Application of artificial neural networks, fuzzy logic and wavelet transform in fault diagnosis via vibration signal analysis: A review

Abstract

Fault diagnosis through vibration analysis is a method widely used by maintenance engineers for the condition monitoring of rotating machinery. Conventional vibration signature analysis techniques have been used, and after the invention of soft computation, techniques such as artificial neural network (ANN), fuzzy logic, wavelet transform, genetic algorithms, are broadly used by several researchers. These techniques show tremendous scope in the field of fault diagnosis through vibration analysis. The objective of the present paper is to provide a brief review of recent developments in the area of applications of ANN, fuzzy logic and wavelet transform in fault diagnosis. Special attention is given to the rolling element bearings fault diagnosis through vibration analysis, due to the fact that bearings are among the most important and frequently encountered components in rotating machinery.

Keywords:

• Rolling element bearing
• vibration analysis
• fast Fourier transform
• wavelet transform
• artificial neural network
• fuzzy logic

Additional information

Notes on contributors

P Jayaswal

Pratesh Jayaswal received his BE degree in Mechanical Engineering from Madhav Institute of Technology and Science, Gwalior, India, in 2000, and ME degree in Tribology and Maintenance from Shree Govindram Secsaria Institute of Technology and Science, Indore, India, in 2003. He is currently working towards his PhD degree in the Department of Mechanical Engineering, Madhav Institute of Technology and Science, Gwalior, under Rajiv Gandhi Technical University, Bhopal, India. His research areas are vibration analysis, condition monitoring, and the application of advanced signal processing techniques in machine fault signature analysis. He is a Reader in the Department of Mechanical Engineering, Madhav Institute of Technology and Science, Gwalior, India. He has published several research papers in national and international journals and conferences. He has guided 21 MTech thesis students in the area of production engineering, and reviewed several research paper and books in the area of machine design and vibration analysis.

A K Wadhwani

AK Wadhwani obtained his BE (Electrical) from Bhopal University, India, in 1987, ME Electrical (Measurement and Instrumentation) from the University of Roorkee, Roorkee, India, in 1993, and PhD in Electrical Engineering from Indian Institute of Technology Roorkee in 2003. At present he is working as reader in Electrical Engineering Department at Madhav Institute of Technology and Science, Gwalior, India. He has published 40 research papers in national and international journals and conferences for the benefit of students, faculty and field engineers. His areas of interest are applications of neural networks, fuzzy logic and wavelets in electrical engineering, and digital signal processing. He is life member of ISTE and is currently guiding five PhD students.