Title: An intelligent system for estimating full product Life Cycle Cost at the early design stage

Authors: Haifeng Liu, Vivekanand Gopalkrishnan, Wee-Keong Ng, Bin Song, Xiang Li

Addresses: School of Computer Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Singapore. ' School of Computer Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Singapore. ' School of Computer Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Singapore. ' Singapore Institute of Manufacturing Technology, 71 Nanyang Drive, Singapore 638075, Singapore. ' Singapore Institute of Manufacturing Technology, 71 Nanyang Drive, Singapore 638075, Singapore

Abstract: It becomes clear for manufacturing companies that product Life Cycle Cost (LCC) is as crucial as product quality and functionality in deciding the success of a product in the market today. While LCC estimation has been seen as an aid to design decision making, the current cost estimating techniques suffer from drawbacks of low accuracy, restriction to specific lifecycle phases, and so on. We propose to build up an efficient and an intelligent LCC estimation system that aims to overcome the drawbacks of existing systems. As a generic system, it allows the users to alternatively apply the Activity-Based Costing (ABC) technique and state-of-the-art Machine Learning (ML) techniques to define and estimate various LCC elements depending upon the information available in a Product Lifecycle Database (PLD). The system consists of five major components: PLD, LCC template manager, ABC module, ML module and synthesiser. Through the proposed hybrid approach, the system considers all the aspects of the product lifecycle, and can be used at the very early stages of design and provide information to designers in a timely manner and in a form that can be understood and used.

Keywords: ABC; activity-based costing; ANN; artificial neural networks; intelligent systems; product lifecycle costs; LCC; regression models; SVM; support vector machines; product lifecycle management; PLM; early design; machine learning; product design.

DOI: 10.1504/IJPLM.2008.021436

International Journal of Product Lifecycle Management, 2008 Vol.3 No.2/3, pp.96 - 113

Available online: 27 Nov 2008 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article