神经元PID控制器在两轮机器人控制中的应用.pdf

20 11年 1月 控 制 工 程 Jan. 2 0 1 1 第18卷第1期 ControlEngineering of China Vo.l 18, No. 1 : 2011) PID 孙 亮, 孙启兵 ( , 100124) : 针对两轮机器人传统 PID控制器参数整定困难的问题, 计了一种神经元 PID控 制器该控制器利用神经元的自学习和自适应能力, 在线实时调整控制器各项参数建立了两 轮机器人的非线性模型, 讨论了神经元 PID 控制系统的结构及其控制算法和各项控制器参数 的学习算法将 计的控制器其应用于两轮机器人的平衡控制中, 并且与传统 PID 控制器进 行了比较, 仿真结果验证了控制器的正确性和有效性将该控制器应用于两轮机器人物理系 统, 取得了良好效果 : 两轮机器人; 自适应; 神经元 PID : TP 273 : pplication ofNeuralPID Controller to TwowheeledRobotControl S UN L iang, SUN Q ibing ( College of Electronic Information and Control Engineering, BeijingU niversity ofTechnology, Beijing 100124, China) Abstract: To the problem that the parameters ofclassicalPID controller twowheeled robots cannotbe easily adjusted, a PID controller based on neural network is presented. Bymaking use of the selflearning and selfadaptive ability ofneuron, the parameters of the con troller can be easily adjusted online in realtmi e. The nonlinearmodelof twowheeled robot is built, and the controll algorithm and the parameter algorithm learn are discussed. The controller is applied to the balancing controlof twowheeled robot and also a comparison is made, the smi ulation result show that the controller is correct and effective. The controller to the twowheeled robot platform is applied and achieved good effect. K ey words: wt owheeled robot; selfadaptive; PID controller 1 2 , [3] [4]