Vibration Analysis of Industrial Drive for Broken Bearing Detection Using Probabilistic Wavelet Neural Network

Abstract

A reliable monitoring of industrial drives plays a vital role to prevent from the performance degradation of machinery. Today’s fault detection system mechanism uses wavelet transform for proper detection of faults, however it required more attention on detecting higher fault rates with lower execution time. Existence of faults on industrial drives leads to higher current flow rate and the broken bearing detected system determined the number of unhealthy bearings but need to develop a faster system with constant frequency domain. Vibration data acquisition was used in our proposed work to detect broken bearing faults in induction machine. To generate an effective fault detection of industrial drives, Biorthogonal Posterior Vibration Signal-Data Probabilistic Wavelet Neural Network (BPPVS-WNN) system was proposed in this paper. This system was focused to reducing the current flow and to identify faults with lesser execution time with harmonic values obtained through fifth derivative. Initially, the construction of Biorthogonal vibration signal-data based wavelet transform in BPPVS-WNN system localizes the time and frequency domain. The Biorthogonal wavelet approximates the broken bearing using double scaling and factor, identifies the transient disturbance due to fault on induction motor through approximate coefficients and detailed coefficient. Posterior Probabilistic Neural Network detects the final level of faults using the detailed coefficient till fifth derivative and the results obtained through it at a faster rate at constant frequency signal on the industrial drive. Experiment through the Simulink tool detects the healthy and unhealthy motor on measuring parametric factors such as fault detection rate based on time, current flow rate and execution time.