Automated Fault Classification of Reciprocating Compressors from Vibration Data: A Case Study on Optimization Using Genetic Algorithm

This article deals with automated fault classification of reciprocating compressors from vibration data. The genetic algorithm was applied to automate the process. A total of 15 fault cases based on practical observation of the machine faults was considered. Vibration data for the various fault cases were collected and processed using the time-frequency analysis, namely the short time Fourier transform (STFT), the smoothed pseudo Wigner-Ville distribution (SPWVD), and the reassigned smoothed pseudo Wigner-Ville distribution (RSPWVD), due to the non-stationary vibration characteristics of the system analyzed. The fault features for the formidable amount of time-frequency data were extracted first and fed into an artificial neural network for fault classification. It is demonstrated in this work that it is feasible to apply the genetic algorithm to automate the fault classification process and thereby minimize the requirement for intervention from the human experts.