Prediction of the life cycle cost using statistical and artificial neural network methods in conceptual product design

Abstract

During the early design stages, over 70% of the total life cycle cost (LCC) of a product is committed and there may be competing concepts with dramatic differences. Additionally, both the lack of detailed information, and the overhead in developing parametric LCC models for a range of concepts make the application of traditional LCC models impractical. This paper describes the development of predictive models for the product LCC during conceptual design. An artificial neural network (ANN) model to predict the product LCC is developed and compared with a conventional statistical model -- a regression model. The results show that the ANN model outperforms the traditional regression model used for predicting the product LCC.