Compound Fault Diagnosis of Aero-Engine Rolling Element Bearing Based on CCA Blind Extraction

Fault diagnosis of aero-engine spindle bearing is a critical technique of engine prognostics and health management. As is known that the diagnosis of compound fault of aero-engine spindle bearing is very difficult and easily affected by other vibration interference signals. We present a canonical correlation analysis (CCA) criterion based method for blind extraction of specific fault signal from multi-channel observations, which is applicable to compound fault diagnosis of aero-engine spindle bearing. The proposed method uses the different fault characteristic frequency of rolling element bearing to estimate the delay parameter in CCA criterion. The conjugate gradient method is adopted to optimize the CCA criterion, which not only speed up the convergence of the optimization algorithm, but also improves the reliability of the resulted algorithm. Both the simulated data and the experimental data are used to verify the effectiveness of the algorithm in compound fault diagnosis.