Recursive linear control of order release to manufacturing cells with random yield

Abstract

One-piece flow job shop production environments in high labor turnover environments are oftentimes characterized by late shipments and incomplete orders due to random and variable yield. The problem addressed in this paper is that of determining an order release policy for a one-piece flow prototype production line in order to meet demand in an environment subject to random and variable yield induced by high labor turnover. This paper is motivated by a problem encountered in a facility that produces prototype parts. The problem at hand can be defined as that of determining a lot size to release into the line to minimize deviations from the demand (i.e., target batch quota) for single-piece flow production in an environment characterized by random and variable yield. The objective of this research was to investigate the utility of recursive linear control as a mechanism for releasing parts into a single-piece flow production cell, and to develop a control algorithm using a Kalman filter. The methodology is evaluated via simulation using actual demand and yield data simulated from a distribution fit from historical data. Order release strategy and yield were found to be the dominant variables for complete and on-time orders without excess and shortages, and linear recursive control was found to be effective for tracking, monitoring and adjusting the release of parts into a single-piece flow job shop in an environment characterized by random and variable yield.