Deriving configuration knowledge and evaluating product variants through intelligent techniques

Abstract

Mass customization has become a crucial business strategy for product manufacturers that aims at satisfying individual customer needs with near mass production efficiency. Companies must develop the necessary infrastructure to derive valid product configurations that satisfy the requirements of lifecycle cost along with customer's constraints. In this paper, to overcome the drawback of current product configurators, we apply a rule mining approach to automatically generate configuration knowledge, and present a hybrid approach based on Activity Based Costing (ABC) and machine learning techniques to estimate LCC of derived product variants from a constraint-based configurator at the design stage. The proposed intelligent techniques would benefit companies in enhancing product development capability in a shorter lifecycle. © 2007 IEEE.