Remaining useful life prediction of induction motors using nonlinear degradation of health index

Prognostics and Health Management (PHM) methodologies are increasingly playing active roles in improving the safety, reliability, availability, as well as productivity of systems in many industries. Focusing on predicting the Remaining Useful Life (RUL) using Health Index (HI) formulation, this paper proposed a generic prognostics framework with HI dynamic smoothing and multi-model ensemble realization, which enables the incorporation of different types of HI degradations. A case implementation with exponential HI degradation was carried out and experimental studies on real data from 8 induction motors were conducted. In comparison with direct prediction and prediction with linear HI degradation, performance improvements were clearly observed, indicating the feasibility and effectiveness of the proposed prognostic method using nonlinearly degrading HI. (C) 2020 Elsevier Ltd. All rights reserved.