An Information Economic Approach for Model Selection In Engineering Design

Abstract

An important element of successful engineering design is the effective management of resources to support design decisions. Design decisions can be thought of as having two phases—a formulation phase and a solution phase. As part of the formulation phase, engineers must decide which models to use in support of design decisions. Although more accurate models typically lead to better decisions, they also cost more. The question therefore is: Which model provides the best cost-benefit trade-off? In this paper, we focus in particular on the situation in which the systematic error in the models can be bounded by an interval. Based on principles of information economics, the interval-based model error results in bounds on the expected economic value of using a particular model in support of a certain design decision. The decision maker can then select the model that provides the best overall value, considering both the expected benefits resulting from the decision and the cost of the decision-making process. The approach is illustrated with the design of an I-beam structure.