基于优化模糊RBF神经网络的挖掘机铲斗轨迹控制研究  

Research on Excavator Bucket Trajectory Control Based on Optimization of Fuzzy RBF Neural Network

作　　者：周洲[1,2] 杜常清 邹斌 徐玉兵[2,3] ZHOU Zhou;DU Chang-qing;ZOU Bin;XU Yu-bing(School of Automotive Engineering,Wuhan University of Technology,Wuhan 430070,China;Hubei Key Laboratory of Hyundai Automotive Parts Technology,Wuhan University of Technology,Wuhan 430070,China;Hubei Collaborative Innovation Center of Auto Parts Technology,Wuhan 430070,China)

机构地区：[1]武汉理工大学汽车工程学院,武汉430070 [2]现代汽车零部件技术湖北省重点实验室(武汉理工大学),武汉430070 [3]汽车零部件技术湖北省协同创新中心,武汉430070

出　　处：《武汉理工大学学报》2023年第10期160-168,共9页Journal of Wuhan University of Technology

基　　金：国家重点研发计划(2020YFB1709900)。

摘　　要：针对挖掘机电液伺服控制系统中存在的非线性和时变性问题,本文结合RBF神经网络和模糊控制各自的优点提出一种基于模糊RBF神经网络PID控制方法。利用K-means层次聚类法确定模糊神经网络的结构参数,并采用改进SSA算法优化训练模糊神经网络。本文还建立了挖掘机铲斗系统的AMESim模型和电控系统的Simulink控制策略模型,并进行联合仿真分析。仿真结果表明:与一般模糊RBF神经网络相比,本文优化后的模糊RBF神经网络在铲斗系统空载时,能将控制精度提升33.7%,在铲斗系统满载时,能将控制精度提升36.2%。This paper presents a fuzzy RBF neural network PID controller for the electro-hydraulic servo system of excavators,which combines the merits of RBF neural network and fuzzy control to cope with the nonlinearity and time-varying characteristics of the system.The K-means hierarchical clustering method is applied to determine the structure parameters of the fuzzy neural network,and the training of the network is optimized by using an improved SSA algorithm.Moreover,this paper builds an AMESim model for the excavator bucket system and a Simulink model for the electric control strategy,and performs a joint simulation analysis.The simulation results show that compared with the general fuzzy RBF neural network,the optimized fuzzy RBF neural network can improve the control accuracy by 33.7%when the bucket system is unloaded and 36.2%when the bucket system is fully loaded.

关 键 词：模糊RBF神经网络 麻雀搜索算法 铲斗轨迹控制 电液伺服系统 

分 类 号：TU621[建筑科学—建筑技术科学]