Surrogate Modeling and Optimizing for CCP Etch Process

Abstract

In order to analyze performance of the Capacitively Coupled Plasma (CCP) etcher, commercial software like OPTIMUS can be applied to approximate etch process model by Response Surface Method (RSM) or Radial Basis Functions (RBF). Multi-factor parameters are concerned in etch process, like frequencies of the dual Radio Frequency system (RF) and flow rate and flow ratio of the process gas. When facing the multi-dimensional problem, the algorithms would turned to be inefficiency and the optimization process may be trapped in local minimum area or cannot converge because of oscillation. To improve surrogate modeling for the CCP etcher, a self-optimizing RBF (SO-RBF) algorithm is proposed and a process modeling tool is developed. Experiments on a state-of-art dual station CCP etcher shows that based on the global approximation model generated by this algorithm, process parameter optimization can be easily implemented with less error than OPTIMUS.