Modeling etch rate and uniformity of oxide via etching in a CHF 3/CF 4 plasma using neural networks

Abstract

An oxide film etched in a magnetically-enhanced CHF 3/CF 4 plasma has been modeled using neural networks. The etch process was characterized with a 2 4−1 factorial experiment. The experimental factors and ranges include 20–80 sccm CHF 3 flow rate, 10–40 sccm CF 4 flow rate, 300–800 W radio frequency (RF) power, and 50–200 mTorr pressure. Radicals (F, CF 1, and CF 2) measured with optical emission spectroscopy were related to etch responses. In the experiments conducted, increases in etch rate generally corresponded to decreases in nonuniformity. Etch nonuniformity was strongly dependent on RF power. The relative significance of polymer deposition and ion bombardment was separated and explained. The root-mean-squared prediction errors are 174 Å/min and 0.425% for etch rate and etch nonuniformity models, respectively.