A conceptual model to enable prescriptive maintenance for etching equipment in semiconductor manufacturing
Abstract
The high equipment intensity and complexity of production processes in semiconductor manufacturing leads to challenging requirements regarding plant availability in this competitive market. In the present paper, we address these challenges by proposing a conceptual model to enable prescriptive maintenance in semiconductor manufacturing. Different Machine Learning Algorithms are used to predict time-to-failure intervals for unplanned downtimes. Furthermore, the concept uses Bayesian Networks to predict the root cause of a failure and ultimately leads to recommendations, which are integrated into maintenance planning routines, in order to increase the system availability by initiating specific maintenance measures. Finally, the benefit of prescriptive maintenance is demonstrated in an industrial use case for etching equipment in semiconductor manufacturing.
