Comparison of Data Mining and Neural Network Methods on Aero-engine Vibration Fault Diagnosis

Data mining and artificial neural network (ANN) have been extensively applied on machinery fault diagnosis. Aero-engine, as one kind of rotating machine with complex structure and high rotating speed, has complicated vibration faults. ANN is a good tool for aero-engine fault diagnosis, since they have strong ability to learn complex nonlinear functions. Data mining has advantages of discovering knowledge from mountain of data, providing a simple way to interpret complex decision problem, and automatically extract diagnostic rules to replace the expert´s advice. This paper presents application of the two methods on aero-engine vibration fault diagnosis and then makes a comparison between them. From the study of this paper, both the two methods are effective on aeroengine vibration fault diagnosis, while each of them has its individual quality.