Fault Detection and Diagnosis in Gears Using Wavelet Analysis Techniques and Comparison on their Diagnostic Capability

The concept of vibration based condition monitoring technology has been developing at a rapid stage in the recent years suiting to the maintenance of sophisticated and complicated machines. Nowadays, wavelet analysis based signal processing technique is applied as effective tool for condition monitoring. The experimental studies were conducted on the gear testing apparatus to obtain the vibration signal from a healthy gear and an induced faulty gear. In this paper, two different techniques using Laplace wavelet as base function are used to characterize the fault in the gear signals, specifically wavelet enveloped power spectrum and wavelet kurtosis. The wavelet parameters are optimized using genetic algorithm to select most fault related features. A comparative study detailing features of fault characterization is also given in order to understand the effectiveness of both the wavelet based signal processing methods and their fault diagnosis capability.