ARL-Wavelet-BPF optimization using PSO algorithm for bearing fault diagnosis

Rotating element bearings are the backbone of every rotating machine. Vibration signals measured from these bearings are used to diagnose the health of the machine, but when the signal-to-noise ratio is low, it is challenging to diagnose the fault frequency. In this paper, a new method is proposed to enhance the signal-to-noise ratio by applying the Asymmetric Real Laplace wavelet Bandpass Filter (ARL-wavelet-BPF). The Gaussian function of the ARL-wavelet represents an excellent BPF with smooth edges which helps to minimize the ripple effects. The bandwidth and center frequency of the ARL-wavelet-BPF are optimized using the Particle Swarm Optimization (PSO) algorithm. Spectral kurtosis (SK) of the envelope spectrum is employed as a fitness function for the PSO algorithm which helps to track the periodic spikes generated by the fault frequency in the vibration signal. To validate the performance of the ARL-wavelet-BPF, different vibration signals with low signal-to-noise ratio are used and faults are diagnosed.