A Case Study on Target Cost Estimation Using Back-Propagation and Genetic Algorithm Trained Neural Networks
Journal of Cost Analysis and Parametrics
Cost estimation of new products has always been difficult as only few attributes will be known. In these situations, parametric methods are commonly used using a priori determined cost function where parameters are evaluated from historical data. Neural networks, in contrast, are nonparametric, i.e., they attempt to fit curves without being provided a predetermined function. In this article, this property of neural networks is used to investigate their applicability for cost estimation of certain major aircraft subassemblies. The study is conducted in collaboration with an aerospace company located in Montreal, Canada. Two neural network models, one trained by the gradient descent algorithm and the other by genetic algorithm, are considered and compared with one another. The study, using historical data, shows an example for which the neural network model trained by genetic algorithm is robust and fits well both the training and validation data sets.
Dr. Adil Salam currently manages 4 categories of indirect spend for the Canadian cross-divisional Purchasing team for the Novartis, a Pharmaceutical company headquartered in Basel, Switzerland. He received his Ph.D. degree in Mechanical Engineering (Thesis: Lean Accounting: Measuring Target Costs) from Concordia University, Montreal, Canada in 2012. He also received his Masters and Bachelor degrees in Industrial from Concordia University. His current research is in the domains of Lean Accounting, Target Costing, and Design Effort Estimation.
Dr. Fantahun M. Defersha received his PhD in Mechanical Engineering (Thesis area – Manufacturing System) in 2006 from Concordia University, Montreal, Canada. He is currently an assistant professor in the School of Engineering, University of Guelph, Guelph, Ontario, CANADA. His research interests are in Manufacturing system analysis, ﬂexible and cellular manufacturing systems, reconﬁgurable machine tools and reconﬁgurable manufacturing systems, part sequencing and scheduling, production and inventory planning, lean manufacturing, productivity improvement and cost analysis, artiﬁcial intelligence, and meta-heuristics.
Dr. Nadia F. Bhuiyan is an Associate Professor in the Department of Mechanical and Industrial Engineering at Concordia University (Montreal, Canada). She is also the Associate Director of the Concordia Institute of Aerospace and Design Innovation. Dr. Bhuiyan’s research focuses on product development processes and lean, dealing with the design, development, production, and distribution of goods and services, with a focus on emerging tools and techniques for integrating design and manufacturing to improve process performance.
Dr. M. Chen is a Professor in the Department of Mechanical and Industrial Engineering, Concordia University. He received his B.Eng. and MS degrees in Industrial Management Engineering from Beijing University of Aeronautics and Astronautics, Beijing, China. He received his Ph.D. degree in Industrial Engineering from University of Manitoba in 1991. He was a faculty member at the University of Regina before he joined Concordia in 1999. His research is in manufacturing system and process optimization as well as in supply chain management.