摘要
针对两轮机器人传统PID控制器参数整定困难的问题,设计了一种神经元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。将设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。
To the problem that the parameters of classical PID controller two-wheeled robots cannot be easily adjusted,a PID controller based on neural network is presented.By making use of the self-learning and self-adaptive ability of neuron,the parameters of the controller can be easily adjusted on-line in real-time.The nonlinear model of two-wheeled robot is built,and the controll algorithm and the parameter algorithm learn are discussed.The controller is applied to the balancing control of two-wheeled robot and also a comparison is made,the simulation result show that the controller is correct and effective.The controller to the two-wheeled robot platform is applied and achieved good effect.
出处
《控制工程》
CSCD
北大核心
2011年第1期113-115,共3页
Control Engineering of China
基金
国家自然科学基金资助项目(60774077)
国家"863"计划资助项目(2007AA04Z226)
