Imperfect Repair Proportional Intensity Models for Maintained Systems

摘要

The failure processes of a maintained system can be studied from the failure data using imperfect repair models. Additional information on the failure process can also be utilized in the form of covariates using proportional intensity models for getting more realistic results. Both these models can be combined to form imperfect repair proportional intensity models making use of the times to failure and the covariate data together. Such models have been proposed earlier with imperfect repair models using maximal repair baseline intensity. One model GPIM has been proposed using minimal repair baseline intensity. This paper proposes ARA and ARI imperfect repair proportional intensity models using minimal repair baseline intensity. These models are then applied to the field data from an industrial-setting to demonstrate that appropriate parameter estimates for such phenomena can be obtained, and such models are shown to more closely describe the failure processes of a maintained system.