Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques
Partial discharge (PD) diagnostics in Gas Insulated Switchgear (GIS) is important for reliable and secure operation of electrical utilities. Different techniques were used for PD diagnosis in GIS. In this work, PD diagnosis in GIS is proposed based on PD pulse sequence. PD pulse sequence only requir...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2022
|
| _version_ | 1811137595064713216 |
|---|---|
| author | Mansour, Diaa-Eldin A. Taha, Ibrahim B.m. Farade, Rizwan A. Abdul Wahab, Noor Izzri |
| author_facet | Mansour, Diaa-Eldin A. Taha, Ibrahim B.m. Farade, Rizwan A. Abdul Wahab, Noor Izzri |
| author_sort | Mansour, Diaa-Eldin A. |
| collection | UPM |
| description | Partial discharge (PD) diagnostics in Gas Insulated Switchgear (GIS) is important for reliable and secure operation of electrical utilities. Different techniques were used for PD diagnosis in GIS. In this work, PD diagnosis in GIS is proposed based on PD pulse sequence. PD pulse sequence only requires the measurement of PD phase appearance and its corresponding instantaneous voltage. The PD diagnosis of various defect types is implemented using five optimized machine learning classification techniques: decision tree classification, ensemble methods, k-nearest neighbouring, Discriminant analysis, and Naïve Bayes classification. The features used for PD pulse sequence are the voltage change and phase angle change between successive PD pulses. Three scenarios are proposed for predicting the defect types in GIS. The first scenario is built based on the extracted features for two successive PD pulses, the second scenario is built based on the extracted features for three successive PD pulses, while the last scenario is built based on the extracted features for four successive PD pulses. The results illustrate the superior detecting accuracy of the second scenario with the proposed five ML classification techniques. The optimized ML classification techniques are implemented and carried out based on MATLAB software package. The ensemble classification method exhibited the highest accuracy for PD-based diagnosis in GIS with an overall accuracy of 97.1%. |
| first_indexed | 2024-09-25T03:36:47Z |
| format | Article |
| id | upm.eprints-102663 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-09-25T03:36:47Z |
| publishDate | 2022 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | upm.eprints-1026632024-06-29T14:17:00Z http://psasir.upm.edu.my/id/eprint/102663/ Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques Mansour, Diaa-Eldin A. Taha, Ibrahim B.m. Farade, Rizwan A. Abdul Wahab, Noor Izzri Partial discharge (PD) diagnostics in Gas Insulated Switchgear (GIS) is important for reliable and secure operation of electrical utilities. Different techniques were used for PD diagnosis in GIS. In this work, PD diagnosis in GIS is proposed based on PD pulse sequence. PD pulse sequence only requires the measurement of PD phase appearance and its corresponding instantaneous voltage. The PD diagnosis of various defect types is implemented using five optimized machine learning classification techniques: decision tree classification, ensemble methods, k-nearest neighbouring, Discriminant analysis, and Naïve Bayes classification. The features used for PD pulse sequence are the voltage change and phase angle change between successive PD pulses. Three scenarios are proposed for predicting the defect types in GIS. The first scenario is built based on the extracted features for two successive PD pulses, the second scenario is built based on the extracted features for three successive PD pulses, while the last scenario is built based on the extracted features for four successive PD pulses. The results illustrate the superior detecting accuracy of the second scenario with the proposed five ML classification techniques. The optimized ML classification techniques are implemented and carried out based on MATLAB software package. The ensemble classification method exhibited the highest accuracy for PD-based diagnosis in GIS with an overall accuracy of 97.1%. Elsevier 2022 Article PeerReviewed Mansour, Diaa-Eldin A. and Taha, Ibrahim B.m. and Farade, Rizwan A. and Abdul Wahab, Noor Izzri (2022) Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques. Electric Power Systems Research, 211. art. no. 108162. pp. 1-8. ISSN 0378-7796; ESSN: 1873-2046 https://linkinghub.elsevier.com/retrieve/pii/S0378779622003777 10.1016/j.epsr.2022.108162 |
| spellingShingle | Mansour, Diaa-Eldin A. Taha, Ibrahim B.m. Farade, Rizwan A. Abdul Wahab, Noor Izzri Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques |
| title | Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques |
| title_full | Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques |
| title_fullStr | Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques |
| title_full_unstemmed | Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques |
| title_short | Partial discharge diagnosis in GIS based on pulse sequence features and optimized machine learning classification techniques |
| title_sort | partial discharge diagnosis in gis based on pulse sequence features and optimized machine learning classification techniques |
| work_keys_str_mv | AT mansourdiaaeldina partialdischargediagnosisingisbasedonpulsesequencefeaturesandoptimizedmachinelearningclassificationtechniques AT tahaibrahimbm partialdischargediagnosisingisbasedonpulsesequencefeaturesandoptimizedmachinelearningclassificationtechniques AT faraderizwana partialdischargediagnosisingisbasedonpulsesequencefeaturesandoptimizedmachinelearningclassificationtechniques AT abdulwahabnoorizzri partialdischargediagnosisingisbasedonpulsesequencefeaturesandoptimizedmachinelearningclassificationtechniques |