Abstract
Simulation is essentially a trial-and-error approach, and is therefore, time-consuming and does not provide a method for optimization. Metamodelling techniques have been recently pursued in order to tackle these drawbacks. The main objective has been to provide robust, fast decision support aids to enhance the overall effectiveness of decision-making processes. This paper proposes an application of simulation metamodelling through artificial neural networks (ANNs). The building of the appropriate ANN model over second-order linear regression model and the reverse simulation metamodelling as simulation-optimization are assisted by the Neuro Software. To validate the proposed approach, a case study which is adopted from literature, deals with a lot sizing problem in make-to-order supply chain. The optimal solution is to determine the fixed lot size for each manufacturing product type that will ensure order mean flow time target. The comparative results with others metamodels techniques; illustrate the efficiency and effectiveness of the proposed approach.