Abstract: For the multi-objective green flexible job shop scheduling problem, a multi-objective optimization model with minimizing the maximum completion time, total load and total energy consumption as objectives is established, and an improved NSGA-II multi-objective optimization algorithm with adaptive crossover mutation operator and learning mechanism is proposed. In this algorithm, the initial population is obtained by the non-dominated sorting selection strategy based on global, local and random selection through a two-level coding mechanism of machine and process. Hybrid crossover mutation strategy with adaptive operator is adopted to improve the global search performance of the algorithm. A distribution function is introduced to improve the elite preserving strategy and the diversity of population. Neighborhood search is carried out by learning mechanism to improve the local search capability of the algorithm. Finally, Brandimarte and Kacem data sets are used to test the algorithm. The results show that the improved NSGA-II algorithm for solving multi-objective green flexible job-shop scheduling problems has the advantages of high precision, fast convergence and good diversity of solution sets, which can guide the practical production decisions.