Gear tooth surface damage diagnosis based on analyzing the vibration signal of an individual gear tooth

Abstract

Gear failure is the main cause of machine malfunction. Therefore, it has become increasingly important to detect gear failure to ensure the normal operation of a machine. Here, we propose a gear damage detection and localization approach by studying the vibration signal of an individual gear tooth and support vector machines. Generally, it is difficult to detect a small gear failure in the total vibration signal. The waveform of an individual gear tooth was studied to investigate the vibration features of a gear in more detail. The characteristics of damaged and normal teeth were investigated by analyzing their individual waveform. Besides, the feature parameters were also extracted from both the time and frequency domains of the waveform to investigate the characteristics of each gear tooth. The difference between the damaged and normal teeth was detected by the waveform and feature parameters. Additionally, the condition of each gear tooth was diagnosed by support vector machines using the extracted feature parameters. The method was used to analyze the results of cyclic fatigue experiments. The conditions of most of the gear teeth were correctly classified, validating the proposed method.