PROCESS CONTROL: A BAYESIAN APPROACH USING DYNAMIC PROGRAMMING.
Academic Article
Overview
Additional Document Info
View All
Overview
abstract
A model is formulated for the time dependent environment and optimized using dynamic programming. The cost factors included in the model formulation are for sampling, investigating and overhauling the process, and producing defective items. The pertinent design parameters are the sample size at each inspection, the interval between successive inspections, and the values of the sample outcome which dictate the proper operating decision. The model accommodates process operations which have a single quality characteristics of interest. It is assumed that this characteristic is a continuous random variable as is the process parameter mu , the mean operating level. Furthermore, it is assumed that mu can be satisfactorily approximated by a discrete random variable and that the time between successive shifts in the operating level is dictated by the exponential distribution. This assertion thereby assures a Markovian decision process.