Multiobjective Framework for Modular Design Generation Incorporating Demand Uncertainty

Recent developments in process design have focused on establishing optimization-based approaches to support decision making under uncertainty by creating customized designs under specified production requirements. Modular-based design has long been recognized as a preferred alternative because it results in more flexible solutions in a dynamically changing environment. This paper introduces an integrated data analysis, stochastic design optimization approach to generate a portfolio of standardized designs that span the random demand space. The main idea is to cluster the demand and generate a Pareto set of designs by modeling cost and robustness in a multiobjective framework. Two case studies are presented to illustrate the applicability of the proposed approach.