Abstract: Aiming at the scheduling problem of sterilization process in medical equipment enterprises, a batch scheduling method of parallel machines with different capacities for sterilization process was proposed, and a batch scheduling model of parallel machines with different capacities was established, which aims to minimize the total delay time, minimize the total processing energy consumption and maximize the loading rate of sterilization cabinet. An improved NSGA-III algorithm was proposed to solve the model. In order to obtain a higher quality batch scheduling solution, EDT+MLC heuristic rules were used to generate the initial population in INSGA-III, and a local search strategy was designed to improve the search capability of the algorithm at the later stage of iteration. Finally, in order to verify the effectiveness and feasibility of the model and method, a comparative analysis was conducted between the simulation and the traditional scheduling method, and the results show that the model and algorithm have obvious advantages over the traditional scheduling method, which can provide a new idea for the actual production scheduling of medical enterprises.