摘要
本文提出了一种模糊神经网络控制器,该控制器用于工业机器人关节驱动的位置控制,克服了传统PID很难达到对非线性以及不确定因素的控制效果和简单模糊控制不能完全消除稳态误差的缺点,通过神经网络对模糊规则的学习优化,提高了机器人关节末端位置精度,具有较好控制效果。
A kind of fuzzy-neural network control is proposed in the paper. It is used to joint actuation for robotic manipulators position servo system. It overcomes some defects of traditional PID control which is difficult to control nonlinear and uncertainties event and simply fuzzy control which can not remove steady error thoroughly. The control accuracy of position was improved by learning and optimizing fuzzy rules. The simulation and experimental results show that this method improves the control performance of system and has preferable effects.
出处
《微计算机信息》
北大核心
2006年第01Z期215-217,共3页
Control & Automation
基金
黑龙江省教育厅基金资助项目:1055HQ036
关键词
模糊神经网络
传统PID控制
补偿控制
fuzzy-neural network
traditional PID control
Compensation control