Application of Causality Model to Propose Maintenance Action of Parts

Abstract

This paper discusses the application of a causality model to propose maintenance actions for the purpose of promoting the reuse of mechanical parts. To realize effective reuse of mechanical parts for the development of a sustainable society, it is essential to manage the individual parts over their entire life cycle. For this purpose, we are developing a “part agent” that is programmed to follow its real-life counterpart throughout its life cycle. A part agent provides the user with appropriate advices on the reuse of its part and promotes the circulation of reused parts. In this study, we propose a method to estimate the probability of failure occurrence and determine the corresponding maintenance action. The probability of the failure occurrence is calculated by the causality among events relating to the part and the conditional probability, which is the probability of occurrence of the resultant event against the occurrence of input events. To calculate the conditional probability of events representing the state of a part, the deterioration of the part is simulated based on its operating and environmental conditions. A causality model including this conditional probability is constructed, and the failure probability of the part is estimated. In this paper, we report a mechanism that updates the conditional probabilities according to the operating and environmental conditions that correspond to the different stages in a life cycle.