Iterative variational mode decomposition and extreme learning machine for gearbox diagnosis based on vibration signals

  • M. Firdaus Isham Institute of Noise and Vibration, Universiti Teknologi Malaysia, 54100 Kuala Lumpur, Malaysia.
  • M. Salman Leong Institute of Noise and Vibration, Universiti Teknologi Malaysia, 54100 Kuala Lumpur, Malaysia
  • L. M. Hee Institute of Noise and Vibration, Universiti Teknologi Malaysia, 54100 Kuala Lumpur, Malaysia
  • Z. A. B. Ahmad School of Mechanical Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia. Phone: +60326154413; Fax: +60326932854
Keywords: Variational mode decomposition, extreme learning machine, gearbox, signal processing, fault diagnosis, mode selection

Abstract

Vibration-based monitoring and diagnosis provide an excellent and reliable monitoring strategies for maintaining and sustaining a million dollars of industrial assets. The signal processing method is one of the key elements in gearbox fault diagnosis for extracting most useful information from raw vibration signals. Variational mode decomposition (VMD) is one of the recent signal processing methods that helps to solve many limitations in traditional signal processing method. However, pre-determine the input parameters especially the mode number become a challenging task for using this method. Then, this study aims to propose an iterative approach for selecting the mode number for the VMD method by using the normalized mean value (NMV) plot. The NMV value is calculates based on the ratio of a summation of VMD modes and the input signals. The result shows that the proposed iterative VMD approach can select an accurate mode number for the VMD method. Then, the vibration signals decomposed into different VMD modes and used for gearbox fault diagnosis. Statistical features have been extracted from the selected VMD modes and pass into extreme learning machine (ELM) for fault classification. Iterative VMD-ELM provide significance improvement of about 20% higher accuracy in classification result as compared with EMD-ELM. Hence, this research study offers a new mean for gearbox diagnosis strategy.  

Published
2019-03-29
How to Cite
Isham, M. F., Leong, M. S., Hee, L. M., & Ahmad, Z. A. B. (2019). Iterative variational mode decomposition and extreme learning machine for gearbox diagnosis based on vibration signals. Journal of Mechanical Engineering and Sciences, 13(1), 4477-4492. https://doi.org/10.15282/jmes.13.1.2019.10.0380