Article: Design of optimal MLP and RBF neural network classifier for fault diagnosis of three phase induction motor Journal: International Journal of Advanced Mechatronic Systems (IJAMECHS) 2010 Vol.2 No.3 pp.204 - 216 Abstract: Induction motors are subject to incipient faults which, if undetected, may lead to serious machine failures. Now, it is well understood that incipient fault detection methods applied in large induction motors (e.g., greater than 100 hp) are often too costly or may not be feasible for use on small and medium size induction motors. From the scrupulous review of the related work, it is observed that neuro-fuzzy and neural network (NN) based fault detection schemes are performed only for large machines and they are not only expensive but also complex. Our NN based incipient fault detection method avoid the problems associated with traditional incipient fault detection schemes by employing more readily available information such as stator current. This paper develops inexpensive, reliable and non-invasive NN based incipient fault detection scheme for small and medium sized induction motors. Detailed design procedure for achieving the optimal NN model and sensitivity analysis for dimensionality reduction is proposed. Overall, 13 statistical parameters are used as feature space to achieve the desired classification. MLP and RBF NN models are designed and verified for optimal performance in fault identification on experimental data set of custom designed 2 hp, three phase 50 Hz induction motor. Inderscience Publishers - linking academia, business and industry through research

Title: Design of optimal MLP and RBF neural network classifier for fault diagnosis of three phase induction motor

Authors: V.N. Ghate, S.V. Dudul

Addresses: Faculty in Electrical Engineering, Government College of Engineering, Kathora Naka, Amravati. 444604, M.S., India. ' Department of Applied Electronics, Sant Gadge Baba Amravati University, Amravati – 44602, M.S., India

Abstract: Induction motors are subject to incipient faults which, if undetected, may lead to serious machine failures. Now, it is well understood that incipient fault detection methods applied in large induction motors (e.g., greater than 100 hp) are often too costly or may not be feasible for use on small and medium size induction motors. From the scrupulous review of the related work, it is observed that neuro-fuzzy and neural network (NN) based fault detection schemes are performed only for large machines and they are not only expensive but also complex. Our NN based incipient fault detection method avoid the problems associated with traditional incipient fault detection schemes by employing more readily available information such as stator current. This paper develops inexpensive, reliable and non-invasive NN based incipient fault detection scheme for small and medium sized induction motors. Detailed design procedure for achieving the optimal NN model and sensitivity analysis for dimensionality reduction is proposed. Overall, 13 statistical parameters are used as feature space to achieve the desired classification. MLP and RBF NN models are designed and verified for optimal performance in fault identification on experimental data set of custom designed 2 hp, three phase 50 Hz induction motor.

Keywords: induction motors; fault detection; MLP; RBF; neural networks; classifiers; fault diagnosis.

DOI: 10.1504/IJAMECHS.2010.033045

International Journal of Advanced Mechatronic Systems, 2010 Vol.2 No.3, pp.204 - 216

Published online: 07 May 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Design of optimal MLP and RBF neural network classifier for fault diagnosis of three phase induction motor

Keep up-to-date