Abstract:Based on the Flexible Job-Shop Scheduling Problem (FJSP),an improved particle swarm optimization algorithm is proposed,which is based on solution space distance clustering and variable neighborhood search.In this algorithm,a better solution to the problem is that the greedy strategy is adopted to introduce a variable neighborhood search method,adjusting machine location of the biggest key processes on the critical path,adjusting the relative position changes which is on the critical path.According to the space distance of the machining process,the K-means clustering is used to get the "excellent individuals" of machine processing,increasing the local search performance.At the same time,the speed of the particle swarm optimization is updated with the local self-adaptive stagnation strategy,and the relative position of the local segment could be kept unchanged.Through the experimental simulation,the optimization algorithm achieves good effectiveness,and the convergence speed is rapider and the performance is better compared with the general PSO algorithm.