Acoustic Emission Monitoring for Film Thickness of Mechanical Seals Based on Feature Dimension Reduction and Cascaded Decision

Mechanical seals operates by a thin fluid film to separate the pair of seal faces. The thickness of this film must be optimized for preventing the friction of two end faces and minimizing the leakage. In this study, the fluid film is measured by eddy current and acoustic emission techniques, and the data of eddy current are used to direct the processing of acoustic emission signal. To decrease the noise, wavelet packet and kernel principal component analysis are used to extract the data features. Then cascaded decision is presented to improve the recognition rate of artificial neural network, by which the film thickness can be estimated.