Evaluating reliance level of a virtual metrology system

This paper proposes a novel method for evaluating the reliability of a virtual metrology system (VMS). The proposed method calculates a reliance index (RI) value between zero and one by analyzing the process data of production equipment to determine the reliability of the virtual metrology results. This method also defines an RI threshold. If an RI value exceeds the threshold, the conjecture result is reliable; otherwise, the conjecture result needs to be further examined. Besides the RI, the method also proposes process data similarity indexes (SIs). The SIs are defined to assess the degree of similarity between the input set of process data and those historical sets of process data used to establish the conjecture model. The proposed method includes two types of SIs: global similarity index (GSI) and individual similarity index (ISI). Both GSI and ISI are applied to assist the RI in gauging the reliance level and locating the key parameter(s) that cause major deviation, thus resolving the VMS manufacturability problem. An illustrative example involving 300-mm semiconductor foundry etching equipment is presented. Experimental results demonstrate that the proposed method is applicable to the VMS of production equipment (such as that for semiconductor and TFT-LCD).