Optimal Scheduling Strategy for Multiple Production Workshops Based on State Space Model

The aim of this study is to explore the optimal scheduling strategy of multiple production workshops based on a state space model to improve production efficiency, reduce system crash rate and optimize resource allocation. Through in-depth analysis of the running state of the production workshop, this study constructed a scheduling algorithm based on state space model (SAB-SSM), which could accurately describe and predict the production situation of the workshop and provide strong support for the optimization of scheduling strategies. The experimental data show that with the increase of iteration times, the SAB-SSM strategy shows a significant downward trend in the system collapse rate, and the overall collapse rate is significantly lower than the other three strategies. Specifically, the system crash rate of the SAB-SSM strategy is maintained at a low level at multiple iteration points, which shows its strong stability and optimization ability. Although Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Particle Swarm Optimization-Simulated Annealing (PSO-SA) strategies also show some optimization effects, their system crash rates fluctuate greatly and are significantly higher than those of SAB-SSM strategies at some iteration points. This suggests that these two strategies may have certain limitations when dealing with complex and changing production environments. Automated Guided Vehicle (AGV) strategy, as a comparison strategy, has a relatively high system breakdown rate, which further verifies the superiority of the SAB-SSM strategy in multiple production shop scheduling. The proposal and application of the SAB-SSM strategy also provide a new and efficient method to solve the scheduling problems of multiple production workshops. The experimental results not only validate the effectiveness and superiority of the SAB-SSM strategy, but also provide new directions and ideas for future research.