Residual life prediction of repairable systems subject to imperfect preventive maintenance using extended proportional hazards model

Abstract

Proportional hazards model (PHM) is a representative tool for equipment residual life (RL) prediction and preventive maintenance (PM) scheduling in a condition-based maintenance (CBM) program. However, the use of PHM in a CBM program is currently limited to irreparable systems or repairable systems receiving perfect PM acts. Motivated by the classical lifetime distribution-based imperfect PM model and the PHM, our recent study proposes an extended PHM (EPHM) for PM scheduling of systems subject to imperfect PM acts and variable operational conditions. This study further proposes the use of EPHM (with time-varying covariates) for RL prediction of repairable systems subject to imperfect PM acts. A numerical experiment based on a typical degradation model illustrates the use of the EPHM. The experimental results provide evidence that the EPHM provides reasonably accurate and reliable RL prediction after imperfect PM acts, as opposed to the overestimation by the classical PHM which does not take the effect of imperfect PM acts into account.