An Adaptive RBF Neural Network Control Method for a Class of Nonlinear Systems

This paper focuses on designing an adaptive radial basis function neural network (RBFNN) control method for a class of nonlinear systems with unknown parameters and bounded disturbances. The problems raised by the unknown functions and external disturbances in the nonlinear system are overcome by RBFNN, combined with the single parameter direct adaptive control method. The novel adaptive control method is designed to reduce the amount of computations effectively. The uniform ultimate boundedness of the closed-loop system is guaranteed by the proposed controller. A coupled motor drives (CMD) system, which satisfies the structure of nonlinear system, is taken for simulation to confirm the effectiveness of the method. Simulations show that the developed adaptive controller has favorable performance on tracking desired signal and verify the stability of the closed-loop system.      

基于PSO优化的潜艇深度非线性PID控制

根据潜艇操纵控制过程非线性、慢时变的特点,在潜艇深度垂直面运动方程的基础上设计了一种基于粒子群算法的潜艇深度非线性PID控制器,针对非线性PID控制设计参数较多的问题,将参数设计问题转化为一种优化设计问题,借助粒子群优化算法,以某型潜艇深度控制系统为研究对象,对系统中的非线性PID控制参数进行了优化.仿真结果表明,该控制器不仅能较好地实现深度保持,相对于传统PID控制具有更好的稳态精度,对舵机的损耗也比传统PID控制小.     

空间微重力环境地面模拟系统的控制器设计

针对小型和迷你型试验目标,提出一种新的空间微重力环境模拟系统.系统采用平面气浮和气缸垂直悬浮组合方案来模拟空间微重力环境,并采用恒张力控制思想来模拟垂直地面方向上的微重力状态.采用RBF神经网络控制和滑模变结构控制复合控制方案,其中RBF神经网络用于逼近和补偿系统的不确定信息,并作为前馈补偿使跟踪误差快速收敛;通过滑模变结构控制消除RBF神经网络的逼近误差和不定随机干扰的影响,保证系统的鲁棒性.实验研究结果表明,该控制方案是有效的,系统具有较好的动态响应能力、鲁棒性和自适应能力.     

Improved nonlinear trajectory tracking using RBFNN for a robotic helicopter

This paper presents a backstepping control method using radial‐basis‐function neural network (RBFNN) for improving trajectory tracking performance of a robotic helicopter. Many well‐known nonlinear controllers for robotic helicopters have been constructed based on the approximate dynamic model in which the coupling effect is neglected; their qualitative behavior must be further analyzed to ensure that the unmodeled dynamics do not destroy the stability of the closed‐loop system. In order to improve the controller design process, the proposed controller is developed based on the complete dynamic model of robotic helicopters by using an RBFNN function approximation to the neglected dynamic uncertainties, and then proving that all the trajectory tracking error variables are globally ultimately bounded and converge to a neighborhood of the origin. The merits of the proposal controller are exemplified by four numerical simulations, showing that the proposed controller outperforms a well‐known controller in (J. Robust Nonlinear Control 2004; 14 (12):1035–1059). Copyright © 2009 John Wiley & Sons, Ltd.     

一类新的RBF 神经网络在非线性系统建模中的应用

提出一种基于输入集分类函数的新的距离度量方法,它与前传回归的正交最小二乘法相结合,不仅可以学习分类超平面的参数,而且可以选择重要的输入节点。这种结构的RBFNN特别适用于非线性动力学系统的辨识（建模）和控制。将改进的RBFNN用于化工中的聚合反应过程建模,结果表明该方法是有效而适用的。     

An Adaptive Neural Sliding Mode Controller for MIMO Systems

Here, a novel adaptive neural sliding mode controller (ANSMC) is proposed to handle the coupling and dynamic uncertainty of MIMO systems. The structure of this model-free new controller is based on a radial basis function neural network (RBFNN) which is derived from Lyapunov stability theory and relaxing Kalman–Yacubovich lemma to monitor the system for tracking a user-defined reference model. The weights of RBFNN can be initialized at zero, then, a novel online tuning algorithm is developed based on Lyapunov stability theory. A boundary layer function is introduced into the updating law to cover the parameter errors and modeling errors, and to guarantee the state errors converge into a specified error bound. An e-modification is added into the updating law to release the assumption of persistent excitation and obtain the appropriate values of the connecting weights of a RBFNN. To evaluate the control performance of the proposed controller, a two-link robot system is chosen as the simulation case. The numerical simulations results show that this novel controller has very good tracking accuracy, stability and robustness.     

基于全调节RBF神经网络的自适应飞行控制器

设计了一种基于径向基函数神经网络(RBF NN)的飞行控制器结构,运用李雅普诺夫综合法导出稳定的RBF NN参数调节律,以保证整个系统的稳定性.由于能在线地调节RBF NN的全部参数(连接权、高斯函数的中心和宽度),避免了因人为地估计中心和宽度参数而带来的性能损失,因而提高了控制性能.以F8战斗机为控制对象进行了仿真分析,仿真表明,在存在70%的模型误差的情况下,该控制器仍然能实现较好的跟踪控制,表现出很好的鲁棒性,远远优于传统的只调节连接权值的算法.     

基于S函数调节的非线性自适应动态面控制

针对一类控制增益未知的多输入多输出（MIMO）非线性系统,提出了一种基于神经网络的鲁棒自适应动态面控制方法．利用动态面控制解决反推法的计算膨胀问题;同时在参数自适应律中引入S（Sigmoid）函数,动态调节神经网络的收敛速度,解决了自适应初始阶段的抖振现象．利用李亚普诺夫稳定性定理,证明了闭环系统所有信号最终有界,系统的跟踪误差最终收敛到有界紧集内．仿真结果表明了该方法的有效性．     

基于径向基函数神经网络的机器人滑模控制

尽管滑模控制响应快,对系统参数和外部扰动呈不变性,但在保证系统的渐进稳定性上却存在很强的抖动缺点.因此,在一般滑模控制的基础上,引入了径向基函数神经网络(RBFNN).利用滑模控制的特点设定目标函数,将切换函数作为RBFNN的输入,滑模控制量作为其输出.利用RBF神经网络的在线学习功能,消除了控制的抖动,同时使系统具有很强的鲁棒性.对两连杆机械手进行了仿真研究,其结果表明,在存在模型误差和外部扰动的情况下,该方案既能达到高精度快速跟踪的目的,又能消除滑模控制的抖动问题.     

Adaptive Sliding Mode Control for Re-entry Attitude of Near Space Hypersonic Vehicle Based on Backstepping Design

Combining sliding mode control method with radial basis function neural network (RBFNN), this paper proposes a robust adaptive control scheme based on backstepping design for re-entry attitude tracking control of near space hypersonic vehicle (NSHV) in the presence of parameter variations and external disturbances. In the attitude angle loop, a robust adaptive virtual control law is designed by using the adaptive method to estimate the unknown upper bound of the compound uncertainties. In the angular velocity loop, an adaptive sliding mode control law is designed to suppress the effect of parameter variations and external disturbances. The main benefit of the sliding mode control is robustness to parameter variations and external disturbances. To further improve the control performance, RBFNNs are introduced to approximate the compound uncertainties in the attitude angle loop and angular velocity loop, respectively. Based on Lyapunov stability theory, the tracking errors are shown to be asymptotically stable. Simulation results show that the proposed control system attains a satisfied control performance and is robust against parameter variations and external disturbances.      

A simple PID control for asymptotic visual regulation of robot manipulators

This paper addresses the asymptotic regulation problem of robot manipulators with a vision‐based feedback. A simple image‐based transpose Jacobian proportional‐integral‐derivative (PID) control is proposed. The closed‐loop system formed by the proposed PID control and robot system is shown to be asymptotically stable by using Lyapunov's direct method and LaSalle's invariance theorem. Advantages of the proposed control include the absence of dynamical model parameters in the control law formulation and the control gains are easily chosen according to simple inequalities including some well‐known bounds extracted from robot dynamics and kinematics. Simulations performed on a two degree‐of‐freedom manipulator are provided to illustrate the effectiveness of the proposed approach. Copyright © 2010 John Wiley & Sons, Ltd.     

多变量非方系统多环PI控制器设计

基于等价传递函数（ETF）理论,提出含有多时滞的高维多变量非方系统多环PI（preportional-integral）控制器设计方法．首先,利用等价传递函数与被控过程传递函数的广义逆之间关系推导出ETF的求解通式．接着,基于已获得的ETF,利用IMC-PID（internal model control-proportional integral derivation）原理设计控制器,再利用Maclaurin级数展开获得多环PI控制器参数．所提ETF算法不仅具有更高的精度且适应于高维非方系统．最后通过仿真实例验证了所提算法的简单性和有效性．     

PWM整流器的径向基函数神经网络控制新方法

提出了一种用于PWM单位功率因数整流器的神经网络(neural network， NN)控制方法．运用预测电流对电压型PWM整流器的有功、无功电流实现解耦，电压环采用基于径向基函数(radial basis function， RBF)神经网络自适应调整参数的PI控制器．仿真结果表明，这种PI控制器可以在线调整PI参数，快速跟踪整流器的变化过程，使PWM整流器获得较好的动、静态特性，并对电网负载扰动有较强的适应能力．     

改进Smith控制与RBF单神经元PID的换热器控制系统

为了高效控制工质出口温度,维持换热器稳定运行,针对Smith预估控制算法及径向基函数(RBF)神经网络辨识单神经元比例-积分-微分(PID)控制算法特点,提出了Smith控制算法和RBF神经网络辨识单神经元PID相结合的控制策略,对Smith控制算法在结构上进行了改进,以提高RBF神经网络辨识单神经元PID控制的抗干扰能力,减少Smith控制算法对模型的依赖程度.仿真分析表明:应用于换热器工质出口温度控制系统,改进算法控制性能显著优于其它控制方法,抗干扰能力得到了大幅提高.     

基于神经网络的一类非线性系统的稳定自适应控制器设计方法*

针对一类非线性连续时间系统,其中非线性函数未知,提出了一种基于神经网络的稳定自适应控制方案,由于控制律的选择基于Ｌｙａｐｕｎｏｖ稳定性理论,因此,该控制方案不仅能够解决这类非线性系统的跟踪问题。     

非仿射纯反馈系统的间接自适应神经网络控制

针对非仿射纯反馈系统,提出了一种新的设计方案.与现有文献中方法不同,该方案不是直接利用逼近技巧构建理想的反馈控制器.首先通过自抗扰思想将非仿射纯反馈系统转化成含有未知控制系数以及未知非线性的仿射系统,并且证明了可行性.然后结合微分器和全调节径向基函数神经网络,利用自适应反演技巧设计了自抗扰控制器,微分器的引入避免了传统反演的计算复杂性.最后,从理论上证明了所设计的控制器能够保证闭环系统所有信号半全局一致有界,并且证明了系统状态渐进收敛到零点的残集内.仿真例子验证了算法的有效性.     

一种稳定的机器人神经网络控制器研究

研究一种稳定的机器人神经网络（ＮＮ）控制器，提出了由神经网络控制器和监督控制器构成的控制方案，给出了控制器的设计方法及ＮＮ学习自适应律，并基于Ｌｙａｐｕｎｏｖ方法证明了控制系统的稳定性和ＮＮ参数收敛性，仿真结果表明该控制方案具有良好的鲁棒性和参数收敛性，从而证明控制器的有效性。     

基于改进型RBF神经网络辨识的PID控制

针对工业控制领域复杂非线性时变系统．提出了基于改进型RBF神经网络的PID参数在线自整定方法。采用改进型RBF神经网络辨识器在线辨识系统模型，自动调整PID控制器参数，实现系统的智能控制。仿真结果表明，与常规RBF神经网络PID控制方法相比，该方法具有控制精度高、响应速度快的优点，并且具备较强的自适应性和鲁棒性。     

RBFNN‐Based Identification and Compensation Mechanism for Disturbance‐Like Parametric Friction with Application to Tractor‐Trailer Vehicles

This paper develops an effective identification and compensation mechanism for the disturbance‐like parametric friction of a typical underactuated tractor‐trailer vehicle system. To begin with, a parametric friction model is proposed to describe various friction effects associated with the system velocity, and then a disturbance‐like parametric friction concept is introduced by considering the motion characteristics of tractor‐trailer vehicle. Next, the radial basis function neural network (RBFNN) is employed to identify the friction due to its high convergence rate, superior approximation precision and local‐minima avoidance ability. Afterwards, a sliding mode control (SMC) is utilized to compensate the identified friction due to its numerous merits, such as strong robustness and fast convergence. On the basis of the effective combination of identification and compensation mechanism, a favorable transient performance can be achieved during the desired velocity tracking process. Lastly, the simulation results confirm that the RBFNN‐based disturbance‐like parametric friction identification and compensation mechanism can effectively improve the trajectory tracking performance of tractor‐trailer vehicle.     

不平衡数据分类的混合算法

针对传统分类算法处理不平衡数据时,小类的分类精度过低问题,提出一种径向基函数神经网络和随机森林集成的混合分类算法．在小类样本之间用随机插值方式平衡数据集的分布,利用受试者特征曲线在置信度为95％下的面积为标准去除冗余特征;之后对输入数据用Bagging技术进行扰动,并以径向基函数神经网络作为随机森林中的基分类器,采用绝大多数投票方法进行决策的融合和输出．将该算法应用于UCI数据,以G均值和受试者特征曲线下的面积为评判标准,结果表明该方法能够有效地提高中度和高度不平衡数据的分类精度．