RBFN在OFDM快衰落信道估计中的应用

研究了径向基函数网络（RBFN）在正交频分复用（OFDM）系统快衰落信道估计中的应用，提出了一种基于分散导频的RBFN信道估计器。较之基于梳状导频的RBFN估计器，该估计器极大地提高了频带利用率，且具有良好的误码率性能。     

一类基于径向基函数网的分工协作混合系统

径向基函数网络(Radial Basis Function Network,RBFN)是二十世纪八十年代末提出的一种神经网络.当网络的输入维数较大时,RBFN的系统复杂性大大提高,从而使RBFN的行为受到影响,因此降低RBFN输入维数已成为RBFN的研究热点.本文提出一类基于RBFN的分工协作系统及其学习算法(A Divide-and-Cooperate HybridSystem Based RBFN,DCRBFN).DCRBFN是一种由多个子RBFN组成的混合结构,每个子RBFN具有自己的输入空间.由于DCRBFN把高维模型分解为低维模型,所以DCRBFN不仅明显降低了RBFN的复杂性而且网络的收敛速度更快.实验表明,DCRBFN在处理高维模型的行为明显优于RBFN.     

基于DSP实现的自动变速器神经网络换挡研究

研究了车辆自动变速器的换挡建模问题，介绍了利用径向基神经网络（RBFN）的换挡建模方法和算法，为了满足建模过程的在线运行，设计了DSP处理器TMS320C31和80C196双CPU硬件系统，测试结果表明，RBFN网模型能够很好从驾驶员的换挡数据中获得换挡规律，利用DSP实现RBFN算法满足工程要求。     

一种调整型径向基网络偏微分方程解法

基于径向基神经网络（RBFN）的偏微分方程（PDE）求解算法中,仪通过搜索最佳权值逼近方程解,精度有限。实际上在建立的RBFN中可能存在对求解PDE贡献很小的但是增加算法复杂度的神经元,或者缺少对方程解贡献很大的辅助神经元。基于这个事实提出一种新的算法：在搜索最佳权值同时调整RBFN结构,删除对方程解贡献小的神经元,增加对方程解贡献大的辅助神经元;采用最小均方误羔梯度下降法得到最优权值;最后得到PDE的逼近解。仿真实验表明新算法较传统的RBFN算法,精度更高,误差收敛速度更快;可广泛应用于工程实践。     

基于SVM和RBFN的汽车主动降噪系统传感器故障诊断

汽车主动降噪系统的工作依赖于多个噪声传感器,一旦传感器发生故障,将严重影响降噪效果。为保证汽车主动降噪系统的性能,提出了由支持向量机(SVM)预测模型和径向基神经网络(RBFN)预测模型构成的传感器故障诊断系统,SVM模型判断是否发生传感器故障,RBFN模型则利用各传感器间的信息冗余关系定位故障传感器并对其信号进行重构。仿真结果表明,该诊断系统可有效实现汽车主动降噪系统中的传感器故障诊断及信号重构。与传统的汽车主动降噪系统相比,引入传感器故障诊断系统可保证更稳定的降噪性能。     

酸性磷铵料浆浓缩过程中氟含量的预测模型

在磷铵生产过程中,料浆的氟含量预测对生产具有重要意义。本文将径向基函数网络(RBFN)与循环子空间回归(CSR)相结合,设计了RBFN—CSR建模方法。RBFN—CSR方法在确定隐含层结构和参数时,将隐单元数取为训练样本数,径向基函数中心矢量取相应样本值,宽度参数根据样本分布情况采用尝试方法选取,隐含层到输出层的网络权系数运用CSR求解。CSR求解过程包容了最小二乘回归(LSR)、主成分回归(PCR)、偏最小二乘回归(PLSR)以及很多中间的回归方法,它可在非常广泛的范围内根据某一准则选择最优的网络结构参数。运用RBFN—CSR方法建立了酸性磷铵料浆浓缩过程中氟含量的预测模型,交叉验证表明,该模型具有较高的预测精度和良好的稳定性能,有一定的实际应用价值。     

基于PLS和GAs的径基函数网络构造策略

鉴于传统径基函数网络(radial basis function network,简称RBFN)构造策略的不足,提出了基于偏最小二乘法(partial least squares,简称PLS)和遗传算法(genetic algorithms,简称GAs)的RBFN构造策略和一种更有效的径基宽度取值方法.在这个集成构造策略中,PLS克服了K-Means算法求取径基易陷入局部最优的弊病,并使合成径基比由正交算法获取的径基更具代表性;而所提出的径基宽度取值方法和GAs则为网络性能和结构的实质性改善与优化提供了保障.实验证实了基于PLS和GAs的RBFN构造策略及所提出的径基宽度取值方法的优越性、可靠性和有效性.     

径向基网络的研究进展和评述

径向基网络(RBFN)是当前人工神经网络技术研究的热点之一,并以其优良的性能广泛应用于各个领域。该文简要介绍了RBFN的结构特点,与经典的多层前传网(MLFN)进行对比,分析了RBFN学习算法从经验到理论,从繁杂到简捷的发展进程,及其存在的问题,归纳了RBFN的一些特殊类型,并对RBFN的研究和发展进行了展望。     

一类递归RBF神经网络模型的稳定性讨论

在径向基函数神经网络（RBFNN）和递归神经网络（RNN）的基础上,提出了一类新的递归径向基函数神经网络（RRBFNN）模型,它具有两种网络模型的优点。文中对它的渐近稳定性和学习算法进行了研究,并给出相关的定理和公式。仿真结果表明了该神经网络模型在控制不稳定非线性系统（如小车－倒摆系统）具有巨大潜力。     

基于RBFN的交互式图像检索方法

相关反馈技术是近年来图像检索中的重要研究方向,它有效地缩短了用户高层语义和图像底层视觉特征的差距,大大提高了系统的检索精度。文中从机器学习的角度出发,提出了一种基于RBFN的相关反馈算法。同时,为了方便用户对检索结果的标记,将模糊逻辑引入到图像检索中。即:用户对检索结果标记为相关图像、模糊相关图像和不相关图像,利用这些反馈信息动态地建立RBFN的结构,并进行检索,这个过程反复进行直到用户得到满意的结果。实验表明,这种方法在图像检索中具有更好的性能和更强的推广能力。     

基于神经网络干扰观测器的一类不确定非线性MIMO系统H_∞跟踪控制

针对一类具有未知外部干扰及内部不确定性的非线性MIMO系统,提出了基于神经网络干扰观测器的鲁棒跟踪控制方法,用于降低控制器对干扰的要求.设计了基于神经网络的干扰观测器,以逼近由外部干扰、内部不确定性和子系统的交叉耦合组成的复合干扰.根据Lyapunov稳定性理论的参数更新律及所设计的控制器,保证了系统中所有信号的最终一致有界性,并获得了给定的跟踪性能指标.仿真结果证明了该方法的有效性.     

基于微分观测器的飞行模拟转台伺服系统非线性控制

飞行模拟器转台伺服系统是导弹飞行的重要模拟设备,用于获取实验数据。针对飞行模拟转台伺服系统在跟踪控制过程中存在参数不确定性、非线性摩擦等不确定性问题,提出了一种基于微分观测器的飞行模拟转台伺服系统非线性控制方法;考虑系统在跟踪控制过程中存在不确定性问题,设计了微分观测器来估计复合不确定扰动;设计非线性控制器来控制飞行模拟转台伺服系统,使得系统可以收敛到期望位置转角信号;通过李雅普洛夫稳定性证明控制器作用在系统条件下的鲁棒性;通过MATLAB/Simulink仿真试验平台验证了文中提出的控制策略能够使系统有效跟踪期望位置转角,具有一定工程应用价值;     

Differential flatness based nonlinear predictive control of fed-batch bioreactors

A trajectory optimization scheme based on the property of differential flatness is proposed in this paper. A dynamic optimization problem is transformed into a lower dimensional nonlinear programming problem through the use of flat outputs. This optimization approach is demonstrated in the repeated optimization of nonlinear dynamic systems under feedback in an approach similar to nonlinear model predictive control. This approach is illustrated on two examples involving biomass optimization and product optimization. Optimization under feedback is studied for the nominal problem and the case where uncertainty is present. The proposed scheme is also used in conjunction with a nonlinear Luenberger observer to generate the optimal trajectories under parametric uncertainty.     

Prediction method for energy consumption per ton of fused magnesium furnaces using data driven and mechanism model

This paper gives an overview of early development of nonlinear disturbance observer design technique and the disturbance observer based control (DOBC) design. Some critical points raised in the development of the methods have been reviewed and discussed which are still relevant for many researchers or practitioners who are interested in this method. The review is followed by the development of a new type of nonlinear PID controller for a robotic manipulator and its experimental tests. It is shown that, under a number of assumptions, the DOBC consisting of a predictive control method and a nonlinear disturbance observer could reduce to a nonlinear PID with special features. Experimental results show that, compared with the predictive control method, the developed controller significantly improves performance robustness against uncertainty and friction. This paper may trigger further research and interests in the development of DOBC and related methods, and building up more understanding between this group of control methods with comparable ones (particularly control methods with integral action).     

Nonlinear observer design for a general class of nonlinear systems with real parametric uncertainty

This paper is a geometric study of the local observer design for a general class of nonlinear systems with real parametric uncertainty. Explicitly, we study the observer design problem for a general class of nonlinear systems with real parametric uncertainty and with an input generator (exosystem). In this paper, we show that for the classical case, when the state equilibrium does not change with the parametric uncertainty, and when the plant output is purely a function of the state, there is no local asymptotic observer for the plant. Next, we show that in sharp contrast to this case, for the general case of problems where we allow the state equilibrium to change with the parametric uncertainty, there typically exist local exponential observers even when the plant output is purely a function of the state. We also present a characterization and construction procedure for local exponential observers for the general class of nonlinear systems with real parametric uncertainty under some stability assumptions. We also show that for the general class of nonlinear systems considered, under some stability assumptions, the existence of local exponential observers in the presence of inputs implies, and is implied by, the existence of local exponential observers in the absence of inputs. Finally, we generalize our results to a general class of nonlinear systems with input generator, and with exogenous disturbance.     

Sigma function in observer design for states and perturbations

For nonlinear systems operating under uncertainty, this paper involves the principle of motion separation to design a state observer with nonlinear corrections in the form of sigma functions. For the systems representable in the regular form with respect to the external perturbations, the above approach yields the current estimates of the unmeasurable state variables and external perturbations without extending the dynamic order of the observer by a model that simulates the action of the external perturbations. The developed algorithms are applied in the control system of an asynchronous drive with an incomplete set of measuring devices.     

A CDM-backstepping control with nonlinear observer for electrically driven robot manipulator

This paper presents a CDM-backstepping strategy for motion control of Electrically-driven manipulator under the conditions of uncertainty and the action of external disturbance, while incorporating a nonlinear observer. Based on this model, a systematic analysis and design algorithm is developed to deal with stabilization and trajectory tracking of elbow robot, one feature of this work is employing the backstepping observer to achieve the exponential stability with position and velocity estimations. The results of computer simulations demonstrate that accurate and robust motion control can be achieved by using the proposed approach.     

Approximate finite‐time control for a class of uncertain nonlinear systems with dynamic compensation

In this work, a new robust nonlinear feedback control method with dynamic active compensation is proposed; the active control method has been applied to an integral series of finite‐time single‐input single‐output nonlinear system with uncertainty. In further tracking the closed‐loop stability and nonlinear uncertainty, an extended state observer has been employed to solve the immeasurability and nonlinear uncertainty within a nonlinear system. A singular perturbation theory has been used to solve for the finite‐time stability of the closed‐loop system; furthermore, numerical simulations showed that the robust nonlinear feedback controller tracked the uncertainty in a nonlinear Duffing‐type oscillator and has proven the effectiveness of the approximate finite‐time control strategy proposed. By using an approximate finite‐time control approach with active compensation, the uncertainty in a nonlinear system could be accurately estimated and controlled. Copyright © 2017 John Wiley & Sons, Ltd.     

Nonlinear observer design for a general class of discrete-time nonlinear systems with real parametric uncertainty

This paper is a geometric study of the local observer design for a general class of discrete-time nonlinear systems with real parametric uncertainty. Explicitly, we study the observer design problem for a general class of discrete-time nonlinear systems with real parametric uncertainty and with an input generator (exosystem). In this paper, we show that for the classical case, when the state equilibrium does not change with the parametric uncertainty, and when the plant output is purely a function of the state, there is no local asymptotic observer for the plant. Next, we show that in sharp contrast to this case, for the general case of problems where we allow the state equilibrium to change with the parametric uncertainty, there typically exist local exponential observers even when the plant output is purely a function of the state. We also present a characterization and construction procedure for local exponential observers for the general class of discrete-time nonlinear systems with real parametric uncertainty under some stability assumptions. We also show that for the general class of discrete-time nonlinear systems considered, under some stability assumptions, the existence of local exponential observers in the presence of inputs implies, and is implied by the existence of local exponential observers in the absence of inputs. Finally, we generalize our results to a general class of discrete-time nonlinear systems with input generator, and with exogenous disturbance.     

Stability analysis of a control system with nonlinear input uncertainty based on disturbance observer

In disturbance observer (DO)‐based control, control input attenuates a disturbance using observer output. Thus, the input may not achieve the attenuation if the input term includes uncertainty. Therefore, in order to correctly suppress the disturbance, it is essential to consider the uncertainty existing in the input term, and thus this article focuses on a nonlinear uncertainty in the input term. This article analyzes the stability and robustness of a DO‐based nonlinear control system with both the disturbance and the input uncertainty. We address the case that the disturbance and the uncertainty depend on time and states of a controlled system. The disturbance and the uncertainty are gathered in an integrated disturbance, and the integrated disturbance depends on many variables: the states, the control input, and the time. Therefore, a norm estimations for the disturbance and a time variation of the disturbance is difficult without knowledge of the state trajectory. Hence, a slope‐restriction for the disturbance is used for the stability analysis. Based on the mathematical analysis, we show input‐to‐state stability conditions due to extend the application class of the DO‐based controller to a control system with the disturbance and the nonlinear input uncertainty. The analytical results are verified by numerical simulations.