基于神经网络的总装机架翻转设备同步控制研究  

Research on Synchronization Control of General Assembly Rack Turning Equipment Based on Neural Network

作　　者：胡懿宸 苏东海[1] 杨皓奇 罗擎 HU Yichen;SU Donghai;YANG Haoqi;LUO Qing(School of Mechanical Engineering,Shenyang University of Technology,Shenyang 110870,China)

机构地区：[1]沈阳工业大学机械工程学院,沈阳110870

出　　处：《机械工程师》2021年第10期72-73,77,共3页Mechanical Engineer

摘　　要：总装机架翻转设备采用两套独立的阀控液压马达系统。为减小两液压马达间的同步误差,文中提出一种交叉耦合同步驱动控制策略,并采用单神经元神经网络控制器对PID控制进行学习和改进。在加入机架刚性连接的情况下,通过建模和仿真验证,基于单神经元神经网络的阀控液压马达系统可以有效减小液压马达之间的角度差值,增加同步控制精度。Two independent valve-controlled hydraulic motor systems are used in general assembly rack turning equipment.In order to reduce the synchronization error between the two hydraulic motors,this paper proposes a cross-coupling synchronization drive control strategy,and uses a single neuron neural network controller to learn and improve PID control.With the addition of rack rigid connections,modeling and simulation verify that a valve-controlled hydraulic motor system based on a single neuron neural network can effectively reduce the angle difference between the hydraulic motors and increase the synchronization control accuracy.

关 键 词：阀控液压马达 同步控制 神经网络 单神经元 

分 类 号：TH137[机械工程—机械制造及自动化]