A Reliability Approach on Redesigning the Warehouses in Supply Chain with Uncertain Parameters via Integrated Monte Carlo Simulation and Tuned Artificial Neural Network

In this paper, a reliability approach on reconfiguration decisions in a supply chain network is studied based on coupling the simulation concepts and artificial neural network. In other words, due to the limited budget for warehouse relocation in a supply chain, the failure probability is assessed for determining the robust decision for future supply chain configuration. Traditional solving approaches can find the failure probability in problems with small scenarios and limited dimensions, while huge number of scenarios needs to be optimized by an efficient approach in terms of accuracy in obtained solution and improving the computational time simultaneously. Hence, the tuned artificial neural network (ANN) is applied to forecast the failure probability while network's parameters and available budget are stochastic. The results show that simulation of problem using ANN can work appropriately in selecting the configuration with considerable less time consumption and forecasting error. Keywords: Tuned Artificial Neural Network, Reliability, Monte Carlo Simulation, Warehouse Relocation.