Simulation is often used for the evaluation of a Master Production Schedule (MPS). Also, the goal of this paper is the study of the design of a simulation model by reducing its complexity. According to theory of constraints, we want to build reduced models composed exclusively by bottleneck and, in order to do that, a neural network, particularly a multilayer perceptron, is used. Moreover, the structure of the network is determined by using a pruning procedure. This approach is applied to a sawmill flow shop case.