A predictive maintenance policy for manufacturing systems considering degradation of health monitoring device

Health monitoring device (HMD) providing the current condition for its monitored manufacturing system is often subjected to a gradual degradation process. The degradation of the HMD may lead to inaccurate system condition monitoring data, conducting to non-appropriate maintenance decision-making. This paper presents a novel predictive maintenance policy for manufacturing systems considering degradation of its HMD. To address this issue, a method based on Kalman filter is developed for estimating the system state. However, due to the data uncertainty given by statistic noise and HMD degradation impacts, the error between estimated value and true state is unavoidable. To overcome this issue, an adaptive predictive maintenance, in which both the estimated state of system and the current state of HMD are used for maintenance decision-making, is then proposed for the system and its HMD. A cost model is developed to find the optimal maintenance policy. A case study of injection molding machine is conducted to show the applications and the benefits of the proposed maintenance policy.