STM Journals Peer-reviewed research from Consortium e-Learning Network

Trends in Mechanical Engineering & Technology

To Diagnose the Broken Tooth Fault, Signal Processing Techniques and Machine Learning Technique are Applied

  1. Manoj Kumar Gangwar

Abstract

The objective of this research is to study the diagnosis of broken tooth fault of spur gear using vibration signals with signal processing and machine learning techniques. In this study, experiment has been performed and analyse on the broken tooth fault and healthy spur gear conditions. This paper describes two approaches to signal processing techniques from acquired vibration signals, which are time-domain and frequency domain, involving statistical characteristics of vibration signals. The changes of noise level during operation in terms of decibels is also considered in this study. This study is motivated by the J48 decision tree machine learning algorithm as for spur gear fault diagnosis. The proposed techniques have been examined that both signal processing to be useful for fault diagnosis and may be enhanced by analysing both sides. J48 decision tree provide better classification accuracy about 96.67% in identifying broken tooth fault during running condition. The proposed approach may be used effectively to properly diagnose fault or analyse vibration in any machinery parts.

Keywords

Support