Advanced Process Control Using Virtual Metrology to Cope with Etcher Condition Change

In a semiconductor plasma etcher, an advanced process control (APC) system using virtual metrology (VM) is required to achieve further device miniaturization. Although a highly accurate VM model is necessary to realize the system, the prediction accuracy can be worse when correlations between the critical dimension (CD) and equipment data change because of changes in etcher conditions. To solve the problem, we propose a multiple VM model selection APC system. This paper shows that the proposed system contributes to improving prediction accuracy even though the correlation change occurs by simulation based on the actual etcher experimental data.