不确定环境下再制造加工车间多目标调度优化方法  

Multi-objective optimization method of remanufacturing processing workshop scheduling under uncertain conditions

作　　者：张铭鑫[1] 张玺[1] 彭建刚[1] 陈鸿海[1] 

机构地区：[1]合肥工业大学机械与汽车工程学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2016年第4期433-439,542,共8页Journal of Hefei University of Technology：Natural Science

基　　金：国家重点基础研究发展计划(973计划)资助项目(2011CB013406)

摘　　要：针对再制造生产过程中工件的加工时间和成本不确定性调度问题,文章提出了一种不确定环境下再制造加工车间多目标调度优化方法。该方法采用模糊变量表示其不确定性参数,以最小化加工时间和成本为目标,在满足模糊交货期等约束条件下,构建了不确定环境下多目标决策的模糊机会约束规划模型,并提出了求解该模型的混合智能算法;应用模糊模拟技术产生样本数据,用于训练神经网络以逼近不确定函数;针对神经网络中存在收敛速度慢、容易陷入局部最优的缺点,应用改进的粒子群算法优化神经网路,将训练好的神经网路嵌入改进的遗传算法中求解调度模型。最后,通过仿真实例,验证该模型和算法的可行性。The multi-objective optimization method of remanufacturing processing workshop scheduling under uncertain conditions is proposed to solve the uncertainty problem of the processing time and cost for scheduling the remanufactured parts. In this method, the fuzzy variables are used to express the uncertain parameters, and the minimized processing time and cost are taken as the targets, and the fuzzy chance-constrained programming model with multi-objective decision under uncertain conditions is established, which can give solution through using the hybrid intelligence algorithm. To approach the uncertain function, the data generated from the fuzzy simulation are used for training neural net- works. The modified particle swarm algorithm is used for overcoming the defect of the low convergence rate and local optimization to optimize the neural networks. The well-trained neural networks are assigned to the modified genetic algorithm to establish the scheduling model. Finally, the feasibility of the model and algorithm is verified through the simulation example.

关 键 词：再制造 加工车间调度 模糊机会约束规划 混合智能算法 

分 类 号：TH186[机械工程—机械制造及自动化]