A Multi-Objective Optimization Model Using Improved NSGA-II for Optimizing Metal Mines Production Process

Production process optimization is an indispensable step in industrial production. The optimization of the metal mines production process (MMPP) can increase production efficiency and thus promote the utilization rate of the metal mineral resources in the frame work of sustainable development. This study establishes a multi-objective optimization model for optimizing the MMPP by maximizing economic and resource benefits. To get better non-dominated Pareto optimal solutions, an improved non-dominated sorting genetic algorithm-II (NSGA-II) is proposed. The symmetric Latin hypercube design is adopted to generate the initial population with high diversity. The mutation and crossover of the differential evolution algorithms are introduced into the NSGA-II to replace the genetic algorithm for improving convergence. The control parameters of the mutation scale factor and crossover rate of the differential evolution algorithm are adaptively adjusted to improve the diversity of candidate solutions. To verify the performance of the improved NSGA-II, four test functions from the ZDT series functions are chosen for experimentation. The experimental results indicate that the improved NSGA-II outperforms the comparative algorithms in diversity and convergence. Moreover, the application of the proposed method to the Yinshan copper mines shows that the improved NSGA-II is effective in optimizing the MMPP and a reliable method in promoting utilization rate of metal mineral resources in the framework of sustainable development.