Abstract
Machine condition monitoring (MCM) aims to evaluate machine health conditions by statistically analysing machine condition data. Health indicators (HIs) such as Gini index, negative entropy, spectral kurtosis et al. have been commonly applied in MCM. But these HIs lack a statistical threshold and monotonic degradation tendency. To monitor the health condition of rotating machines, a nonparametric nonlinear profile monitoring method for MCM is proposed in this paper. And a Hotelling T-square health indicator (HTHI) with a statistical threshold is constructed with B-spline modeling and Hotelling T-square statistic. Experimental validation on a public bearing dataset shows that the constructed HTHI can effectively detect early machine faults and monotonically evaluate degradation trends, which enriches methods of MCM domain.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
