Classification of Partial Discharge Measured under Different Levels of Noise Contamination
Cable joint insulation breakdown may cause a huge loss to power companies. Therefore, it is vital to diagnose the insulation quality to detect early signs of insulation failure. It is well known that there is a correlation between Partial discharge (PD) and the insulation quality. Although many work...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science
2017
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/19044/1/Classification_of_Partial_Discharge_Measured_under_Different_Levels_of_Noise_Contamination.pdf |
| _version_ | 1825721222721175552 |
|---|---|
| author | Raymond, W.J.K. Illias, Hazlee Azil Bakar, Ab Halim Abu |
| author_facet | Raymond, W.J.K. Illias, Hazlee Azil Bakar, Ab Halim Abu |
| author_sort | Raymond, W.J.K. |
| collection | UM |
| description | Cable joint insulation breakdown may cause a huge loss to power companies. Therefore, it is vital to diagnose the insulation quality to detect early signs of insulation failure. It is well known that there is a correlation between Partial discharge (PD) and the insulation quality. Although many works have been done on PD pattern recognition, it is usually performed in a noise free environment. Also, works on PD pattern recognition in actual cable joint are less likely to be found in literature. Therefore, in this work, classifications of actual cable joint defect types from partial discharge data contaminated by noise were performed. Five crosslinked polyethylene (XLPE) cable joints with artificially created defects were prepared based on the defects commonly encountered on site. Three different types of input feature were extracted from the PD pattern under artificially created noisy environment. These include statistical features, fractal features and principal component analysis (PCA) features. These input features were used to train the classifiers to classify each PD defect types. Classifications were performed using three different artificial intelligence classifiers, which include Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Support Vector Machine (SVM). It was found that the classification accuracy decreases with higher noise level but PCA features used in SVM and ANN showed the strongest tolerance against noise contamination. |
| first_indexed | 2024-03-06T05:47:06Z |
| format | Article |
| id | um.eprints-19044 |
| institution | Universiti Malaya |
| language | English |
| last_indexed | 2024-03-06T05:47:06Z |
| publishDate | 2017 |
| publisher | Public Library of Science |
| record_format | dspace |
| spelling | um.eprints-190442019-12-06T08:39:43Z http://eprints.um.edu.my/19044/ Classification of Partial Discharge Measured under Different Levels of Noise Contamination Raymond, W.J.K. Illias, Hazlee Azil Bakar, Ab Halim Abu TK Electrical engineering. Electronics Nuclear engineering Cable joint insulation breakdown may cause a huge loss to power companies. Therefore, it is vital to diagnose the insulation quality to detect early signs of insulation failure. It is well known that there is a correlation between Partial discharge (PD) and the insulation quality. Although many works have been done on PD pattern recognition, it is usually performed in a noise free environment. Also, works on PD pattern recognition in actual cable joint are less likely to be found in literature. Therefore, in this work, classifications of actual cable joint defect types from partial discharge data contaminated by noise were performed. Five crosslinked polyethylene (XLPE) cable joints with artificially created defects were prepared based on the defects commonly encountered on site. Three different types of input feature were extracted from the PD pattern under artificially created noisy environment. These include statistical features, fractal features and principal component analysis (PCA) features. These input features were used to train the classifiers to classify each PD defect types. Classifications were performed using three different artificial intelligence classifiers, which include Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Support Vector Machine (SVM). It was found that the classification accuracy decreases with higher noise level but PCA features used in SVM and ANN showed the strongest tolerance against noise contamination. Public Library of Science 2017 Article PeerReviewed application/pdf en http://eprints.um.edu.my/19044/1/Classification_of_Partial_Discharge_Measured_under_Different_Levels_of_Noise_Contamination.pdf Raymond, W.J.K. and Illias, Hazlee Azil and Bakar, Ab Halim Abu (2017) Classification of Partial Discharge Measured under Different Levels of Noise Contamination. PLoS ONE, 12 (1). e0170111. ISSN 1932-6203, DOI https://doi.org/10.1371/journal.pone.0170111 <https://doi.org/10.1371/journal.pone.0170111>. http://dx.doi.org/10.1371/journal.pone.0170111 doi:10.1371/journal.pone.0170111 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Raymond, W.J.K. Illias, Hazlee Azil Bakar, Ab Halim Abu Classification of Partial Discharge Measured under Different Levels of Noise Contamination |
| title | Classification of Partial Discharge Measured under Different Levels of Noise Contamination |
| title_full | Classification of Partial Discharge Measured under Different Levels of Noise Contamination |
| title_fullStr | Classification of Partial Discharge Measured under Different Levels of Noise Contamination |
| title_full_unstemmed | Classification of Partial Discharge Measured under Different Levels of Noise Contamination |
| title_short | Classification of Partial Discharge Measured under Different Levels of Noise Contamination |
| title_sort | classification of partial discharge measured under different levels of noise contamination |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.um.edu.my/19044/1/Classification_of_Partial_Discharge_Measured_under_Different_Levels_of_Noise_Contamination.pdf |
| work_keys_str_mv | AT raymondwjk classificationofpartialdischargemeasuredunderdifferentlevelsofnoisecontamination AT illiashazleeazil classificationofpartialdischargemeasuredunderdifferentlevelsofnoisecontamination AT bakarabhalimabu classificationofpartialdischargemeasuredunderdifferentlevelsofnoisecontamination |