气动人工肌肉手臂的神经网络Smith预估控制

Smith Prediction Control for the PAM Manipulator Using a Recurrent Neural Network

针对含时滞d的1关节气动人工肌肉(PAM)手臂,用三层递归神经网络(RNN),建立PAM手臂包含时滞的模型(即非线性Smith预估器),并超前d步预测PAM手臂的输出角度。将此超前d步的预测值作为反馈量,与设定值相比较得到的误差作为PID控制器输入量,实现Smith预估PID控制。同时每一步都用RNN模型当前时刻的输出值与PAM手臂当前时刻实际输出值之差的平方做为RNN权值的在线调整准则对RNN预测模型的权值进行在线调整,以自适应PAM手臂的不确定性和时变性。使用Matlab通过串口和研华亚当模块对实物PAM手臂进行控制,控制效果表明所提出的Smith预估PID控制算法比常规PID控制算法的性能有显著提高,证明所提出的算法是有效的和切实可行的。

It adopts a three-layer recurrent neural network（RNN） as a nonlinear smith predictor, to model a 1-joint pneumatic artificial muscle（PAM） manipulator, and to predict the d-step ahead output of the PAM manipulator. The difference between the desired output and the feedback variable, which is the d-step ahead predict output, is taken as the input of the PID controller. And the Smith predic- tion PID control is realized. At every sampling step, the weights of the RNN are adjusted by using the criterion of the square of the difference between the present output of the RNN model and the present actual output of the PAM manipulator so as to handle the uncer- tainty and time-variety of the PAM manipulator. Through a serial port and two ADAM modules, this paper uses a Matlab program to control the PAM manipulator. The operation results of the PAM manipulator show that the proposed method is effective and feasible compared with the traditional PID control.