A real manufacturing system faces lots of real world situations such as stochastic behaviors which lack of this issue is noticeable in previous researches. The aim of this paper is to find the optimum layout and the most appropriate handling transporters for the problem by a novel solving algorithm. The new model contains two objective functions including the material handling costs (MHC) and the complication time of jobs (make span). Real world situations such as stochastic processing times, random breakdowns and cross traffics among transporters are considered in this paper. Several experiment designs have been produced using DOE technique in simulation software and an artificial neural network (ANN) as a meta-model was used to estimate the objective functions in the meta-heuristic algorithms. A hybrid non-dominated sorting genetic algorithm (H-NSGA-II), is applied for optimization task. The proposed methodology is evaluated through a real case study. First, simulation model is validated by comparing with real data set. Then, the prediction performance of ANN is investigated. Finally, the ability of H-NSGA-II, in searching the solution space, is compared to the traditional NSGA-II. The results show that the proposed approach, combing simulation, ANN and H-NSGA-II, provides promising solutionsfor practical applications.