A Modified Probabilistic Neural Network-based Algorithm for Detecting Turn Faults in Induction Machines

Abstract

In this paper, an intelligent technique for detecting the turn fault and supply voltage unbalances in an induction machine is proposed under varying load conditions. The proposed probabilistic neural network (PNN) technique is based on well-established statistical principles rather than heuristic approaches that are adopted in the multi-layer perceptrons. The PNN is derived from the Bayes decision strategy and nonparametric kernel-based estimators of probability density functions. The machine model is developed for inter-turn short circuit fault and it is compared with its a priori models for its robustness in detecting the fault at incipient stages under various operating conditions of the machine. This algorithm is proposed for first time and training, testing, and validation results using the method appear promising and easily realizable in the industries.

Keywords:

• Entropy
• Incipient
• Induction motors
• Probabilistic neural network
• Supply unbalance
• Varying load

Additional information

Notes on contributors

Jeevanand Seshadrinath

Jeevanand Seshadrinath received the M.Tech degree from Electrical Engineering Department, National Institute of Technology Calicut (NITC), in 2008, and is currently working towards the Ph.D. degree in Electrical Engineering from Indian Institute of Technology Delhi, India. His research topic is on condition monitoring of induction machines and variable frequency drives.

Mr Jeevanand is an active member of Industry Applications Society (IAS) and Industrial Electronics Society (IES). He is an execom member of the IEEE (PES-IAS and PELS-IES) chapters of the IEEE Delhi Section. His areas of interest include electrical machines, condition monitoring and fault diagnosis of drives, signal processing and computational intelligence.

E-mail: [email protected]

Bhim Singh

Bhim Singh received Bachelor of Engineering (Electrical) degree from University of Roorkee, Roorkee, India, in 1977, and M.Tech. (Power Apparatus and Systems) and Ph.D. degrees from Indian Institute of Technology Delhi New Delhi, India, in 1979 and 1983, respectively. In 1983, he joined Department of Electrical Engineering, University of Roorkee, as a Lecturer. He became a Reader there in 1988. In December 1990, he joined Department of Electrical Engineering, IIT Delhi, New Delhi, India, as an Assistant Professor, where he has became an Associate Professor in 1994 and a Professor in 1997.

He has guided 39 Ph.D. dissertations 130 ME/M.Tech theses and 60 BE/B.Tech projects. He has been granted one US patent and filed ten Indian patents. He has executed more than sixty sponsored and consultancy projects. His fields of interest include power electronics, electrical machines, electric drives, power quality, FACTS (Flexible AC Transmission Systems), HVDC (High Voltage Direct Current) transmission systems and renewable energy generation.

Prof. Singh is a Fellow of IEEE(Institute of electrical and electronics engineers) Indian National Academy of Engineering (FNAE), the National Academy of Science, India (FNASc), the Institution of Engineering and Technology (FIET), the Institution of Engineers (India) (FIE), and the Institution of Electronics and Telecommunication Engineers (FIETE).

E-mail: [email protected]

Bijaya Ketan Panigrahi

Bijaya Ketan Panigrahi received the Ph.D. degree from Sambalpur University, Sambalpur, India. Since 2005, he has been an Associate Professor with the Department of Electrical Engineering, Indian Institute of Technology (IIT) Delhi, New Delhi, India. Prior to joining IIT Delhi, he was a Lecturer with the University College of Engineering, Burla, Sambalpur, for 13 Years.

His research areas include the study of advance signal processing techniques, computational intelligence algorithms, and their applications to the electrical engineering domain, particularly to the domain of power systems. His main research focuses on the development of advanced DSP tools and machine intelligence techniques for power quality studies, protection of power systems, etc. He also works in the area of application of evolutionary computing techniques (GA, PSO, clonal algorithm, ACO, bacterial foraging, harmony search, etc.) to solve the problems related to power system planning, operation, and control.

E-mail: [email protected]