Learning-Based Preference Modeling in Engineering Design Decision-Making

Abstract

Focusing on the efforts towards a consistent preference representation in decision based engineering design, this paper presents a learning-based comparison and preference modeling process. Through effective integration of a deductive reasoning-based on designer’s outcome ranking in a lottery questions-based elicitation process, this work offers a reliable framework for formulating utility functions that reflect designer’s priorities accurately and consistently. It is expected that this integrated approach will reduce designer’s cognitive burden, and lead to accurate and consistent preference representation. Salient features of this approach include a linear programming based dynamic preference learning method and a logical analysis of preference inconsistencies. The development of this method and its utilization in engineering design are presented in the context of a mechanism design problem and the results are discussed.