Feature Selection and Fault Classification of Reciprocating Compressors using a Genetic Algorithm and a Probabilistic Neural Network

Feature Selection and Fault Classification of Reciprocating Compressors using a Genetic Algorithm and a Probabilistic Neural Network

M Ahmed, F Gu and A Ball

M.Ahmed@hud.ac.uk

Diagnostic Engineering Research Group, University of Huddersfield, HD1 3DH, UK

Abstract

Faults occurring in reciprocating compressors can degrade their performance, consume additional energy and cause severe damage to the machine. Although vibration monitoring techniques are often used for early fault detection and diagnosis, it is difficult to prescribe a given set of effective diagnostic features because of the wide variety of operating conditions and the complexity of the vibration signals which originate from the many different vibrating and impact sources.

Authors describe a  study of the use of genetic algorithms (GAs) and neural networks (NNs) to select effective diagnostic features for the fault diagnosis of a reciprocating compressor. A large number of common features are calculated from the time and frequency domains and envelope analysis.

Applying GAs and NNs to these features found that envelope analysis has the most potential for differentiating three common faults: valve leakage, inter-cooler leakage and a loose drive belt. Simultaneously, the spread parameter of the probabilistic

Full Text Source (Subscription or Fee): http://iopscience.iop.org/1742-6596/305/1/012112