Using system dynamics, neural nets, and eigenvalues to analyse supply chain behaviour - A case study

Full Citation
Rabelo, L., Helal, M., Lertpattarapong, C., Moraga, R., Sarmiento, A. 2008. Using system dynamics, neural nets, and eigenvalues to analyse supply chain behaviour - A case study. International Journal of Production Research, (46) 1: 51 – 71.

Abstract
This paper presents a new analysis approach to detect behavioural changes in manufacturing supply chains due to endogenous and/or exogenous influences and forecast the impact of these changes in the short and long term horizons. First a dynamic model of the supply chain is developed using system dynamics simulation. Afterward, Neural Networks, which can be encapsulated in software agents, are utilized to detect the changes at a very early stage so that an enterprise would have enough time to respond and counteract any unwanted situations. Then, principles of stability and controllability are used to apply and make modifications to the information and materials flows to adapt to the changes and avoid the expected behaviour. A case study of an actual electronics manufacturing company demonstrates the methodology developed.
Keywords: Supply chain modelling, System dynamics, Neural Nets, Eigenvalue analysis