Single-machine-based predictive maintenance model considering intelligent machinery prognostics

As an increasing number of manufacturers are beginning to realize the importance of maintaining throughput, many maintenance models have been developed to enable machines to achieve near-zero downtime. However, previous maintenance models usually ignore machine's deterioration process. Therefore, this paper develops a novel data-driven machinery prognostic approach for machine performance assessment and prediction. With this prognostic information, a predictive maintenance model is proposed for a repairable deteriorating machine. As machine performance can be assessed, once it reaches the maintenance threshold, a maintenance operation is performed to restore the machine. Moreover, an operational cost is introduced to meet real manufacturing process. In this predictive maintenance model, the optimal maintenance threshold and maintenance cycle number are obtained with the aim to minimize the long-term average cost. Finally, a case study is presented. The computational results show the efficiency of this proposed predictive maintenance model.