基于改进粒子群算法作业车间调度问题的优化

针对作业车间调度问题,提出一种基于自适应权重和混沌的改进粒子群优化算法。构建以机器加工时间最短为优化目标的多约束作业车间调度模型,采用基于工序排列的编码方式得到粒子参数与工序序列的映射关系;基于自适应权重改进粒子群算法中的惯性系数和加速因子,使得算法可以根据适应度值动态调整参数因子;采用反向学习策略改善种群初始解的质量;引入莱维飞行、变邻域搜索、混沌,增强了算法的搜索能力,避免陷入局部最优解。试验结果表明:改进粒子群算法可以有效地提高粒子利用率,平衡全局搜索与局部搜索能力,改善传统粒子群算法易早熟的缺点,得到更优的解。

Optimization of job shop scheduling based on improved particle swarm optimization algorithm

An improved particle swarm optimization algorithm was proposed based on adaptive weights and chaos aiming at the job shop scheduling. A multiple constrained job shop scheduling model was built with the shortest machining time as the optimization goal. The mapping relationship between particle parameters and operation sequences was obtained by coding method based on ranked order value. The inertial coefficient and acceleration factor in the particle swarm optimization algorithm were improved based on the adaptive weights, so that the algorithm could dynamically adjust parameters based on the fitness value. The reverse learning was used to improve the quality of initial solution. Considering the problem of local optimum, some measures were used to enhance the search of algorithm, such as Lévy flight, variable neighborhood search and chaos. The results showed that improved particle swarm optimization could effectively improve utilization of particles, balance the global search and local search, avoid the premature convergence of the traditional particle swarm optimization algorithm, and get better results.