A Hybrid PSO-ANN-based Fault Classification System for EHV Transmission Lines

Abstract

The paper presents a robust design of Artificial Neural Network Classifier used for the classification of faults occurring on Extra High Voltage Transmission lines with multiple series compensation. The feature selection and model parameters play a vital role in providing better accuracy as well as stability of Classifier in recognition of fault patterns. The paper describes the use of Particle Swarm Optimization (PSO)-assisted training of Artificial Neural Network (ANN). The PSO is used to find the optimal number of features to attain sufficiently high accuracy along with optimal design parameters of ANN so as to reduce the computational burden. A combined use of Multiresolution Wavelet Analysis (MRA) and Statistical Features (SF) module is shown for fault pattern analysis. A Particle Swarm optimization based Neural Network with Feature Selection (PSONNFS) Algorithm developed is applied on a large database of fault patterns with a wide range of operating conditions in series compensated system. The best features found from the PSONNFS algorithm are later used to find the optimal structure of ANN. The results obtained provide an enhanced model of ANN with a high degree of accuracy with optimality in Classifier parameters. A Genetic Algorithm based Neural Network optimization with Feature Selection (GANNFS) is also developed to verify the performance of the classifier. The results of the PSONNFS algorithm are further compared with the GANNFS algorithm. The results obtained show an enhanced model of ANN using PSONNFS which has a high degree of accuracy with optimality in Classifier parameters.

KEYWORDS:

• ANN
• EHV transmission line
• Fault classifier
• Feature selection
• Genetic algorithm
• Particle swarm optimization
• Wavelet transform

Additional information

Notes on contributors

Pranav D. Raval

Pranav D Raval received BE in electrical engineering from Saurashtra University, Rajkot, India in 2001, ME (Electrical Power System) from Sardar Patel University, Vallabh Vidyanagar, India in 2004. He is currently working as assistant professor in the Department of Electrical Engineering at LE College, Morbi, India. He is a life time member of ISTE and IAENG. His current research interests include areas like power system protection, artificial intelligence, FACT devices, and digital signal processing. He is a recipient of best Teacher’s Award by CVM, India in 2007.

Ashit S. Pandya

Ashit S Pandya has received BE in electrical engineering from North Gujarat University, Patan, India in 1991, ME in electrical power system from Gujarat University, Ahmedabad, India in 1998 and PhD in electrical engineering from MS University, Baroda, India in 2010. He is currently working as Principal in AVPTI, Engineering College. He has a total experience of 25 years in teaching and 1.5 years in Industry. He is a member of ISTE and IEI organizations. His areas of interest in research includes power system protection, power system control, FACTS. He has received several awards which include (1) Rashtriya Vidya Sarswati Puraskar from IIE&M, New Delhi in 2009. (2) Glory of Education Excellence Award in 2011, New Delhi (3) Golden Educationist of India in 2013, New Delhi (4) Asia Pacific Achievers’ Award in 2014 at Tashkent, Russia, by Indian Solidarity Council, New Delhi. (5) Pedagogical Innovations Award in 2015 from Gujarat Technological University, Ahmedabad. Email: [email protected]