A NEURAL-NETWORK-BASED APPROACH FOR ESTIMATING THE COST OF ASSEMBLY SYSTEMS

Any product that consists of two or more parts requires some form of a ssembly. The selection of the most appropriate assembly system for a p roduct or a family of similar products and the detailed design of the assembly system are important activities in the life cycle of many pro ducts. The selection of an assembly system is usually based on cost-be nefit analysis. The analysis requires engineering expertise and decisi on-support systems for data collection and data processing. This paper demonstrates the potential value of using neural networks in cost est imation as opposed to traditional regression or engineering analysis. A network architecture is proposed by which the expected cost of six m ajor types of assembly systems is estimated. The performances of the n etwork are compared to those of a regression model commonly used for c ost estimation. The neural network consistently outperformed the regre ssion model with respect to several performance measures.