This paper addresses a problem arising in the coordination between two consecutive stages of a production system. Production is organised in batches of identical jobs. Each job is characterised by two distinct attributes, and all jobs sharing the same attributes are processed together as a single batch. Due to the structural and organisational characteristics of the production system, the two stages have to process the same batch sequence. When two consecutive batches with different attributes are processed, at least one stage must pay a setup, in order to reconfigure its own devices. Each stage incurs a setup cost that is a general nondecreasing function of the number of its own setups, and the problem consists of finding a batch sequence minimising the total setup costs of the production system. We present an original solution approach for the considered problem that is shown to be very effective using an extensive experimental campaign.

Optimization of simulated systems is the goal of many methods, but most methods assume known environments. We, however, develop a “robust” methodology that accounts for uncertain environments. Our methodology uses Taguchi’s view of the uncertain world but replaces his statistical techniques by design and analysis of simulation experiments based on Kriging (Gaussian process model); moreover, we use bootstrapping to quantify the variability in the estimated Kriging metamodels. In addition, we combine Kriging with nonlinear programming, and we estimate the Pareto frontier. We illustrate the resulting methodology through economic order quantity (EOQ) inventory models. Our results suggest that robust optimization requires order quantities that differ from the classic EOQ. We also compare our results with results we previously obtained using response surface methodology instead of Kriging.