Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh
Due to excellent mechanical and electrical properties, cross-linked polyethylene (XLPE) cables are commonly used in the power industry. However, cable joints are the weakest part of XLPE cables and are susceptible to insulation failures. Cable joint insulation breakup can cause large losses for powe...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2020
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/11910/ http://studentsrepo.um.edu.my/11910/1/Muhammad_Shairazi.jpg http://studentsrepo.um.edu.my/11910/8/shairazi.pdf |
| _version_ | 1848774510884421632 |
|---|---|
| author | Muhammad Shairazi , Mohd Salleh |
| author_facet | Muhammad Shairazi , Mohd Salleh |
| author_sort | Muhammad Shairazi , Mohd Salleh |
| building | UM Research Repository |
| collection | Online Access |
| description | Due to excellent mechanical and electrical properties, cross-linked polyethylene (XLPE) cables are commonly used in the power industry. However, cable joints are the weakest part of XLPE cables and are susceptible to insulation failures. Cable joint insulation breakup can cause large losses for power companies. It is therefore necessary to evaluate the consistency of the insulation for early detection of insulation failure. It is known that there is a link between the partial discharge (PD) and the quality of the insulation. PD analysis is an important tool for assessing the quality of insulation in cable joints. In this study, XLPE cable joints with artificial defects, which are commonly found on-site, were prepared. The input data from the PD measurement results were used to train k-nearest neighbor (KNN) algorithm to classify each type of defect in the cable joint samples. Discrete wavelet transform (DWT) was used to denoise the PD signals and denoised PD signals were used to identify different types of defect in cable joints. The extracted input features from the denoised signals were used to train the classifier. Classifications were also carried out using support vector machine (SVM) and artificial neural network (ANN) for comparison with KNN. The performance of each method was evaluated through its accuracy. From the comparison of the results obtained, it was found that the approach for partial discharge of cable joint defect signals using DWT method and classified by KNN yields the highest accuracy among all of the methods tested under different signal-to-noise ratios. |
| first_indexed | 2025-11-14T13:59:27Z |
| format | Thesis |
| id | um-11910 |
| institution | University Malaya |
| institution_category | Local University |
| last_indexed | 2025-11-14T13:59:27Z |
| publishDate | 2020 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | um-119102021-02-08T19:19:04Z Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh Muhammad Shairazi , Mohd Salleh TK Electrical engineering. Electronics Nuclear engineering Due to excellent mechanical and electrical properties, cross-linked polyethylene (XLPE) cables are commonly used in the power industry. However, cable joints are the weakest part of XLPE cables and are susceptible to insulation failures. Cable joint insulation breakup can cause large losses for power companies. It is therefore necessary to evaluate the consistency of the insulation for early detection of insulation failure. It is known that there is a link between the partial discharge (PD) and the quality of the insulation. PD analysis is an important tool for assessing the quality of insulation in cable joints. In this study, XLPE cable joints with artificial defects, which are commonly found on-site, were prepared. The input data from the PD measurement results were used to train k-nearest neighbor (KNN) algorithm to classify each type of defect in the cable joint samples. Discrete wavelet transform (DWT) was used to denoise the PD signals and denoised PD signals were used to identify different types of defect in cable joints. The extracted input features from the denoised signals were used to train the classifier. Classifications were also carried out using support vector machine (SVM) and artificial neural network (ANN) for comparison with KNN. The performance of each method was evaluated through its accuracy. From the comparison of the results obtained, it was found that the approach for partial discharge of cable joint defect signals using DWT method and classified by KNN yields the highest accuracy among all of the methods tested under different signal-to-noise ratios. 2020-05 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/11910/1/Muhammad_Shairazi.jpg application/pdf http://studentsrepo.um.edu.my/11910/8/shairazi.pdf Muhammad Shairazi , Mohd Salleh (2020) Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh. Masters thesis, University Malaya. http://studentsrepo.um.edu.my/11910/ |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Muhammad Shairazi , Mohd Salleh Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh |
| title | Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh |
| title_full | Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh |
| title_fullStr | Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh |
| title_full_unstemmed | Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh |
| title_short | Partial discharge classification for XLPE cable joints using K nearest neighbors algorithm / Muhammad Shairazi Mohd Salleh |
| title_sort | partial discharge classification for xlpe cable joints using k nearest neighbors algorithm / muhammad shairazi mohd salleh |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://studentsrepo.um.edu.my/11910/ http://studentsrepo.um.edu.my/11910/1/Muhammad_Shairazi.jpg http://studentsrepo.um.edu.my/11910/8/shairazi.pdf |