Adaptive neural control and learning of affine nonlinear systems

This paper presents deterministic learning from adaptive neural network control of affine nonlinear systems with completely unknown system dynamics. Thanks to the learning capability of radial basis function, neural network (NN), stable adaptive NN controller is designed for the unknown affine nonlinear systems. The designed adaptive NN controller is rigorously shown that learning of the unknown closed-loop system dynamics can be achieved during the stable control process because partial persistent excitation condition of some internal signals in the closed-loop system is satisfied. Subsequently, neural learning controller using the knowledge obtained from deterministic learning is constructed to achieve closed-loop stability and improve control performance. Numerical simulation is provided to show the effectiveness of the proposed control scheme.     

Deterministic learning and neural control of a class of nonlinear systems toward improved performance

A deterministic learning theory was recently presented which states that an appropriately designed adaptive neural controller can learn the system internal dynamics while attempting to control a class of nonlinear systems in normal form. In this paper, we further investigate deterministic learning of the class of nonlinear systems with relaxed conditions, and neural control of the class of system toward improved performance. Firstly, without the assumption on the upper bound of the derivative of the unknown affine term, an adaptive neural controller is proposed to achieve stability and tracking of the plant states to that of the reference model. When output tracking is achieved, a partial PE condition is satisfied, and deterministic learning from adaptive neural control of the class of nonlinear systems is implemented without the priori knowledge on the upper bound of the derivative of the affine term. Secondly, by utilizing the obtained knowledge of system dynamics, a neural controller with constant RBF networks embedded is presented, in which the learned knowledge can be effectively exploited to achieve stability and improved control performance. Simulation studies are included to demonstrate the effectiveness of the results.     

基于确定学习的机器人任务空间自适应神经网络控制

针对产生回归轨迹的连续非线性动态系统, 确定学习可实现未知闭环系统动态的局部准确逼近. 基于确定学习理论, 本文使用径向基函数(Radial basis function, RBF)神经网络为机器人任务空间跟踪控制设计了一种新的自适应神经网络控制算法, 不仅实现了闭环系统所有信号的最终一致有界, 而且在稳定的控制过程中, 沿着回归跟踪轨迹实现了部分神经网络权值收敛到最优值以及未知闭环系统动态的局部准确逼近. 学过的知识以时不变且空间分布的方式表达、以常值神经网络权值的方式存储, 可以用来改进系统的控制性能, 也可以应用到后续相同或相似的控制任务中, 节约时间和能量. 最后, 用仿真说明了所设计控制算法的正确性和有效性.     

Adaptive neural control of high-order uncertain nonaffine systems: A transformation to affine systems approach

This brief investigates the adaptive neural network (NN) control of a class of high-order nonaffine nonlinear systems with completely unknown dynamics. Since the control terms appear within the unknown nonlinearity, traditional control schemes and stability analysis are usually rendered extremely complicated. Our main contribution includes a novel system transformation that converts the nonaffine system into an affine system through a combination of a low-pass filter and state transformation. As a result, the state-feedback control of the nonaffine system can be viewed as the output-feedback control of an affine system in normal form. The transformed system becomes linear with respect to the new input while the traditional backstepping approach is not needed thus allowing the synthesis to be extremely simplified. It is theoretically proven that all the signals in the closed-loop system are uniformly ultimately bounded (UUB). Simulation results are provided to demonstrate the performance of the developed controller.     

Learning from NN output feedback control of nonlinear systems in Brunovsky canonical form

In this paper, we investigate the learning issue in the adaptive neural network (NN) output feedback control of nonlinear systems in Brunovsky canonical form with unknown affine term. With only output measurements, a high-gain observer (HGO) is employed to estimate the derivatives of the system output which may be associated with the generation of peaking phenomenon. The adverse effect of peaking on learning and its elimination strategies are analyzed. When the gain of HGO is chosen too high, it may cause the failure of learning from the unknown closed-loop system dynamics. Hence, the gain of HGO is not chosen too high to relieve peaking and guarantee the accuracy of the estimated system states. Then, learning from the unknown closed-loop system dynamics can be achieved. When repeating the same or similar control tasks, a neural learning controller is presented which can effectively recall and reuse the learned knowledge to guarantee the output tracking performance. Finally, simulation results demonstrate the effectiveness of the proposed scheme.     

基于ELM的一类MIMO仿射非线性系统的鲁棒自适应控制

针对一类多输入多输出(MIMO) 仿射非线性动态系统, 提出一种基于极限学习机(ELM) 的鲁棒自适应神经控制方法. ELM随机确定单隐层前馈网络(SLFNs) 的隐含层参数, 仅需调整网络的输出权值, 能以极快的学习速度获得良好的推广性. 在所提出的控制方法中, 利用ELM逼近系统的未知非线性项, 针对ELM网络的权值、逼近误差及外界扰动的未知上界值分别设计参数自适应律, 通过Lyapunov 稳定性分析可以保证闭环系统所有信号半全局最终一致有界. 仿真结果表明了该控制方法的有效性.

     

Adaptive backstepping controller design for nonlinear uncertain systems using fuzzy neural systems

In this article, we propose an adaptive backstepping control scheme using fuzzy neural networks (FNNs), ABC_FNN, for a class of nonlinear non-affine systems in non-triangular form. The nonlinear non-affine system contains the uncertainty, external disturbance or parameters variations. Two kinds of FNN systems are used to estimate the unknown system functions. According to the FNN estimations, the adaptive backstepping control (ABC_FNN) signal can be generated by backstepping design procedure such that the system output follows the desired trajectory. To ensure robustness and performance, a proportional-integral-surface function and robust controller are designed to improve the control performance. Based on the Lyapunov stability theory, the stability of a closed-loop system is guaranteed and the adaptive laws of the FNN parameters are obtained. This approach is also valid for nonlinear affine system with uncertainty or disturbance. The uncertainty and disturbance terms are estimated by FNNs and treated by the ABC_FNN scheme. Finally, the effectiveness of the proposed ABC_FNN is demonstrated through the simulation of controlling a nonlinear non-affine system and the continuously stirred tank reactor plant to demonstrate the performances of our approach.     

任意切换下高能随机系统的神经网络预设控制

针对一类不确定高能随机非线性系统,开展自适应神经网络backstepping控制研究,并保证在任意切换信号下的预设跟踪性能.该高能系统假定系统动态和任意切换信号未知.首先,利用预设性能控制,保证跟踪控制性能;其次,RBF神经网络用来克服未知系统动态,仅用到单一自适应更新参数,从而克服过参数问题;最后,基于公共的Lyapunov稳定性理论提出自适应神经网络控制策略,并减少了学习参数.最终结果表明所设计的公共控制器能保证所有闭环信号半全局最终一致有界,并能在任意切换下保证预设的跟踪性能.仿真结果进一步表明所提出方法的有效性.     

具有输入和输出约束的高阶随机系统神经网络控制

针对高阶非线性系统,开展自适应神经网络跟踪控制器设计,系统受到随机扰动的影响.首次把输入和输出约束问题引入到高阶系统的跟踪控制中,并假定系统动态是未知.首先借用高斯误差函数表达连续可微的非对称饱和模型以实现输入约束,和障碍Lyapunov函数保证系统输出受限;其次,针对高阶非线性系统,径向基函数(RBF)神经网络用来克服未知系统动态和随机扰动.在每一步的backstepping计算中,仅用到单一的自适应更新参数,从而克服了过参数问题;最后,基于Lyapunov稳定性理论提出自适应神经网络控制策略,并减少了学习参数.最终结果表明设计的控制器能保证所有闭环信号半全局最终一致有界,并能使跟踪误差收敛到零值小的邻域内.仿真研究进一步验证了提出方法的有效性.     

含未知信息的轮式移动机器人编队确定学习控制

本文研究含未知信息的轮式移动机器人(wheeled mobile robots,WMR)的编队控制问题.首先,基于领航–跟随法和虚拟结构法,将WMR编队控制问题转化为跟随机器人对参考虚拟机器人的跟踪控制问题.然后,利用径向基函数神经网络(radial basis function neural networks,RBF NN)对WMR的未知系统动态进行学习,以及根据李雅普诺夫稳定性理论设计了稳定的自适应RBF NN控制器和RBF NN权值估计的学习率.依据确定学习理论,闭环系统内部信号在对回归轨迹实现跟踪控制的过程中满足部分持续激励(persistent excitation,PE)条件.随着PE条件的满足,RBF NN权值估计收敛到其理想权值,实现了对未知闭环系统动态的准确学习.最后,利用学习结果设计了RBF NN学习控制器,保证了控制系统的稳定与收敛,实现了闭环稳定性和改进了控制性能,并通过仿真验证了所提控制方法的正确性和有效性.