Classification of vectors forms dedicated to bearings fault detection of electrical machines based on PSO algorithm
Keywords: Time-frequency representations, analytic vibration signal, dispersion parameter, Hilbert transform particle swarm optimization
AbstractEarly detecting and diagnosing bearing defects during operation aid in preventing abnormal fault progres-sion and decrease productivity loss. Vibration signal analy-sis is one of the most widely applied methods for bearing problem diagnosis, for its effectiveness and easy manipulation. Time-frequency analysis has received considerable interest in the field of bearing fault detection over the past few decades. A key element of this procedure is extracting informative features from the TFRs. In this report, we have developed a method based on cloud point dispersion parameter. The essence of the feature extraction is to project from faulty machine to a low size signal time-frequency representation (TFR), which is deliberately designed for maximizing the separability between classes, a distinct TFR is designed for each class. The feature vectors size is optimized using Particle Swarm Optimization method (PSO). This approach is validated on an academic case and then tested on real data taken from the PRONOSTIA experimental platform.
DYNAMICS OF MECHANICAL SYSTEMS