As a useful tool for process control in a high volume semiconductor manufacturing environment, virtual metrology for the etch rate in a plasma etch process is investigated using optical emission spectroscopy (OES) data. Virtual metrology is a surrogate measurement taken from the process instead of from direct measurement, and it can provide in-situ metrology of a wafer's geometry from a predictive model. A statistical regression model that correlates the selected wavelengths of the optical emission spectra to the etch rate is established using the OES data collected over 20 experimental runs. In addition, an argon actinometry study is employed to quantify the OES data, and it provides valuable insight into the analysis of the OES data. The established virtual metrology model is further verified with an additional 20 runs of data. As a result, the virtual metrology model with both process recipe tool data and in-situ data shows higher prediction accuracy by as much as 56% compared with either the process recipe tool data or the in-situ data alone.

Optical emission spectroscopy (OES) is often used for real-time analysis of the plasma processes. OES has been suggested as a primary plasma process monitoring tool. It has the advantage of non-invasive in-situ monitoring capability but selecting the proper wavelengths for the analysis of OES data generally relies on empirically established methods. In this paper, we propose a practical method for the selection of OES wavelength peaks for the analysis of plasma etch process and this is done by investigating reactants and by-product gas species that reside in the plasma etch chamber. Wavelength selection criteria are based on the standard deviation and correlation coefficients. Moreover, chemical actinometry is employed for the normalization of the selected wavelengths. We also present the importance of chemical actinometry of OES data for quantitative analysis of plasma. Then, the suggested OES peak selection method is employed.. This method is used to find out the reason behind abnormal etching of PR erosion during a series of SiO 2 etch processes using the same recipe. From the experimental verification, we convinced that OES is not only capable for real-time detection of abnormal plasma process but it is also useful for the analysis of suspicious plasma behavior.