混合EDA求解绿色机器人U型装配线平衡问题  

Hybrid EDA for Solving the Balancing Problem of Green Robotic U-shaped Assembly Line

作　　者：刘梦园 胡蓉[1] 钱斌[1] LIU Meng-yuan;HU Rong;QIAN Bin(School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《控制工程》2023年第2期307-315,共9页Control Engineering of China

基　　金：国家自然科学基金资助项目(51665025,61963022)。

摘　　要：针对带序相关约束的绿色机器人第2类U型装配线问题(GRSDUALBP-2),建立了以同时最小化节拍时间和能耗为优化目标的数学模型,并提出一种混合分布估计算法(HEDA)进行求解。首先,在算法编码解码阶段考虑工序与机器人分配的协同优化,设计一种操作分配规则以提高解码效率;然后,在算法优化阶段采用基于概率模型的分布估计算法(EDA),以有效积累和学习优质解信息,并设计3种邻域策略以进一步提高算法局部搜索性能;最后,通过仿真实验与算法对比,验证了HEDA是求解GRSDUALBP-2的有效算法。For the green robotic sequence-dependent type-2 U-shaped assembly line balancing problem(GRSDUALBP-2), a mathematical model with the objective of minimizing both cycle time and energy consumption is established, and a hybrid estimation of distribution algorithm(HEDA) is proposed to solve the problem. Firstly, consider the collaborative optimization of process and robot allocation in the algorithm encoding and decoding stage, design an operation allocation rule to improve decoding efficiency. Then, in the algorithm optimization stage, a probability model-based estimation of distribution algorithm(EDA) is used to effectively accumulate and learn high-quality solution information, and three neighborhood strategies are designed to further improve the local search performance of the algorithm. Finally, the simulation experiment and algorithm comparison verify that HEDA is an effective algorithm to solve GRSDUALBP-2.

关 键 词：第2类U型装配线 混合分布估计算法 序相关 多目标优化 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]