CMP Process Optimization Engineering by Machine Learning

Abstract

Advanced Chemical-mechanical polishing (CMP) process not only needs to maintain stable run-to-run thickness control to achieve better within wafer/within chip planarization performance, but also have capability to cover various topologies and layout densities patterned wafer and preventing the hot spots occurrences. In this study, different Neural-Network algorithm with data pre-processing models are implemented to the in-line CMP CLC tuning and dishing/erosion prediction at various topology/pattern density incoming pattern wafers to resolve the most challenging process issues at next generation.