Evaluation of Artificial Intelligence Techniques for Fault Type Identification in Advanced Series Compensated Transmission Lines

ABSTRACT

In this paper, two well-known artificial intelligence techniques, artificial neural network (ANN) and upport vector machine (SVM) have been modelled for fault type classification for a transmission line equipped with thyristor controlled series compensator (TCSC) to compare their performance. Due to the non-linear changes introduced by the compensation devices, protection of the series compensated transmission line has been a difficult task. The problem is still complex for advanced series compensated transmission lines. The relaying procedure for a compensated transmission line usually involves fault type identification and fault section identification to conclude for the final decision. The algorithm modelled in this paper has been devised on the analysis of a half cycle post-fault current signals, with the help of discrete wavelet transform as a feature extraction tool. The training and testing of ANN and SVM have been performed with an identical fault data set for comparison. The accuracy of the classifiers had been tested with a large number of fault cases encircling different system conditions and fault conditions. These system conditions are simulated on Power System Computer Aided Design/ElectroMagnetic Transients Program (PSCAD/EMTP) with variation in system parameters such as change in firing angle of TCSC, fault resistance, fault inception angle, loading angle of generator, and source impedance variation for all 10 types of faults. The classifiers are compared in detail with their performance at various firing angles of TCSC and for different fault types.

Keywords::

• Fault type identification
• TCSC
• Series compensated transmission line
• Support vector machine
• Artificial neural network

Additional information

Notes on contributors

Bhargav Vyas

Bhargav Y. Vyas is pursuing a PhD degree in electrical engineering from Indian Institute of Technology, Roorkee, India. He is an Associate Professor in the Department of Electrical Engineering, Government Engineering College, Rajkot, India. His research interests include power system protection, flexible ac transmission system (FACTS), system modelling, simulation, and artificial intelligence.

E-mail: [email protected]

Rudra Prakash Maheshwari

R. P. Maheshwari was born in Aligarh, India, in 1960. He received the BE and MSc (Engg) degrees in electrical engineering from AMU Aligarh, India, in 1982 and 1985, respectively. He received the PhD degree from the University of Roorkee in 1996 for his work on developments in protective relays. Since 1998, he has been an academic staff member with AMU Aligarh. He is presently a Professor with the Department of Electrical Engineering, IIT Roorkee, India. He has published more than 125 research papers in various International/National Journals and conferences. His areas of interest are power system protection, developments in digital protective relay, protective relay testing, industrial automation and image processing. Dr Maheshwari has been awarded merit certificates for his papers by Institution of Engineers (India) and is a member of various professional societies. He is also on the panel of reviewers for various international journals in the area of power systems. He is involved in providing consultancies in the area of small hydro power plants.

Biswarup Das

Biswarup Das (M’02) was born in 1966 in India. He received a PhD degree in electrical engineering from the Indian Institute of Technology, Kanpur, India, in 1998, with a specialization in electric power systems. Currently, he is a Professor in the Department of Electrical Engineering, Indian Institute of Technology, Roorkee, India. His research interest includes power system protection, distribution automation, flexible transmission systems (FACTS), and power system harmonics.

E-mail: [email protected].