|
Vol.14, No.2, May 2025. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Optimizing the Prediction of Lightning Impulse Withstand Voltage for Glass Insulators Using ANFIS Enhanced with Particle Swarm Optimization (PSO)
Lazreg Taibaoui, Abdelhalim Mahdjoubi, Boubakeur Zegnini
© 2025 Lazreg Taibaoui, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 14, Issue 2, Pages 1725-1732, ISSN 2217-8309, DOI: 10.18421/TEM142-70, May 2025.
Received: 14 October 2024. Revised: 18 April 2025.
Abstract:
High-voltage insulators play a vital role in electric power transmission systems, and their failure can result in significant economic repercussions due to the essential reliance of various industries on uninterrupted power supply. Although extensive research, both experimental and theoretical, has been conducted to understand flashover phenomena in polluted insulators, studies specifically focusing on lightning impulse withstand voltage (LIWV) remain limited. This study introduces a novel hybrid modeling approach combining an Adaptive Neuro-Fuzzy Inference System (ANFIS) with Particle Swarm Optimization (PSO), explicitly designed for applications in high-voltage engineering. The proposed model accurately represents the intricate nonlinear interactions between insulator characteristics and their corresponding LIWV. For the development and validation of this model, experimental datasets were employed, gathered from two distinct types of glass insulators: open-profile and anti-pollution-profile insulators. The performance of the hybrid ANFIS-PSO model was evaluated, yielding remarkable predictive accuracy with a mean absolute percentage error of only 0.2458% and an exceptionally high coefficient of determination (R²=0.99843). These findings underscore the proposed model’s effectiveness and reliability in forecasting lightning impulse withstand voltage for novel insulator designs under diverse environmental conditions.
Keywords – High voltage insulator, particle swarm optimisation, prediction, adaptive neuro-fuzzy inference system (ANFIS), lighting impulse withstand voltage |
|
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |