Abstract
Health indicators (HIs), which can make quantitative measures at different operating states, are critical in machine condition monitoring (MCM). However, inadequate characterization of local statistical HIs and stringent sample requirement for machine learning based MCM are inescapable obstacles to be further investigated. In order to enhance the MCM capacity, a novel degradation space variation evaluating method for MCM is proposed in this paper. Firstly, a compositive condition representation is established from the multi-domain statistical perspective. Through orthonormal transform on adjacent intrinsic condition characterizations, a performance degradation space is dynamically constructed, the variation of which, named condition fluctuation rate (CFR), is accordingly evaluated for MCM. Experimental validations exhibit that the proposed CFR indicator is more sensitive and robust when compared with conventional HIs.
Sign-in/Register to access full text options 
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 callMore From: IEEE Transactions on Instrumentation and Measurement
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
