Intelligent Manufacturing Flexibility Scheduling Optimization Based on Hybrid NSGA-II Algorithm

The flexible job-shop problem is one of the classical problems that have attracted much attention in the field of industrial automation and control. For the Multi-Objective Flexible Job-shop Scheduling Problem (MOFJSP), this paper proposes a hybrid particle swarm Non-dominated Sorting Genetic Algorithm II (NSGA-II) to solve the problem. The high-quality solution of the problem is obtained through particle swarm optimization as part of the initial population of NSGA-II, and an elite strategy is used to prevent the loss of outstanding individuals by mixing all the individuals of the parent and the offspring in a non-dominated sorting method. This approach not only facilitates automation in manufacturing and production but also enhances the control and optimization of complex systems. Furthermore, integrating intelligent transportation systems and the Internet of Things (IoT) into the scheduling process ensures real-time fault diagnosis and fault-tolerant control, thereby improving the overall efficiency and reliability of the production system. The experimental results show that the hybrid optimization approach combining PSO and NSGA-II exhibits superior performance in solving MOFJSP. This research contributes to the advancement of cyber-physical systems and the automation of complex industrial processes.