一种基于RBF神经网络的转台分系统故障诊断方法

针对三轴精密测试转台各分系统故障诊断的需要,提出了一种基于径向基函数(RBF)神经网络的局部故障诊断方法。首先,给出了相应的RBF神经网络的结构,以及一种基于递归最小二乘法的改进学习算法;然后,将其应用到转台控制分系统的局部故障诊断中。根据控制分系统的常见故障及其特征信息,建立起基于RBF神经网络的故障诊断模型;最后,仿真实验结果验证了该方法的有效性。     

基于神经网络的严反馈块非线性系统的鲁棒控制

针对非匹配不确定性的严反馈块非线性系统,基于神经网络提出一种鲁棒控制方法．利用Lyapunov稳定性定理推导出RBF神经网络的全调节律,用于处理系统中的非线性参数不确定性,提高了神经网络的在线逼近能力;采用神经网络和鲁棒控制方法,利用已知信息的同时,对控制系数矩阵未知时的设计问题进行处理,避免了控制器可能的奇异问题;引入非线性跟踪微分器,解决了Backstepping设计中的“计算膨胀”问题．运用Lyapunov稳定性定理证明了闭环系统的所有信号均最终一致有界．     

Dynamic surface control approach to adaptive robust control of nonlinear systems in semi-strict feedback form

This article considers the adaptive robust control of a class of single-input-single-output nonlinear systems in semi-strict feedback form using radial basis function (RBF) networks. It is well known that the standard backstepping design may suffer from “explosion of terms”. To overcome this problem, the recently developed dynamic surface control technique which employs a first-order low-pass filter at each step of the backstepping design procedure is generalized to the nonlinear system under study. Our attention is paid to achieve guaranteed transient performance of the adaptive controller. At each step of design, a feedback controller strengthened by nonlinear damping terms to counteract nonlinear uncertainties is designed to guarantee input-to-state practical stability of the corresponding subsystem, and then parameter adaptations are introduced to reduce the ultimate error bound. Furthermore, for the output trajectory tracking problem, it is recommended to adopt the partial adaptation policy to reduce the computational burden due to “curse of dimension” of the RBF networks. Finally, numerical examples are included to verify the results of theoretical analysis.     

径向基函数神经网络的一种两级学习方法

建立RBF(radial basis function)神经网络模型关键在于确定网络隐中心向量、基宽度参数和隐节点数.为设计结构简单,且具有良好泛化性能径向基网络结构,本文提出了一种RBF网络的两级学习新设计方法.该方法在下级由正则化正交最小二乘法与D-最优试验设计结合算法自动构建结构节俭的RBF网络模型;在上级通过粒子群优化算法优选结合算法中影响网络泛化性能的3个学习参数,即基宽度参数、正则化系数和D-最优代价系数的最佳参数组合.仿真实例表明了该方法的有效性.     

An ISS-modular approach for adaptive neural control of pure-feedback systems

Controlling non-affine non-linear systems is a challenging problem in control theory. In this paper, we consider adaptive neural control of a completely non-affine pure-feedback system using radial basis function (RBF) neural networks (NN). An ISS-modular approach is presented by combining adaptive neural design with the backstepping method, input-to-state stability (ISS) analysis and the small-gain theorem. The difficulty in controlling the non-affine pure-feedback system is overcome by achieving the so-called “ISS-modularity” of the controller-estimator. Specifically, a neural controller is designed to achieve ISS for the state error subsystem with respect to the neural weight estimation errors, and a neural weight estimator is designed to achieve ISS for the weight estimation subsystem with respect to the system state errors. The stability of the entire closed-loop system is guaranteed by the small-gain theorem. The ISS-modular approach provides an effective way for controlling non-affine non-linear systems. Simulation studies are included to demonstrate the effectiveness of the proposed approach.     

A comparison study on a chemical reactor modelling with a physical model and PLRBF networks

The paper presents the modelling practice and considerations for a multivariable process with a first-principle model and three redial basis function (RBF) networks. The process is a laboratory-scaled three-input three-output chemical reactor rig. The RBF networks used are standard RBF networks, pseudo-linear RBF (PLRBF) networks and adaptive PLRBF networks. The first-principle model, the network structures and training algorithms are briefly reviewed. Real data collection with the design of the excitation signal is described. The four models are evaluated by multi-step-ahead prediction errors and the comparison is made. The methods and considerations provide useful experience for deriving data-driven models for industrial processes.     

基于遗传算法的RBF神经网络的优化设计方法

该文提出了一种新的RBF神经网络的设计方法，采用遗传算法对RBF神经网络的隐层节点中心值进行进化优选，用自适应梯度下降法选择隐层节点高斯函数的宽度，用递推的最小二乘法训练RBF神经网络的权值，仿真结果证明了该方法的有效性。     

基于RBF神经网络的射频功放行为模型研究

为了设计和优化高线性功率放大器和通信子系统,在系统级仿真中,构建功率放大器精确的行为模型是极为重要的。应用实际功率放大器晶体管测试板,通过ADS（Advanced Design System）仿真得到大量功放输入输出数据,建立了一个基于RBF（Radial Basis Function）神经网络的行为模型,给出了RBF 神经网络的结构设计及K-均值聚类算法和共轭梯度优化算法,并进行了模型检验。结果表明,基于RBF神经网络的功放行为模型具有较高的精度,相对于BP 神经网络模型具有更高的逼近能力和速度。     

粒子群优化RBF神经网络光伏电池建模研究

本文研究神经网络在光伏电池建模优化问题。由于光伏电池具有高度非线性特性,其输出功率受到外界自然因素的影响,使得传统方法不能满足光伏控制系统动态要求。针对上述问题,本文提出一种粒子群优化的神经网络光伏电池建模算法。改进的方法以日照、温度和负载电压作为提出的RBF神经网络模型的输入值,把光伏电池的输出功率作为神经网络的输出,采用RBF神经网络对光伏电池进行建模,同时利用粒子群算法对神经网络参数进行优化,最后建立光伏电池的动态响应模型。仿真实验结果证明,所提模型更好地克服传统方法的缺点,收敛速度快,具有较高的预测精度和适合能力。     

磁悬浮系统的基于RBF网络的自适应反推控制

针对一类磁悬浮系统,研究了基于RBF网络的自适应反推控制器的设计和分析问题.首先在较弱的条件下,通过引入一监督控制,保证了闭环系统的状态落入一紧集中;然后通过RBF网络的逼近性质和反推设计技术,给出了一种鲁棒自适应控制器的设计;最后利用Lyapunov稳定性理论,严格地分析了这种自适应控制系统的稳定性和跟踪性能.     

Orthogonal RBF Neural Network Approximation

The approximation properties of the RBF neural networks are investigated in this paper. A new approach is proposed, which is based on approximations with orthogonal combinations of functions. An orthogonalization framework is presented for the Gaussian basis functions. It is shown how to use this framework to design efficient neural networks. Using this method we can estimate the necessary number of the hidden nodes, and we can evaluate how appropriate the use of the Gaussian RBF networks is for the approximation of a given function.     

Nonlinear modeling of MCFC stack based on RBF neural networks identification

Modeling molten carbonate fuel cells (MCFC) is very difficult and the most existing models are based on conversation laws which are too complicated to be used to design a control system. This paper presents an application of radial basis functions (RBF) neural networks identification to develop a nonlinear temperature model of MCFC stack. The temperature characters of MCFC stack are briefly analyzed. A summary of RBF neural networks modeling of MCFC is introduced. The simulation tests reveal that it is feasible to establish the model of MCFC stack using RBF neural networks identification. The modeling process avoids using complicated differential equations to describe the stack and the neural networks model developed can be used to predict the temperature responses online which makes it possible to design online controller of MCFC stack.     

一种新的RBF网络两级学习设计方法

为了简化径向基网络结构,构造出良好泛化性能力的网络,提出了一种径向基(RBF)网络的两级学习新设计方法.在下级将正交最小二乘法(OLS)与A-最优设计方法(A-opt)相结合(OLS+A-opt),引入一种基于A-最优设计准则的混合代价函数,同时优化网络模型的逼近性能及模型的充分性,自动构建结构节俭的RBF网络模型;而方法中的关键学习参数A-最优代价系数通过上级粒子群优化方法(PSO)优化获取最佳值.仿真结果表明该方法所设计的RBF网络不仅具有较好的泛化性能,而且也具有良好的模型鲁棒性及充分性,是一种有效的RBF网络设计方法.     

Free vibration analysis of laminated composite plates based on FSDT using one-dimensional IRBFN method

This paper presents a new effective radial basis function (RBF) collocation technique for the free vibration analysis of laminated composite plates using the first order shear deformation theory (FSDT). The plates, which can be rectangular or non-rectangular, are simply discretised by means of Cartesian grids. Instead of using conventional differentiated RBF networks, one-dimensional integrated RBF networks (1D-IRBFN) are employed on grid lines to approximate the field variables. A number of examples concerning various thickness-to-span ratios, material properties and boundary conditions are considered. Results obtained are compared with the exact solutions and numerical results by other techniques in the literature to investigate the performance of the proposed method.     

在线学习RBF神经网络的模型参考自适应控制器

本文给出一种在线学习RBF神经网络的快速算法,并设计了在线学习RBF神经网络的MARAC。通过仿真表明,在线RBF神经网络的MRAC计算量小、在线学习、跟踪时间短、控制精度高的优点。     

变负载机械手轨迹跟踪控制器设计

本文针对具有变负载的不确定刚性机械手系统,提出了一种依赖平均驻留时间的神经网络自适应切换控制策略.本控制方案将夹持不同负载的刚性机械手系统视为切换系统,即根据负载的不同将整个系统分为若干子系统,并基于平均驻留时间原则对每个子系统分别设计控制器.在各子系统中,分别采用径向基函数(RBF)神经网络逼近系统结构参数,以避免控制器对系统精确模型的依赖.同时,基于神经网络设计鲁棒补偿项,以抑制集总扰动对系统的影响.然后,利用多Lyapunov函数方法证明了轨迹跟踪误差的一致最终有界性.最后,通过仿真验证,所提出的控制方案不仅可实现变负载机械手期望轨迹的高精度跟踪,而且可有效削弱输入力矩的抖振.     

在线学习RBF神经网络的模型参考自适应控制器

本文给出一种在线学习RBF神经网络的快速算法,并设计了在线学习RBF神经网络的MARAC。通过仿真表明,在线RBF神经网络的MRAC计算量小、在线学习、跟踪时间短、控制精度高的优点。     

基于信息强度的RBF神经网络结构设计研究

在系统研究前馈神经网络的基础上,针对径向基函数(Radial basis function, RBF) 网络的结构设计问题,提出一种弹性RBF神经网络结构优化设计方法. 利用隐含层神经元的输出信息(Output-information, OI)以及隐含层神经元与输出层神经元间的交互信息(Multi-information, MI)分析网络的连接强度, 以此判断增加或删除RBF神经网络隐含层神经元, 同时调整神经网络的拓扑结构,有效地解决了RBF神经网络结构设计问题; 利用梯度下降的参数修正算法保证了最终RBF网络的精度, 实现了神经网络的结构和参数自校正. 通过对典型非线性函数的逼近与污水处理过程关键水质参数建模, 结果证明了该弹性RBF具有良好的动态特征响应能力和逼近能力, 尤其是在训练速度、泛化能力、最终网络结构等方面较之最小资源神经网络(Minimal resource allocation net works, MRAN)、增长修剪RBF 神经网络(Generalized growing and pruning RBF, GGAP-RBF)和自组织RBF神经网络(Self-organizing RBF, SORBF)有较大的提高.     

径向基函数（RBF）神经网络的一种极大熵学习算法

RBF神经网络中心向量的确定是整个网络学习的关键,该文基于信息论中的极大熵原理构造了训练中心向量的极大熵聚类算法,由此给出了网络的极大熵学习算法。文中最后分别用一个时间序列预测和系统辨识问题验证了该学习算法的有效性,同RBF网络和多层感知机的误差回传算法相比,该算法不仅在学习精度和泛化推广能力上有一定程度的提高,而且学习时间有显著的降低。