Abstract: Aiming at the stacking problem in the assembly process of the order-oriented mixed-flow assembly line workshop, the characteristics of this type of production line were analyzed, the theoretical scheduling optimization model and its algorithm were derived. A multi-objective scheduling optimization model was established with the punctuality of delivery time and the  as objective functions of component completion simultaneity. The particle swarm optimization algorithm was improved and the social particle swarm optimization algorithm based on attractor and natural selection was designed to solve the multi-objective optimization model. The information description method of particle swarm was studied, and a two-dimensional coding method combining process and workpiece information were proposed. The production information was transformed into programming language, so that MATLAB could be used for programming iterative calculation and simulation. The fitness value and iteration times of optimal solution of standard particle swarm optimization, social particle swarm optimization and hybrid particle swarm optimization were compared and analyzed. The superiority of the proposed algorithm was verified. The results indicate that the model is effective and reasonable in the order-oriented mixed-flow assembly scheduling problem. The design of social particle swarm optimization algorithm is fast and effective. The minimum machine utilization rate of the scheduling scheme can reach 72.49%, which solves the assembly stacking problem.

Key words:  order-oriented; mixed-flow assembly line; social particle swarm; two-dimensional coding; multi-objective optimization