceng.2021.107478 DOI:10.1016/j.compeleceng.2021.107478 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Omran, Alaa Hamza Mat Said, Dalila Hussin, Siti Maherah Abdulhussain, Sadiq H. Samet, Haidar Utilizing different types of deep learning models for classification of series arc in photovoltaics systems |
| title | Utilizing different types of deep learning models for classification of series arc in photovoltaics systems |
| title_full | Utilizing different types of deep learning models for classification of series arc in photovoltaics systems |
| title_fullStr | Utilizing different types of deep learning models for classification of series arc in photovoltaics systems |
| title_full_unstemmed | Utilizing different types of deep learning models for classification of series arc in photovoltaics systems |
| title_short | Utilizing different types of deep learning models for classification of series arc in photovoltaics systems |
| title_sort | utilizing different types of deep learning models for classification of series arc in photovoltaics systems |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| work_keys_str_mv | AT omranalaahamza utilizingdifferenttypesofdeeplearningmodelsforclassificationofseriesarcinphotovoltaicssystems AT matsaiddalila utilizingdifferenttypesofdeeplearningmodelsforclassificationofseriesarcinphotovoltaicssystems AT hussinsitimaherah utilizingdifferenttypesofdeeplearningmodelsforclassificationofseriesarcinphotovoltaicssystems AT abdulhussainsadiqh utilizingdifferenttypesofdeeplearningmodelsforclassificationofseriesarcinphotovoltaicssystems AT samethaidar utilizingdifferenttypesofdeeplearningmodelsforclassificationofseriesarcinphotovoltaicssystems |