Robust Control of PM Spherical Stepper Motor Based on Neural Networks

There are many uncertainties and disturbances in the real dynamic system of a spherical stepper motor that make traditional control methods with lower precision, such as uncertain changes of magnetic field, load, and friction that generate speed ripple and deteriorate the 3-D tracking performance of the spherical motor system. In this paper, an available method is proposed to solve them by using neural networks (NNs) and a robust control scheme for improving the performance. First, a simplified torque calculation model based on finite-element method results can guarantee quick prediction of electromagnetic torque with lower error. Thus, the system model considering the friction, load, and disturbances is developed. Second, a robust NN (RNN) control scheme is presented to eliminate uncertainties to improve the tracking robust stability and overcome the undesired influence of uncertainties based on the nonlinear system dynamic model under continuous-trajectory tracking mode. Finally, as an example, the step-response and continuous-tracking processes of the motor using an RNN controller are simulated, and experiments, including the tracking using RNN proportional–differential control, are carried out to confirm the usefulness of the proposed control scheme. The simulation and experimental results of the proposed control scheme on the spherical stepper motor system demonstrate the effectiveness on satisfactory tracking performance.      

SDH系统E1接口定时的高质量恢复

SDH传输网中由指针调整带来的低频抖动和漂移已经成为SDH传输网与其它传输网互通的障碍.这一问题可以通过在SDH系统的边界支路输出口处采用极低带宽的锁相环对SDH网络指针调整带来的抖动和漂移进行平滑来得到改善和解决.本文介绍了一种捕捉速度快、带宽窄、适合于多支路大规模集成的用于SDH系统E1支路接口的二阶全数字锁相环路.     

改进型BP神经网络的非线性多模型自适应控制

针对一类参数未知的非线性离散系统,提出一种基于改进型BP神经网络的多模型控制方法.首先将非线性系统表示为线性部分和非线性部分.当非线性部分对系统影响较小时,则直接采用基于固定模型和自适应模型而设计的鲁棒控制器对系统进行控制;而当非线性部分对系统影响较大时,则采用基于改进的BP神经网络的自适应控制.其次,利用切换准则对控...     

基于LMI的非线性模糊脉冲奇异摄动系统的鲁棒模糊控制

通过推广一般T-S模糊模型定义了一类非线性模糊脉冲奇异摄动系统,基于线性矩阵不等式(LMI)方法提出一种鲁棒模糊控制新方案,采用并行分布补偿(PDC)的基本思想设计状态反馈控制器,并利用Lyapunov理论证明闭环系统全局指数稳定.最后基于LMI方法,将鲁棒模糊控制器的设计问题转化为线性矩阵不等式问题(LMIP).仿真结果表明了该方法的有效性.     

Nonlinear System Control Using Adaptive Neural Fuzzy Networks Based on a Modified Differential Evolution

This study presents an adaptive neural fuzzy network (ANFN) controller based on a modified differential evolution (MODE) for solving control problems. The proposed ANFN controller adopts a functional link neural network as the consequent part of the fuzzy rules. Thus, the consequent part of the ANFN controller is a nonlinear combination of input variables. The proposed MODE learning algorithm adopts an evolutionary learning method to optimize the controller parameters. For design optimization, a new criterion is introduced. A hardware-in-the loop control technique is developed and applied to the designed ANFN controller using the MODE learning algorithm. The proposed ANFN controller with the MODE learning algorithm (ANFN-MODE) is used in two practical applications—the planetary-train-type inverted pendulum system and the magnetic levitation system. The experiment is developed in a real-time visual simulation environment. Experimental results of this study have demonstrated the robustness and effectiveness of the proposed ANFN-MODE controller.      

Adaptive Control of Mechanical Systems Using Neural Networks

In this paper, we consider the decentralized adaptive control design problem for uncertain mechanical systems, where uncertainty may arise due to isolated subsystem and/or interconnections among subsystems. Radial basis function neural networks are used to approximate the nonlinear functions to include both dynamic and interconnection uncertainties in each subsystem. The stability of the thus designed control system can be guaranteed by a rigid proof. Finally, a simulation example is given to illustrate the effectiveness of the proposed algorithm.     

基于神经网络仿射非线性系统滑模自适应控制

研究了一类单输入单输出仿射非线性系统的自适应控制问题.采用反馈线性化方法设计控制器,用神经网络逼近系统中的未知非线性函数,并在神经网络权值的自适应律中引入权值误差的概念,以改善系统的动态性能.同时采用滑模控制方法设计补偿器,提高了系统的鲁棒性.理论分析及仿真结果表明,所设计的控制器,不仅能解决该系统的轨迹跟踪控制问题,...     

Robust Non-Fragile Guaranteed Cost Control for Nonlinear Time Delay Discrete-Time Systems Based on T-S Model

This paper concerns the robust non-fragile guaranteed cost control for nonlinear time delay discrete-time systems based on Takagi-Sugeno （T-S） model. The problem is to design a guaranteed cost state feedback controller which can tolerate uncertainties from both models and gain variation. Sufficient conditions for the existence of such controller are given based on the linear matrix inequality （LMI） approach combined with Lyapunov method and inequality technique. A numerical example is given to illustrate the feasibility and effectiveness of our result.     

基于观测器的含扰动Lipschitz非线性系统鲁棒控制

针对一类含扰动Lipschitz非线性系统的鲁棒控制问题进行了研究,讨论了基于观测器的非线性系统鲁棒控制问题.首先,对满足Lipschitz条件的非线性系统构造出了状态观测器;其次,考虑到系统中的扰动项,根据Lyapunov理论分两种情况以线性矩阵不等式的形式给出基于状态观测器的控制器存在的充分条件,得到了观测器增益矩...     

混沌光学系统的神经网络自适应控制研究

提出一种用于混沌光学系统控制的神经网络自适应控制技术。以一前向神经网络作为受控混沌光学系统的系统辩识器，由此神经网络系统辩识器与受控混沌光学系统输出差值作为负反馈对受控混沌光学系统控制参数进行调整达到控制目的。由于所使用神经网络系统辩识器在常规ＢＰ算法的支持下可从受控混沌光学系统的输出时间序列进行动力学模型重构，因而特别适用于对未知动力学表述的混沌光学系统进行控制。以对布喇格声光双稳混沌系统的系统辩识及自适应控制为例，对此神经网络自适应控制技术可行性进行了示例证明。     

基于在线神经网络的自适应鲁棒飞行控制

一般的自适应神经网络,因为没有长期学习性与全局适应性,只能适应当前的瞬时状态,满足不了导弹高精度飞行的要求.基于李亚普诺夫稳定理论和神经网络的非线性函数的拟合特性,设计了具有背景学习功能的在线自适应神经网络鲁棒控制器.首先分析了逆误差产生的原因,然后用神经网络来补偿系统逆模型误差,并利用李亚普诺夫稳定性理论推导了在线网...     

Congestion Control for ATM Networks Based on Diagonal Recurent Neural Networks

ＣｏｎｇｅｓｔｉｏｎＣｏｎｔｒｏｌｆｏｒＡＴＭＮｅｔｗｏｒｋｓＢａｓｅｄｏｎＤｉａｇｏｎａｌＲｅｃｕｒｅｎｔＮｅｕｒａｌＮｅｔｗｏｒｋｓＨｕａｎｇＹｕｎｘｉａｎＹａｎＷｅｉ（ＡｉｒＦｏｒｃｅＩｎｓｔｉｔｕｔｅｏｆＭｅｔｅｏｒｏｌｏｇｙ，Ｎａｎｊｉｎｇ...     

一种改进的非线性MIMO系统鲁棒自适应反推控制

针对一类具有模型不确定性和未知外界干扰的严反馈非线性MIMO系统,提出一种基于RBF神经网络和反推控制的鲁棒控制律设计方法。应用RBF神经网络在线逼近模型的不确定性,引入低通滤波器消除反推设计方法中由于对虚拟控制反复求导而导致的复杂性问题。同时,在控制律设计中引入一个自适应鲁棒控制项来补偿神经网络逼近误差和未知外界干扰的影响,提高系统的鲁棒性,使整个系统获得更好的跟踪控制性能。基于Lyapunov稳定性定理证明了闭环系统的所有信号半全局一致终结有界;通过适当选择设计参数及初始化误差变量,跟踪误差可收敛到原点的一个任意小邻域内,且跟踪误差的L∞跟踪性能被保证。数值仿真验证了方法的有效性。     

一种新型径向基函数神经网络的非线性系统逼近

讨论了一种新的、正弦型径向基函数(SRBF)神经网络，并用来逼近n堆连续函数。该SRBF所采用的n堆正弦型的基函数是光滑的,并且是致密的。该SRBF网络的权因子是输入的低阶多项式函数。本文给出的一种简单计算程序，显著地降低了网络训练和计算时间。并且由于SRBF的基函数可以非均匀的量化格点为中心。因而降低了网络所需存储的样本数，网络的输出及其一阶导数都是连续的。对于非线性系统。该SRBF网络在系统定义城内的逼近是精确的。并且在存储参数的个数上是最优的。通过实例仿真，证明该方法步骤简单,训练速度快，精度也很理想。     

一类非线性不确定时滞系统鲁棒容错控制

研究一类不确定非线性时滞系统的鲁棒容错控制问题.针对不确定非线性时滞系统,基于执行器连续型增益故障模式,利用Lyapunov-Krasovskii泛函方法和线性矩阵不等式方法,推导了当一类非线性不确定系统满足一定范数有界条件时,闭环系统时滞无关鲁棒容错控制器存在的充分条件,并给出了状态反馈鲁棒容错控制器的设计方法.将所设计的状态反馈控制方法应用于某一非线性不确定时滞系统,仿真结果表明设计的控制器不仅使得该故障系统对于执行器故障具有完整性,并且能达到给定的H∞性能指标,从而验证了所提出方法的可行性和有效性.     

Robust Passivity and Passification for a Class of Singularly Perturbed Nonlinear Systems with Time-Varying Delays and Polytopic Uncertainties via Neural Networks

This paper investigates the problem of robust passivity and passification for a class of singularly perturbed nonlinear systems (SPNS) with time-varying delays and polytopic uncertainties via neural networks. By constructing a proper functional and the linear matrix inequalities (LMIs) technique, some novel sufficient conditions are derived to make SPNS passive. The allowable perturbation bound ξ ^? can be determined via certain algebra inequalities, and the proposed controller based on neural network will make SPNS with polytopic uncertainties passive for all ξ∈(0,ξ ^?). Finally, a numerical example is given to illustrate the theoretical results.     

PID-Like Neural Network Nonlinear Adaptive Control for Uncertain Multivariable Motion Control Systems

A mix locally recurrent neural network was used to create a proportional-integral-derivative (PID)-like neural network nonlinear adaptive controller for uncertain multivariable single-input/multi-output system. It is composed of a neural network with no more than three neural nodes in hidden layer, and there are included an activation feedback and an output feedback, respectively, in a hidden layer. Such a special structure makes the exterior feature of the neural network controller able to become a P, PI, PD, or PID controller as needed. The closed-loop error between directly measured output and expected value of the system is chosen to be the input of the controller. Only a group of initial weights values, which can run the controlled closed-loop system stably, are required to be determined. The proposed controller can update weights of the neural network online according to errors caused by uncertain factors of system such as modeling error and external disturbance, based on stable learning rate. The resilient back-propagation algorithm with sign instead of the gradient is used to update the network weights. The basic ideas, techniques, and system stability proof were presented in detail. Finally, actual experiments both of single and double inverted pendulums were implemented, and the comparison of effectiveness between the proposed controller and the linear optimal regulator were given.     

基于混合观测器的非线性系统的脉冲控制

该文针对基于有限状态自动机的非线性脉冲混合动态系统,设计一种新的脉冲混合观测器,然后应用有限状态自动机理论和Backstepping方法设计了基于混合观测器的脉冲输出反馈控制器,并构造了多Lyapunov函数,通过混合系统的渐近稳定性理论以及多Lyapunov函数法给出整个闭环系统渐近稳定的充分条件,数值仿真验证了该控制器的有效性。     

实现标量混沌信号同步控制的神经网络方法

本文给出了一种利用线性输出神经网络实现标量混沌信号同步控制的方法。该方法利用线性输出神经网络构造被控混沌系统的模型，并基于Lyapunov理论与非线性系统控制方法，设计出神经网络权值变化规律与非线性反馈控制器，使神经网络模型的标量输出能大范围同步于给定的标量混沌信号。理论分析与计算机模拟结果都证实了这种方法的有效性。     

基于径向基函数神经网络的内模控制

文章用径向基神经网络设计内模控制系统,径向基神经网络是通过调整隐层与输出层间的连接权系数来逼近函数,如果隐层神经元数目过少,难免会出现收敛时间长,控制质量差,甚至发散的现象。为此,本文提出了增加调整基函数形状参数和中心向量的方法予以避免,并证明了网络不同调整参量收敛于目标函数极小点的性质。