Change detection in precision manufacturing processes under transient conditions

Abstract

Early detection of changes in transient process behaviors from sensor signals is becoming essential for quality assurance in microelectronics and ultraprecision manufacturing processes. We present a Dirichlet process Gaussian State Machine (DPGSM) representation to capture complex dynamics as a random concatenation of nonlinear stationary segments, and develop a method to detect early-stage fault-inducing changes. Extensive experiments suggest that the present approach, compared to other methods tested, was able to detect slight changes that cause severe surface damage 48ms earlier in an ultraprecision machining (UPM) process, and at least 2000ms earlier in a chemical mechanical planarization (CMP) process.