Fault prognosis approach using data-driven structurally generated residuals

Abstract

© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

This paper presents a fault prognosis approach using data-driven structurally generated residuals. It assumes that a set of residuals generated using structural analysis (SA) and identified using data-driven approach are available. Residuals are used for fault detection purposes activating fault signals when residual values reach anomalous values. In addition, it is possible to predict future faults by means of the detection of anomalous residual deviations. Once an anomalous change in the residual trend has been detected, it is proceed to estimate when this residual deviation will result in a fault detection and therefore which will be the Remaining Useful Life (RUL) time of the system. For this purpose, the future residual evolution is estimated by means of a regressor function. Nominal and interval parameters of regressor function are estimated with available residual data providing nominal and interval values of the RUL of the system. A brushless direct current (BLDC) motor is used as the application case study to illustrate the performance of proposed approach.

This work has been co-financed by the Spanish ResearchAgency (AEI) through the projects SaCoAV (ref. MINECOPID2020-114244RB-I00)andL-BEST(PID2020115905RB-C21).

Peer Reviewed

Postprint (published version)