Design and implementation of an intelligent prognostics system

Abstract

This work proposes an intelligent prognostics system (IPS) for semiconductor and TFT-LCD manufacturing. The IPS comprises several generic embedded devices (GEDs) and a remote host. The GED can be easily embedded into various types of equipment to acquire equipment-engineering data and meet the specification requirements of interface A for supporting semiconductor industry e-diagnostics. Furthermore, the GED has an open-standard application interface offering any pluggable and customized intelligent-maintenance applications. With this feature, intelligent-maintenance tasks can be distributed and localized releasing the factory network burden and enhancing equipment reliability and maintainability. This work also develops two typical pluggable applications: the predictive maintenance scheme (PMS) for equipment fault detection, and the quality prognostics scheme (QPS) for virtual metrology and product quality prediction. Integrating the PMS into the IPS and the QPS into the IPS are respectively accomplished using the conveyor equipment and the sputtering equipment of a TFT-LCD factory. These two illustrative examples clearly demonstrate that IPS is versatile, configurable, and effective.