Model-based Life Cycle Management Using Deterioration Simulation

Abstract

An essential mission of life cycle management (LCM) is to manage the life time of a target system by understanding its states. Since LCM is becoming digitalized and various data throughout a product life cycle can be collected, a data-driven approach such as machine learning has been used. However, a data-driven approach has some drawbacks: a large volume of required data and so called “black box” problem of reasoning results. This paper proposes a model-based approach for condition-based maintenance, where deterioration simulation is executed. The deterioration simulation enables to examine all possible state changes when each part is deteriorated.