Maintenance Scheduling of Semiconductor Production Equipment Based on Particle Swarm Optimization

In this paper, we study the problem of wafer production equipment maintenance scheduling. In order to shorten the maintenance time and ensure the continuity of the production, we proposed an improved particle swarm optimization (PSO) algorithm. The proposed hybrid algorithm is based on standard PSO, and integrated PSO with Simulated Annealing (SA) with probabilistic jump ability to avoid PSO trapping in local optimum. Besides, adaptive adjustment method of inertia weight is used, and add disturbance to the velocity update formula of the algorithm to ensure the fast optimization of particles in the early stage and avoid premature convergence. Experiment results indicate that the proposed algorithm is significant in terms of the maintenance time and downtime loss compared to conventional approaches.