Controlling Production Processes Which are Subject to Linear Trends

Abstract

Industrial processes must often be reset when a critical dimension of the product approaches or exceeds a specified value. This control procedure ensures that specifications remain between predetermined limits, but the resetting operation may be costly and involve loss of production time. Optimal resetting policies are examined for processes which exhibit a linear trend of a variable dimension produced by the process with a known distribution. Optimal policies are discussed for two criteria: (a) maximum rate of production and (b) minimum cost per unit.