Abstract
The advanced technology industries require high precision and highly stable equipment to avoid the cost caused by failure occurrence. Equipment automation and preventive maintenance must be executed to keep equipment within proper operating states. It has always been an important topic for study in inspecting the operating states of equipment by sensors and determing the dynamic preventive maintenance policies according to the real-time condition by computer analyzing centers.This research is focused on the deteriorating system. The real-time equipment operating state can be generated by using health index integrating the parameters inspected by sensors. In this research, a discrete time Markovian multi-state deteriorating model is adopted to describe the state transition of equipment. The model also includes (1) the deteriorating of operating states ( via upper triangular probability transition matrices) and (2) the aging of transition probabilities ( via aging factor )；(3) Base on historical data, we can estimate the model parameters （aging factor and initial transition matrix） and (4) assume that multiple imperfect actions with risk are available.The estimation methodologies of the model parameters are also provided in this research. For the practical application of the model, the maintenance time is also taken into consideration. According to the real-time equipment status, the optimal maintenance policy of each operating state can be generated by the rule of the minimum expected total cost per unit time for each cycle during finite time interval in the near future.