Feature extraction of mixed faults of intershaft bearing based on homologous information and Hjorth parameters

To make correct judgment on the mixed faults of intershaft bearing of aeroplane engine, the paper has proposed a feature option method. This method works by decomposing cross-correlation function (CCF) of homogeneous information from casing with intrinsic time scale decomposition (ITD) for the separation and blending of signals. Furthermore, option of proper rotation components (PRCs) for fault identification is made by abandoning the PRC related with the least Complexity parameter in Hjorth parameters. Moreover, signal is reconstructed based on the autocorrelation function (AF) of residual PRCs. Finally, according to the frequency spectrum of signal reconstructed, fault features corresponding to intershaft bearing are extracted and fault types estimated. The result indicates that the Complexity parameter in Hjorth parameter can be used as an evaluation index to implement the selecting of sensitive fault components. Furthermore, the mixed fault types which come from intershaft bearing of aeroplane engine could be judged correctly.

Automated summary

This paper proposes a feature selection method for judging mixed faults in intershaft bearings. The method decomposes the homogeneous information of the casing and separates and blends signals based on intrinsic time scale decomposition. Fault identification is made by selecting proper rotation components and signal reconstruction is based on the autocorrelation function. Fault features and types are extracted from the reconstructed signal. The study shows that the Complexity parameter can be used as an evaluation index for selecting sensitive fault components and correctly judging mixed fault types in intershaft bearings.