Condition-based maintenance strategy for vehicles using hidden Markov models

Operation and maintenance have their own impact in every field. Maintenance strategy is followed to provide unwavering quality and security for a healthy transportation system. Therefore, the transportation system requires an appropriate maintenance schedule of the vehicles. The classical analysis of the present and future performance of systems tries to assure that the safety and operational condition of the system so as to enhance the ability of credentials of proactive malfunction circumstances. Condition-based maintenance identifies the vehicle status based on wire or wireless monitored data and predicts malfunction to carry out suitable maintenance actions like repair and replacement before it happens. Different uncertainties like terrain, mileage of the vehicle and applied load on the vehicles have been utilized as the constraints of fuzzy-based vehicle maintenance scheduling. The response of vehicle maintenance scheduling (VMS) provides the details regarding the type of maintenance and time period in weeks for proposed maintenance plan. Probability values of constraints acquired by the hidden Markov model have been utilized as input of VMS. The response of vehicle maintenance scheduling has been compared with input obtained by Monte Carlo simulation. Reliability of the methodology corroborates the effectiveness of the proposed methodology in the field of maintenance scheduling for healthy transportation system.