A probabilistic search method for sequential tolerance control

Tolerance control is the set of practices used to ensure that parts are mad e within their specifications. Sequential Tolerance Control (STC) is the pr actice of using the results of earlier operations in the execution of a pro cess plan to locate appropriate set points for later operations. In a previ ously developed set-point adjustment method, the largest sphere that fits i nto the remaining feasible space is moved to its extreme positions in the c oordinate direction of the next operation, x(k), and the next set point is positioned at the mean of the kth coordinates of the centres in these two p ositions. Scaling the feasible space in proportion to the variability of ea ch operation has also been investigated. This paper presents a probabilisti c search method for STC. This method finds the new set point by using the N elder-Mead downhill simplex method to optimize an estimation of the expecte d process yield. Probabilistic search is found to be about as effective as sphere-fitting methods for normally distributed process deviations, but for skewed distributions, the search method is shown to yield better set point s than previous methods.