Optimization of cable fault recognition system using particle swarm optimization
In this paper, a Partial Discharge (PD) based cable fault recognition system has been constructed using Artificial Neural Network (ANN), Support Vector Machine (SVM) and Adaptive Neuro Fuzzy Inference System (ANFIS). The cable fault recognition system can perform well under noise free condition but...
Saved in:
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
World Academy of Research in Science and Engineering
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In this paper, a Partial Discharge (PD) based cable fault recognition system has been constructed using Artificial Neural Network (ANN), Support Vector Machine (SVM) and Adaptive Neuro Fuzzy Inference System (ANFIS). The cable fault recognition system can perform well under noise free condition but endures performance deterioration when PD noise contamination is present. Particle Swarm Optimization (PSO) was used to enhance the performance of classifiers under noise contamination. A performance review has been done to compare the optimized and unoptimized cable fault recognition under noise contamination. Results show that PSO optimized cable fault recognition systems perform better compared to unoptimized cable fault recognition systems. Among the optimized cable fault recognition systems, ANN outperforms SVM and ANFIS. � 2020, World Academy of Research in Science and Engineering. All rights reserved. |
|---|