Prediction of flashover voltage of contaminated insulator using artificial neural networks
Insulator contamination has been identified as the most important factor in the design of external insulation of high voltage transmission, sub-transmission and distribution systems throughout the world. In the electrical design of high voltage insulators, the design engineers need a simple and reli...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Taylor & Francis
2006
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/9041/ |
| _version_ | 1848891797890138112 |
|---|---|
| author | Alawi, Saleh Al Salam, M. A. Maqrashi, A. A. Ahmad, Hussein |
| author_facet | Alawi, Saleh Al Salam, M. A. Maqrashi, A. A. Ahmad, Hussein |
| author_sort | Alawi, Saleh Al |
| building | UTeM Institutional Repository |
| collection | Online Access |
| description | Insulator contamination has been identified as the most important factor in the design of external insulation of high voltage transmission, sub-transmission and distribution systems throughout the world. In the electrical design of high voltage insulators, the design engineers need a simple and reliable tool when calculating the flashover voltages of contaminated insulators. This article presents an artificial neural network (ANN) based technique that predicts the flashover voltages of the insulator under contaminated conditions energized by AC voltage. The results indicate strong agreement between the model prediction and observed values. The statistical analysis shows that the R 2 value for the sixteen cases in the training set was 0.9986. These results demonstrate that the ANN-based model developed in this work can predict the flashover voltage and ESDD, before and after applying a mitigation system, with 99.86% accuracy and with 99.3%, respectively. It was also found that the contribution of the salinity level was approximately 46.51%; the effect of the solution current was 31.78%, while the remaining 21.71% was attributed to the resistivity. These results clearly indicate that salinity is an important factor in determining ESDD and FOV, and its level should be determined carefully. |
| first_indexed | 2025-11-15T21:03:41Z |
| format | Article |
| id | utm-9041 |
| institution | Universiti Teknologi Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T21:03:41Z |
| publishDate | 2006 |
| publisher | Taylor & Francis |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utm-90412018-03-07T21:10:38Z http://eprints.utm.my/9041/ Prediction of flashover voltage of contaminated insulator using artificial neural networks Alawi, Saleh Al Salam, M. A. Maqrashi, A. A. Ahmad, Hussein TK Electrical engineering. Electronics Nuclear engineering Insulator contamination has been identified as the most important factor in the design of external insulation of high voltage transmission, sub-transmission and distribution systems throughout the world. In the electrical design of high voltage insulators, the design engineers need a simple and reliable tool when calculating the flashover voltages of contaminated insulators. This article presents an artificial neural network (ANN) based technique that predicts the flashover voltages of the insulator under contaminated conditions energized by AC voltage. The results indicate strong agreement between the model prediction and observed values. The statistical analysis shows that the R 2 value for the sixteen cases in the training set was 0.9986. These results demonstrate that the ANN-based model developed in this work can predict the flashover voltage and ESDD, before and after applying a mitigation system, with 99.86% accuracy and with 99.3%, respectively. It was also found that the contribution of the salinity level was approximately 46.51%; the effect of the solution current was 31.78%, while the remaining 21.71% was attributed to the resistivity. These results clearly indicate that salinity is an important factor in determining ESDD and FOV, and its level should be determined carefully. Taylor & Francis 2006 Article PeerReviewed Alawi, Saleh Al and Salam, M. A. and Maqrashi, A. A. and Ahmad, Hussein (2006) Prediction of flashover voltage of contaminated insulator using artificial neural networks. Electric Power Components and Systems, 34 (8). pp. 831-840. ISSN 1532-5008 http://dx.doi.org/10.1080/15325000600561563 10.1080/15325000600561563 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Alawi, Saleh Al Salam, M. A. Maqrashi, A. A. Ahmad, Hussein Prediction of flashover voltage of contaminated insulator using artificial neural networks |
| title | Prediction of flashover voltage of contaminated insulator using artificial neural networks |
| title_full | Prediction of flashover voltage of contaminated insulator using artificial neural networks |
| title_fullStr | Prediction of flashover voltage of contaminated insulator using artificial neural networks |
| title_full_unstemmed | Prediction of flashover voltage of contaminated insulator using artificial neural networks |
| title_short | Prediction of flashover voltage of contaminated insulator using artificial neural networks |
| title_sort | prediction of flashover voltage of contaminated insulator using artificial neural networks |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/9041/ http://eprints.utm.my/9041/ http://eprints.utm.my/9041/ |