Optimization of Digital Twin Workshop Scheduling Problem Based on Genetic Algorithm

Abstract

Since traditional shop scheduling methods are mostly optimization methods based on scheduling rules and bottlenecks, it is difficult to obtain the global optimum when dealing with large-scale global optimization problems. As a result, an improved genetic algorithm based digital twin flexible job shop scheduling method is proposed. In the actual production process, genetic algorithm is used to generate the initial plan of flexible job shop scheduling; a digital twin flexible job shop scheduling model is established, with real-time interaction between virtual and physical workshops; the data resources and performance of the workshop are predicted in the virtual workshop; use the digital twin model is used to solve the impact of emergencies such as machine tool failures in the production environment on the production process of workpieces. Combining the workshop data with the workshop production scheduling process experiment, the experiment shows that the flexible job shop scheduling problem solved by genetic algorithm can effectively screen the key parameters, optimize the system performance, and effectively improve the on-time completion level of the workpiece.