共查询到20条相似文献，搜索用时 798 毫秒
1.
提出一种将前馈神经网络用于非线性时变系统辩识的学习算法 ,其要点是把网络权值看作时变系统的一个状态 ,用卡尔曼滤波估计此状态 ,于是网络实现了非线性和时变的映射 .文中推导了该算法 ,仿真结果证实了它的有效性 相似文献
2.
结合支持向量机和神经网络各自的优点,提出了一种新颖的自适应支持向量回归神经网络(SVR-NN).首先,利用支持向量回归方法确定SVR-NN的初始结构和初始化权值,基于支持向量自适应地构造SVR-NN神经网络的隐层节点;然后,使用退火过程的鲁棒学习算法更新网络节点参数和权值.为了验证所提出方法的有效性,给出了自适应SVR-NN应用于非线性动态系统辨识的实例.仿真结果表明,与以前的神经网络方法相比,基于SVR-NN网络的辨识方案能获得相当好的性能,它具有很快的收敛速度.因此,自适应的SVR-NN为非线性系统辨识提供了极有吸引力的新途径. 相似文献
3.
为了提高非视距(NLOS)环境下无线定位的准确性和可靠性,提出了一种利用数字广播信号进行移动台定位的神经网络方法.该方法利用神经网络的学习特性和逼近任意非线性函数的能力,建立到达时间(TOA)和到达时间差(TDOA)测量数据与坐标之间的映射关系.将神经网络的连接权值作为非线性动态系统的状态量进行估计,用基于扩展卡尔曼(EKF)的实时神经网络训练算法来训练多层感知器网络.由于基于EKF的训练算法给出的是连接权值的近似最小方差估计,其收敛性要优于误差反向传播(BP)算法.仿真结果表明,该算法在NLOS环境下有较高的定位精度,性能优于BP基的神经网络算法和最小二乘算法;且该定位方法不依赖于特定的NLOS误差分布,也无需视距(LOS)和非视距识别. 相似文献
4.
本文使用改进的神经网络模型结构与算法来辨识未知非线性系统,具有辨识精度高,速度快的特点。该方法简单有效,为设计非缌陛对象控制器提供了一条思路,从而摆脱了用线性模型近似被控对象的粗略做法。算法中,学习率采用随误差变化率而改变的做法减小了学习率选取的盲目性,加速了网络训练过程。 相似文献
5.
模糊神经网络变结构算法优化的研究 总被引：1，自引：0，他引：1
随着生产实际情况的不断变化,以及模糊神经网络不断的改进和发展,提出一种改进的构造神经网络的方法,并且提出混合学习算法,结合共扼梯度下降法与递归最小二乘估计来分别辨识网络中的前、后件参数,并对非线性系统进行仿真实验,达到控制要求. 相似文献
6.
针对一类可转化为“标准块控制形”的MIMO非线性系统,基于动态面控制技术,提出一种鲁棒自适应神经网络控制算法。采用径向基函数神经网络逼近不确定性模型,通过引入一阶滤波器,消除后推设计中由于反复对虚拟控制的求导而导致的复杂性问题,同时补偿项的引入可避免反馈线性化方法中可能出现的控制器奇异性问题,无需控制增益矩阵正定、可逆的条件。利用李亚普诺夫方法,证明了闭环系统是半全局一致终结有界,适当选取设计常数,跟踪误差可收敛到原点的一个小邻域内。计算机仿真结果表明此法的有效性。 相似文献
7.
A maximum power point tracker for photovoltaic energy systems based on fuzzy neural networks 总被引：1，自引：0，他引：1
Chun-hua Li Xin-jian Zhu Guang-yi Cao Wan-qi Hu Sheng Sui Ming-ruo Hu 《浙江大学学报(A卷英文版)》2009,10(2):263-270
To extract the maximum power from a photovoltaic （PV） energy system, the real-time maximum power point （MPP） of the PV array must be tracked closely. The non-linear and time-variant characteristics of the PV array and the non-linear and non-minimum phase characteristics of a boost converter make it difficult to track the MPP for traditional control strategies. We propose a fuzzy neural network controller （FNNC）, which combines the reasoning capability of fuzzy logical systems and the learning capability of neural networks, to track the MPP. With a derived learning algorithm, the parameters of the FNNC are updated adaptively. A gradient estimator based on a radial basis function neural network is developed to provide the reference information to the FNNC. Simulation results show that the proposed control algorithm provides much better tracking performance compared with the filzzy logic control algorithm. 相似文献
8.
本文给出了多维小波网络的结构及其随机梯度学习算法,提出了基于小波网络的MQAM数字通信自适应均衡器.仿真结果表明:该均衡器对于MQAM数字信号非线性信道的均衡,其性能明显优于传统的基于LMS和RLS算法的线性均衡器和基于RLS算法的判决反馈均衡器,且性能稍好于基于BP网络的均衡器,其缺点是计算复杂度高和训练收敛速度慢.,A novel wavelet network based adaptive equalizer (WNBAE) is presented and the structure and stochastic gradient learning algorithm is given. The proposed WNBAE has better performance than that of the conventional linear transversal equalizer based on the LMS and the RLS algorithms, as well as that of the decision feedback equalizer based on the RLS algorithm, especially for MQAM digital communication reception systems over the nonlinear channels. In addition, it outperforms the BP neural network based adaptive equalizer slightly. However, it has a slow convergence rate and a high computational complexity. Several simulations are performed to evaluate the behavior of the WNBAE. 相似文献
9.
In order to improve the output efficiency of a photovoltaic (PV) energy system, the real-time maximum power point (MPP) of the PV array should be tracked closely. The non-linear and time-variant characteristics of the photovoltaic array and the non-linear and non-minimum phase characteristics of a boost converter make it difficult to track the MPP as in traditional control strategies. A neural fuzzy controller (NFC) in conjunction with the reasoning capability of fuzzy logical systems and the learning capability of neural networks is proposed to track the MPP in this paper. A gradient estimator based on a radial basis function neural network is developed to provide the reference information to the NFC. With a derived learning algorithm, the parameters of the NFC are updated adaptively. Experimental results show that, compared with the fuzzy logic control algorithm, the proposed control algorithm provides much better tracking performance. 相似文献
10.
A closed-chain robot has several advantages over an open-chain robot, such as high mechanical rigidity, high payload, high precision. Accurate trajectory control of a robot is essential in practical use. This paper presents an adaptive proportional integral differential (PID) control algorithm based on radial basis function (RBF) neural network for trajectory tracking of a two-degree-of-freedom (2-DOF) closed-chain robot. In this scheme, an RBF neural network is used to approximate the unknown nonlinear dynamics of the robot, at the same time, the PID parameters can be adjusted online and the high precision can be obtained. Simulation results show that the control algorithm accurately tracks a 2-DOF closed-chain robot trajectories. The results also indicate that the system robustness and tracking performance are superior to the classic PID method. 相似文献
11.
A new neural network model termed ＇standard neural network model＇ （SNNM） is presented, and a state-feedback control law is then designed for the SNNM to stabilize the closed-loop system. The control design constraints are shown to be a set of linear matrix inequalities （LMIs）, which can be easily solved by the MATLAB LMI Control Toolbox to determine the control law. Most recurrent neural networks （including the chaotic neural network） and nonlinear systems modeled by neural networks or Takagi and Sugeno （T-S） fuzzy models can be transformed into the SNNMs to be stabilization controllers synthesized in the framework of a unified SNNM. Finally, three numerical examples are provided to illustrate the design developed in this paper. 相似文献
12.
前馈三层神经网络具有很好的非线性映射能力,而前馈三层神经网络的代数算法能够实现零代价函数的网络精确学习过程,本文将其应用于电磁环境复杂度的评价.首先从时域、空域、频域和能量域四个方面选择电磁环境的评价指标,再建立零代价函数的电磁环境评价模型,进一步说明前馈三层神经网络的代数算法在电磁环境评价上的应用. 相似文献
13.
ＮＴＲＯＤＵＣＴＩＯＮＡｆｔｅｒｍｕｃｈｒｅｓｅａｒｃｈａｎｄｓｏｍｅｓｕｃｃｅｓｓｆｕｌａｐ ｐｌｉｃａｔｉｏｎｓｏｆＡｒｔｉｆｉｃｉａｌＮｅｕｒａｌＮｅｔｗｏｒｋ (ＡＮＮ)ｔｏｃｏｎｔｒｏｌｓｙｓｔｅｍｓ,ＡＮＮｈａｓｂｅｃｏｍｅｏｎｅｏｆｔｈｅｉｍ ｐｏｒｔａｎｔｔｏｏｌｓｔｏｓｈｏｗｔｈｅｉｎｔｅｌｌｉｇｅｎｃｅｏｆｔｈｅｈｕ ｍａｎｂｒａｉｎ .ＳｉｎｃｅＡＮＮｃａｎｂｅｕｓｅｄｔｏｄｅｓｃｒｉｂｅａｎｙｎｏｎｌｉｎｅａｒｃｏｎｔｉｎｕｏｕｓｆｕｎｃｔｉｏｎ ,ｉｔｈａｓｄｒａｗｎｍｕｃｈａｔ… 相似文献
14.
WU Xiao-juan ZHU Xin-jian CAO Guang-yi TU Heng-yong 《浙江大学学报(A卷英文版)》2007,8(9):1505-1509
The solid oxide fuel cell (SOFC) is a nonlinear system that is hard to model by conventional methods. So far,most existing models are based on conversion laws,which are too complicated to be applied to design a control system. To facilitate a valid control strategy design,this paper tries to avoid the internal complexities and presents a modelling study of SOFC per-formance by using a radial basis function (RBF) neural network based on a genetic algorithm (GA). During the process of mod-elling,the GA aims to optimize the parameters of RBF neural networks and the optimum values are regarded as the initial values of the RBF neural network parameters. The validity and accuracy of modelling are tested by simulations,whose results reveal that it is feasible to establish the model of SOFC stack by using RBF neural networks identification based on the GA. Furthermore,it is possible to design an online controller of a SOFC stack based on this GA-RBF neural network identification model. 相似文献
15.
This paper proposes an adaptive algorithm of neural nets with a special perturbation for a real time velocity control system
of a VVVF (Variable Voltage Variable Frequency) hydraulic elevator. The weight vector of the neural network is adaptively
adjusted by the LMS (Least Mean Square) with perturbation, so it is not necessary to know the nonlinear continuous function
of the control system. The nonlinear velocity control system is considered as the controller output function in an adaptive
controller model. The experimental results obtained from the VVVF hydraulic elevator showed that the neural nets controller
using the perturbation algorithm proposed are much stabler and faster in dynamic response compared with the conventional PID
(Proportion-Integration-Derivation) controller.
Project (69775013) Supported by NSFC 相似文献
16.
刘扬 《鹭江职业大学学报》2014,(5):46-50
提出一种信息论结合粒子群优化的贝叶斯网络结构学习算法,将约束最大信息熵作为最高评分函数,对网络结构进行复杂度约束,设计了粒子位置和速度向量的操作方法,解决单纯利用KL距离进行搜索的缺陷。在网络结构的搜索空间相对较大的情况下,该优化算法能在较短的时间内收敛,获得更准确的网络结构。仿真实验结果表明,该算法在时间和精度上都具有较好的效果。 相似文献
17.
18.
张海峰 《河北工业大学成人教育学院学报》2006,21(1):39-44
神经网络是一种新兴的数学建模方法,它具有识别复杂非线性系统的特性,比较适合实时调度。论文对神经网络模型-BP神经网络的结构及算法进行了描述,在此基础上提出了基于BP神经网络的实时调度预测模型。基于BP神经网络的实时调度预测模型的输入变量是相关站点同一时间段的客流量,输出变量为发车调度形式。 相似文献
19.
针对车辆行驶下的路面附着系数估计问题,提出了扩展卡尔曼滤波算法(EKF,Extended Kalman Filter)与径向基神经网络(RBF,Radial Basis Functionneural network)相融合。通过扩展卡尔曼滤波算法得出路面附着系数估计所需要的车辆状态参数,结合轮速等直接数据采用径向基神经网络对路面附着系数进行估计。神经网络的训练样本通过Carsim/Simulink收集不同行驶工况,并采用差值寻优的方法对径向基神经网络算法中的决定系数进行优化。基于双移线工况验证了该算法在路面附着系数估计上具有较高的精准度。 相似文献
20.
1 Introduction The degree of malignancy in brain glioma[1]domi-nates the way of treatment .In case of gradeⅠorⅡaccording to Kernohan,the success rate of operationis satisfactory. Otherwise ,for gradeⅢor IV,the sur-gical risk is high ,and poor life qual… 相似文献