An improved envelope detection method using particle swarm optimisation for rolling element bearing fault diagnosis

Abstract

Abstract Traditionally Envelope Detection (ED) is implemented for detection of rolling element bearing faults by extracting the envelope of band-passed vibration signal and thereafter taking its Fourier transform. The performance of ED is highly sensitive to the envelope window (i.e. central frequency and bandwidth of the passband). This paper employs Particle Swarm Optimisation (PSO) to select the most optimum envelope window to band pass the vibration signals emanating from rotating driveline that was run in normal and with faults induced rolling element bearings. The envelopes of band-passed signals were extracted with the help of Hilbert Transform. The performance of ED whose envelope window was optimised by PSO to identify various commonly occurring bearing faults such as bearing with Outer Race Fault (ORF), Inner Race Fault (IRF) and Rolling Element Fault (REF) were checked under varying load conditions. The performance of ‘ED enhanced by PSO’ was also checked with increase in the severity of defect. It was shown that the improved ED method is successfully able to identify all types of bearing faults under different load conditions. It was shown that the by selecting envelope window by PSO makes ED especially useful to identify bearing faults at the incipient stage of defect. It was also shown by presenting comparative performance that by optimising the envelope window by PSO the performance of ED gets significantly enhanced in comparison to the traditional ED method for bearing fault diagnosis.