Abstract
Diagnostic health monitoring without prior knowledge is still a hard problem in the prognostic and health management field. A multivariate diagnostic health monitoring strategy is proposed based on...
Highlights
Prognostic and health management (PHM) technology is important to various spacecrafts for successful task management, orbital maintenance, and service life prolongation
In order to solve the shortcomings of the existing multivariate approaches and real application restricts, a feasible and effective multivariate diagnostic health monitoring strategy for in-orbit spacecrafts based on deep forest is proposed in this article
The multivariate diagnostic health monitoring, combined with effective feature extraction, fuzzy C-means clustering (FCM), and deep forest classifier, has been proposed to solve the problem of synthesized health index (SHI) construction and empirical thresholds setting in the PHM field
Summary
Prognostic and health management (PHM) technology is important to various spacecrafts for successful task management, orbital maintenance, and service life prolongation. Multivariate approaches[7,20,21] are newly emerging techniques that automatically divide the health degradation process into several stages using unsupervised clustering algorithms and label the current health state by searching the nearest cluster Compared with the former two approaches, the multivariate approaches do not need to establish a 1D SHI, predefine the thresholds of different health states, or have a large number of similar historical samples. A feasible and effective data-driven diagnostic health monitoring strategy for in-orbit spacecrafts is needed to solve the following basic problems: 1. A feasible and effective data-driven diagnostic health monitoring strategy for in-orbit spacecrafts is needed to solve the following basic problems: 1. How to extract multi-domain health-degradation-relevant features from massive multivariate telemetry data?
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
