Research on Multi Agent Adaptive Optimization Scheduling for Production Operations in Mechanical Manufacturing Workshops

In the scheduling of production operations in mechanical manufacturing workshops, the workshop environment is complex, and dynamic situations such as orders, equipment failures, and emergency order insertion occur frequently. Traditional methods lack real-time perception and dynamic adjustment capabilities, making it difficult to quickly re plan scheduling plans in the face of dynamic disturbances in the production environment, resulting in cost consumption and low equipment load rates. Therefore, a multi-agent based adaptive optimization scheduling method is proposed. This method first constructs a framework for the interaction behavior mechanism of multi-agent systems, achieves information sharing and task collaborative allocation through standardized interaction, generates executable scheduling plans, and quickly triggers rescheduling when dynamic disturbances occur. After completing the interaction design, build an adaptive scheduling model to convert the weighted sum of time cost, processing cost, and non-conforming product loss into a single objective function, and set constraints such as equipment power limit and product qualification rate. For this complex model, differential evolution algorithm is used to solve it. Firstly, a set of scheduling parameters is defined and merged to generate an initial population. During evolution, the objective function values are dynamically evaluated to screen parameters. Later, a non dominated solution set management strategy is used to maintain diversity. After reaching the preset iteration times, the non dominated solution set is output as the optimal parameter combination, which is applied to the actual production process in the workshop to achieve adaptive optimization scheduling. The experimental results show that compared with traditional scheduling methods, this method reduces the cost of mechanical production operations by 28.1% and 33.3%, respectively. While ensuring maximum economic benefits, the comprehensive equipment full load rate reaches over 95%, effectively reducing resource waste.