In this paper, we applied segmental semi-Markov models to the problems of plasma etch endpoint detection. The model is quite a useful, flexible, and accurate framework for change-point detection and pattern matching. By modeling the problem within a generative model framework (including notions of state and time explicitly) one can incorporate prior knowledge in a principled manner and use the tools of probabilistic inference to infer change-points and pattern in an optimal manner. For more details of the techniques outlined in this paper, we refer the reader to our longer papers (Ge and Smyth 2000b,a).