Intelligent sampling decision scheme based on the AVM system

Abstract

Wafer inspection plays a significant role in monitoring the quality of wafers production for continuous improvement. However, it requires measuring tools and additional cycle time to do real metrology, which is costly and time-consuming. Therefore, reducing sampling rate to as low as possible is a high priority to reduce production cost. Several sampling methods in the literature were proposed to achieve this goal. They utilised real sampling inspections as the representatives for the other related wafers to monitor the whole production process. Under the condition of stable manufacturing process, virtual metrology (VM) may be applied to monitor the quality of wafers, while real metrology is unavailable. Therefore, the sampling rate may further be reduced with a sampling decision scheme being designed according to reliable VM. Nevertheless, once a new production variation occurs between planned samplings and no real metrology is available during this period for updating the VM models, un-reliable VM predictions may be produced. The authors have developed the automatic virtual metrology (AVM) system for various VM applications. Therefore, this paper focuses on applying various indices of the AVM system to develop an intelligent sampling decision scheme for reducing sampling rate, while VM accuracy is still sustained.