Approximate estimation of the product life cycle cost using artificial neural networks in conceptual design

Abstract

In order to improve the design of products and reduce design changes, cost, and time to market, life cycle engineering has emerged as an effective approach to address these issues in today's competitive global market. As over 70% of the total life cycle cost of a product is committed at the early design stage, designers can substantially reduce the life cycle cost Of products by giving due consideration to the life cycle implications of their design decisions. During the early design stages there may be competing requirements. In addition, detailed information is scarce and decisions must be made quickly. Thus, both the overhead in developing parametric life cycle cost (LCC) models for a wide range of concepts or requirements, and the lack of detailed information make the application of traditional LCC models impractical. A different approach is required because a traditional LCC method should be incorporated in the very early design stages. This paper explores an approximate method for providing the preliminary life cycle cost. Learning algorithms trained to use the known characteristics of existing products can perhaps allow the life cycle cost of new products to be approximated quickly, during the conceptual design phase without the overhead of defining new LCC models. Artificial neural networks are trained to generalise product attributes and life cycle cost data from preexisting LCC studies. Then, the product designers query the trained artificial model with new high-level product attribute data to obtain an LCC for a new product concept quickly. Foundations for the learning LCC approach are established, and then an application is provided. This paper has been developed to provide designers with LCC information to guide them in conceptual design.