Segmental Semi-Markov Models for Endpoint Detection in Plasma Etching

We investigate two statistical-detection problems, change-point detection and pattern matching in plasma etch endpoint detection. Our approach is based on a segmental semi-Markov model framework. In the change-point detection problem, the changepoint corresponds to state switching in the model. For pattern matching, the pattern is approximated as a sequence of linear segments which are then modeled as segments (states) in the model. The segmental semi-Markov model is an extension of the standard hidden Markov model (HMM), from which learning and inference algorithms are extended to solve the problems of change-point detection and pattern matching in a principled manner. Results on both simulated and real data from semiconductor manufacturing illustrate the flexibility and accuracy of the proposed framework.