Monitoring and Early-Warning of the Supply Chain by Using System Dynamics and Neural Networks

Effective management of a supply chain requires the ability to detect unexpected variations at an early stage, which brings the possibility of taking preventive decisions to mitigate the variations. This paper proposes a methodology that monitors the dynamic trends of supply chain performance indicators, and gives early-warnings for potential risks. Initially, a supply chain model is built using system dynamics. Then, based on this model, a neural network which can be trained to adapt to the real supply chain is developed. Acting as the kernel of monitoring and early-warning module, the neural network can make online predictions of dynamic trend of indicators so that an enterprise would have enough time to respond to any unwanted situations. The architecture of monitoring and early-warning module is proposed and a case study of the manufacturing industry is presented to illustrate the methodology and architecture.