Machinery Monitoring and Diagnostics Using Pseudo Wigner-Ville Distribution andBackpropagation Neural Network

摘要

Artificial Neural Networks provide a data based approach to problem solving,patterned after neurological systems, which has proven successful on unique and noisy data. The pseudo Wigner-Ville distribution provides an excellent characterization of a stationary or non-stationary input signal by transforming a time signal into a joint time-frequency Domain. This characterization provides an energy level associated with any processed Characteristic frequency, which when used as an input to an artificial neural network will aide in the detection of location and severity of machinery faults. Research is presented where the union of an artificial neural network, utilizing the highly successful backpropagation paradigm, and the pseudo wigner-ville distribution are demonstrated and shown to provide remarkable success as a tool for machinery monitoring. Machinery monitoring, Pseudo Wigner-Ville distribution, Machinery diagnostics, Backpropagation neural network.