Learning From Adaptive Neural Dynamic Surface Control of Strict-Feedback Systems
Learning From Adaptive Neural Dynamic Surface Control of Strict-Feedback Systems
复制标题
从严格反馈系统的自适应神经动态表面控制中学习
DOI：
10.1109/tnnls.2014.2335749
复制
发表时间：
2015-06
影响因子：
10.4
通讯作者：
Cong Wang
中科院分区：
文献类型：
--
作者：
Min Wang;Cong Wang
学习在自主控制系统中起着至关重要的作用。然而，如何实现非线性系统在非平稳环境下的学习是一个具有挑战性的问题。针对一类n阶严格反馈系统，提出了一种基于自适应动态面控制（DSC）技术的学习方法，实现了类人的“干中学”和“用所学知识做”的能力.为了实现学习，本文首先提出了稳定的自适应DSC与辅助一阶滤波器，它确保了所有的信号在闭环系统的有界性和跟踪误差在有限时间内收敛。在DSC的帮助下，滤波器输出变量的导数被用作神经网络（NN）的输入，而不是传统的中间变量。因此，所提出的自适应DSC方法大大降低了神经网络输入的维数，特别是对于高阶系统。在稳定的DSC设计之后，我们将稳定的闭环系统分解成一系列线性时变扰动子系统。使用递归设计，神经网络输入变量的递归属性很容易验证，因为复杂性是克服使用DSC。随后，径向基函数神经网络的部分持续激励条件得到满足。通过结合状态变换，闭环系统动力学的精确近似递归地实现在局部区域沿着递归轨道。然后，学习控制方法，利用学习到的知识，提出了实现闭环稳定性和改善的控制性能。仿真结果表明，该方法不仅可以重用学习到的知识，获得更好的控制性能，具有更快的跟踪收敛速度和更小的跟踪误差，而且由于减少了神经网络输入变量的数量和复杂度，大大减轻了计算负担。
Learning plays an essential role in autonomous control systems. However, how to achieve learning in the nonstationary environment for nonlinear systems is a challenging problem. In this paper, we present learning method for a class of nth-order strict-feedback systems by adaptive dynamic surface control (DSC) technology, which achieves the human-like ability of learning by doing and doing with learned knowledge. To achieve the learning, this paper first proposes stable adaptive DSC with auxiliary first-order filters, which ensures the boundedness of all the signals in the closed-loop system and the convergence of tracking errors in a finite time. With the help of DSC, the derivative of the filter output variable is used as the neural network (NN) input instead of traditional intermediate variables. As a result, the proposed adaptive DSC method reduces greatly the dimension of NN inputs, especially for high-order systems. After the stable DSC design, we decompose the stable closed-loop system into a series of linear time-varying perturbed subsystems. Using a recursive design, the recurrent property of NN input variables is easily verified since the complexity is overcome using DSC. Subsequently, the partial persistent excitation condition of the radial basis function NN is satisfied. By combining a state transformation, accurate approximations of the closed-loop system dynamics are recursively achieved in a local region along recurrent orbits. Then, the learning control method using the learned knowledge is proposed to achieve the closed-loop stability and the improved control performance. Simulation studies are performed to demonstrate the proposed scheme can not only reuse the learned knowledge to achieve the better control performance with the faster tracking convergence rate and the smaller tracking error but also greatly alleviate the computational burden because of reducing the number and complexity of NN input variables.
登录
查看更多内容
DOI：
10.1142/3774
发表时间：
1999-02
期刊：
--
影响因子：
--
作者：
S. Ge;Tong-heng Lee;C. Harris
通讯作者：
S. Ge;Tong-heng Lee;C. Harris
DOI：
10.1109/cdc.2003.1271916
发表时间：
2003-12
期刊：
42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)
影响因子：
--
作者：
Cong Wang;D. Hill
通讯作者：
Cong Wang;D. Hill
不确定MIMO纯反馈非线性系统的基于观测器的自适应模糊反步输出反馈控制
影响因子：
11.9
作者：
Tong, Shaocheng;Li, Yongming;Shi, Peng
通讯作者：
Shi, Peng
影响因子：
6.8
作者：
S. Yoo;Jin Bae Park;Y. Choi
通讯作者：
S. Yoo;Jin Bae Park;Y. Choi
影响因子：
6.8
作者：
K. Fu
通讯作者：
K. Fu