Application of locally weighted partial least squares to design of semiconductor virtual metrology

In the semiconductor industry, virtual metrology (VM) has been widely investigated and used to predict important characteristics of products. However, VM is not always successful because its prediction performance deteriorates due to changes in process characteristics. In particular, maintenance of equipment strongly affects the process characteristics and the prediction performance. In the present work, VM was developed by using locally weighted partial least squares (LW-PLS), which is a type of Just-In-Time modeling technique. The developed VM was applied to a dry etching process and a chemical mechanical polishing (CMP) process. The industrial application results have shown that the developed VM based on LW-PLS is superior to the conventional VM based on sequential update model (SUM), locally weighted regression (LWR), and PLS. Furthermore, it has been confirmed that the LW-PLS-based VM can keep its high prediction performance even after the maintenance, i.e. replacement of parts.