Title: Comparison of denoising schemes and dimensionality reduction techniques for fault diagnosis of rolling element bearing using wavelet transform

Authors: H.S. Kumar; P. Srinivasa Pai; N.S. Sriram; G.S. Vijay; M. Vijay Patil

Addresses: Department of Mechanical Engineering, NMAM Institute of Technology, Nitte, 574110, India; Visveswaraya Technological University, Belagavi – 590018, Karnataka, India ' Department of Mechanical Engineering, NMAM Institute of Technology, Nitte, 574110, India; Visveswaraya Technological University, Belagavi – 590018, Karnataka, India ' Department of Mechanical Engineering, Vidya Vikas Institute of Engineering and Technology, 570 028, Mysore, India; Visveswaraya Technological University, Belagavi – 590018, Karnataka, India ' Department of Mechanical and Manufacturing Engineering, MIT, Manipal University, Manipal, 576 104, India ' Department of Mechanical Engineering, NMAM Institute of Technology, Nitte, 574110, India; Visveswaraya Technological University, Belagavi – 590018, Karnataka, India

Abstract: This paper presents the evaluation of five wavelets-based denoising schemes in order to select the best possible scheme for denoising bearing vibration signals and dimensionality reduction techniques using artificial neural network (ANN). Vibration signals from four conditions of rolling element bearing (REB) namely normal (N), defect on inner race (IR), defect on ball (B) and defect on outer race (OR) have been denoised using interval-dependent denoising scheme, which is the best possible scheme. The denoised signal is subjected to discrete wavelet transform (DWT) to extract 17 statistical features. Principal component analysis (PCA)-based dimensionality reduction technique (DRT) namely PCA alone, Kernel-PCA (KPCA) alone, PCA using SVD and KPCA using SVD have been used for reducing the dimension of the features. It is found that KPCA using SVD resulted in highest prediction accuracy using ANN, making it suitable for effective REB fault diagnosis. [Received 30 November 2015; Revised 17 June 2016; Accepted 20 June 2016]

Keywords: vibration signals; discrete wavelet transform; DWT; wavelet-based denoising; kernel PCA; KPCA; principal component analysis; artificial neural networks; ANNs; SVD; singular value decomposition; dimensionality reduction; fault diagnosis; rolling element bearings.

DOI: 10.1504/IJMR.2016.079461

International Journal of Manufacturing Research, 2016 Vol.11 No.3, pp.238 - 258

Received: 18 Jan 2016
Accepted: 20 Jun 2016
Published online: 28 Sep 2016 *

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