Planned Maintenance Schedule Update Method for Predictive Maintenance of Semiconductor Plasma Etcher

Abstract

In a semiconductor plasma etcher, it is becoming increasingly necessary to improve productivity. Thus, to reduce unplanned maintenance, predictive maintenance (PdM) is typically conducted. In PdM, the planned maintenance schedule is updated on the basis of the predicted failure timing. However, in practice, the predicted failure timing has a probabilistic variability. Therefore, we propose a maintenance schedule update method on the basis of the expected maintenance cost calculated from the probabilistic variability of the failure timing. We applied our method to a dataset that model failure cases of etchers and found that our method was effective in terms of maintenance costs.