This research investigates simulation-based Multi-Objective Optimization (MOO) in complex systems. The main goal of this research is to develop a metamodeling approach that can simultaneously simulate multiple conflicting objectives in complex systems. This research seeks to identify and analyze the challenges in optimizing complex systems and provide solutions to improve the performance and efficiency of these systems. By using meta models, an attempt is made to reduce computational time and increase the accuracy of optimization results. In this paper, MOO in the mining system of a copper mining complex is presented using the NBI optimization method and regression meta model. For this purpose, two objective functions are considered: maximizing the total extraction amount, which includes the sum of sulfide, oxide, low-grade ore and waste extractions in the mine, and minimizing the transportation travel time, subject to the constraints of storage capacity, transportation equipment and budget. The Central Composite Design (CCD) method is used to construct the Design of Experiments (DOE) for the design variables. Firstly, the design variables include the number of 120-ton, 240-ton, 35-ton and 100-ton trucks are considered. The amount of objectives in each design combination is considered as the response surface. The appropriate meta model to maximize the total extraction rate and minimize the transportation travel time, two modified nonlinear regression functions are determined. The accuracy of the models for selection is examined using PRESS and R2 statistics. Also, the most common PRESS error is used to validate the meta models. Then, the MOO problem is solved using the modified NBI method. Finally, the Pareto solutions using this approach are presented and discussed. This study investigates simulation-based MOO in complex systems and develops a metamodeling approach. The results show that the use of meta models can significantly reduce computational time and increase the accuracy of optimization results. By simulating multiple conflicting objectives simultaneously, this study identifies and analyzes the challenges in optimizing complex systems and provides effective solutions to improve the performance of these systems. In addition, the models developed in this study can help in optimal decision-making in various engineering and management fields and can be used as an efficient tool in solving complex problems. Ultimately, this study will not only contribute to a better understanding of optimization processes in complex systems, but will also pave the way for future research in this area.