期刊文献+

二次检索

题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

年份

学科

期刊收录

共找到41篇文章
< 1 2 3 >
每页显示 20 50 100
State estimation for neural neutral-type networks with mixed time-varying delays and Markovian jumping parameters 被引量:2
1
作者 S.Lakshmanan Ju H.Park +1 位作者 H.Y.Jung P.Balasubramaniam 《Chinese Physics B》 SCIE EI CAS CSCD 2012年第10期29-37,共9页
This paper is concerned with a delay-dependent state estimator for neutral-type neural networks with mixed timevarying delays and Markovian jumping parameters.The addressed neural networks have a finite number of mode... This paper is concerned with a delay-dependent state estimator for neutral-type neural networks with mixed timevarying delays and Markovian jumping parameters.The addressed neural networks have a finite number of modes,and the modes may jump from one to another according to a Markov process.By construction of a suitable Lyapunov-Krasovskii functional,a delay-dependent condition is developed to estimate the neuron states through available output measurements such that the estimation error system is globally asymptotically stable in a mean square.The criterion is formulated in terms of a set of linear matrix inequalities(LMIs),which can be checked efficiently by use of some standard numerical packages. 展开更多
关键词 neural networks state estimation neutral delay Markovian jumping parameters
下载PDF
Improved results on state estimation for neural networks with time-varying delays 被引量:1
2
作者 Tao LI 1 , Shumin FEI 2 , Hong LU 2 (1.School of Instrument Science & Engineering, Southeast University, Nanjing Jiangsu 210096, China 2.Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing Jiangsu 210096, China) 《控制理论与应用(英文版)》 EI 2010年第2期215-221,共7页
In this paper, some improved results on the state estimation problem for recurrent neural networks with both time-varying and distributed time-varying delays are presented. Through available output measurements, an im... In this paper, some improved results on the state estimation problem for recurrent neural networks with both time-varying and distributed time-varying delays are presented. Through available output measurements, an improved delay-dependent criterion is established to estimate the neuron states such that the dynamics of the estimation error is globally exponentially stable, and the derivative of time-delay being less than 1 is removed, which generalize the existent methods. Finally, two illustrative examples are given to demonstrate the effectiveness of the proposed results. 展开更多
关键词 Exponential state estimator Recurrent neural networks Exponential stability Time-varying delays Linear matrix inequality (LMI)
下载PDF
Augmented Lyapunov approach to H_∞ state estimation of static neural networks with discrete and distributed time-varying delays
3
作者 M.Syed Ali R.Saravanakumar 《Chinese Physics B》 SCIE EI CAS CSCD 2015年第5期140-147,共8页
This paper deals with H∞ state estimation problem of neural networks with discrete and distributed time-varying delays. A novel delay-dependent concept of H∞ state estimation is proposed to estimate the H∞ performa... This paper deals with H∞ state estimation problem of neural networks with discrete and distributed time-varying delays. A novel delay-dependent concept of H∞ state estimation is proposed to estimate the H∞ performance and global asymptotic stability of the concerned neural networks. By constructing the Lyapunov-Krasovskii functional and using the linear matrix inequality technique, sufficient conditions for delay-dependent H∞ performances are obtained, which can be easily solved by some standard numerical algorithms. Finally, numerical examples are given to illustrate the usefulness and effectiveness of the proposed theoretical results. 展开更多
关键词 distributed delay H∞ state estimation neural networks stability analysis
下载PDF
Stability Analysis of Cohen-Grossberg Neural Networks with Time-Varying Delays 被引量:1
4
作者 刘艳青 唐万生 《Transactions of Tianjin University》 EI CAS 2007年第1期12-17,共6页
The global exponential stability of Cohen-Grossberg neural networks with time-varying delays is studied. By constructing several suitable Lyapunov functionals and utilizing differential in-equality techniques, some su... The global exponential stability of Cohen-Grossberg neural networks with time-varying delays is studied. By constructing several suitable Lyapunov functionals and utilizing differential in-equality techniques, some sufficient criteria for the global exponential stability and the exponential convergence rate of the equilibrium point of the system are obtained. The criteria do not require the activation functions to be differentiable or monotone nondecreasing. Some stability results from previous works are extended and improved. Comparisons are made to demonstrate the advantage of our results. 展开更多
关键词 Cohen-Grossberg neural networks time-varying delay equilibrium point global exponential stability convergence rate
下载PDF
Global exponential stability for delayed cellular neural networks and estimate of exponential convergence rate 被引量:1
5
作者 张强 马润年 许进 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2004年第3期344-349,共6页
Some sufficient conditions for the global exponential stability and lower bounds on the rate of exponential convergence of the cellular neural networks with delay (DCNNs) are obtained by means of a method based on del... Some sufficient conditions for the global exponential stability and lower bounds on the rate of exponential convergence of the cellular neural networks with delay (DCNNs) are obtained by means of a method based on delay differential inequality. The method, which does not make use of any Lyapunov functional, is simple and valid for the stability analysis of neural networks with delay. Some previously established results in this paper are shown to be special casses of the presented result. 展开更多
关键词 global exponential stability convergence rate cellular neural networks with delay delay differential inequality.
下载PDF
Effective suppression of beta oscillation in Parkinsonian state via a noisy direct delayed feedback control scheme
6
作者 Hai-Tao Yu Zi-Han Meng +2 位作者 Chen Liu Jiang Wang Jing Liu 《Chinese Physics B》 SCIE EI CAS CSCD 2021年第3期555-563,共9页
This work explores the function of the noisy direct delayed feedback(NDDF)control strategy in suppressing the pathological oscillations in the basal ganglia(BG)with Parkinson’s disease(PD).Deep brain stimulation(DBS)... This work explores the function of the noisy direct delayed feedback(NDDF)control strategy in suppressing the pathological oscillations in the basal ganglia(BG)with Parkinson’s disease(PD).Deep brain stimulation(DBS)alleviates the PD state fantastically.However,due to its unclear mechanism and open-loop characteristic,it is challenging to further improve its effects with lower energy expenditure.The noise stimulus performs competitively in alleviating the PD state theoretically,but it cannot adapt to the neural condition timely and automatically due to its open-loop control scheme.The direct delayed feedback(DDF)control strategy is able to disturb excessive synchronous effectively.Therefore,the NDDF control strategy is proposed and researched based on a BG computational model,which can reflect the intrinsic properties of the BG neurons and their connections with thalamic neurons.Simulation results show that the NDDF control strategy with optimal parameters is effective in removing the pathological beta oscillations.By comparison,we find the NDDF control strategy performs more excellent than DDF in alleviating PD state.Additionally,we define the multiple-NDDF control strategy and find that the multiple-NDDF with appropriate parameters performs better than NDDF.The obtained results contribute to the cure for PD symptoms by optimizing the noise-induced improvement of the BG dysfunction. 展开更多
关键词 basal ganglia neural networks Parkinsonian state noise delayed feedback
下载PDF
Exponential convergence and stability of delayed fuzzy cellular neural networks with time-varying coefficients 被引量:1
7
作者 Manchun TAN 《控制理论与应用(英文版)》 EI 2011年第4期500-504,共5页
In this paper, the dynamic behaviors of fuzzy cellular neural networks (FCNNs) with time-varying coefficients and delays are considered. Some criteria are established to ensure the exponential convergence or exponen... In this paper, the dynamic behaviors of fuzzy cellular neural networks (FCNNs) with time-varying coefficients and delays are considered. Some criteria are established to ensure the exponential convergence or exponential stability of such neural networks. The effectiveness of obtained results is illustrated by a numerical example. 展开更多
关键词 delayed neural networks Exponential convergence Exponential stability Fuzzy cellular neural networks Time-varying coefficients
原文传递
Global Exponential Convergence of Neutral Type Competitive Neural Networks with D Operator and Mixed Delay
8
作者 AOUITI Chaouki ASSALI El Abed BEN GHARBIA Imen 《Journal of Systems Science & Complexity》 SCIE EI CSCD 2020年第6期1785-1803,共19页
The models of competitive neural network(CNN)was in recent past proposed to describe the dynamics of cortical cognitive maps with unsupervised synaptic modifications,where there are two types of memories:Long-term mem... The models of competitive neural network(CNN)was in recent past proposed to describe the dynamics of cortical cognitive maps with unsupervised synaptic modifications,where there are two types of memories:Long-term memories(LTM)and short-term memories(STM),LTM presents unsupervised and slow synaptic modifications and STM characterize the fast neural activity.This paper is concerned with a class of neutral type CNN’s with mixed delay and D operator.By employing the appropriate differential inequality theory,some sufficient conditions are given to ensure that all solutions of the model converge exponentially to zero vector.Finally,an illustrative example is also given at the end of this paper to show the effectiveness of the proposed results. 展开更多
关键词 Competitive neural networks D operator exponential convergence neutral type delay
原文传递
Combining unscented Kalman filter and wavelet neural network for anti-slug
9
作者 Chuan Wang Long Chen +7 位作者 Lei Li Yong-Hong Yan Juan Sun Chao Yu Xin Deng Chun-Ping Liang Xue-Liang Zhang Wei-Ming Peng 《Petroleum Science》 SCIE EI CAS CSCD 2023年第6期3752-3765,共14页
The stability of the subsea oil and gas production system is heavily influenced by slug flow. One successful method of managing slug flow is to use top valve control based on subsea pipeline pressure. However, the com... The stability of the subsea oil and gas production system is heavily influenced by slug flow. One successful method of managing slug flow is to use top valve control based on subsea pipeline pressure. However, the complexity of production makes it difficult to measure the pressure of subsea pipelines, and measured values are not always accessible in real-time. The research introduces a technique for integrating Unscented Kalman Filter (UKF) and Wavelet Neural Network (WNN) to estimate the state of subsea pipeline pressure using historical data and a state model. The proposed method treats multiphase flow transport as a nonlinear model, with a dynamic WNN serving as the state observer. To achieve real-time state estimation, the WNN is included into the UKF algorithm to create a WNN-based UKF state equation. Integrate WNN and UKF in a novel way to predict system state accurately. The simulated results show that the approach can efficiently predict the inlet pressure and manage the slug flow in real-time using the riser's top pressure, outlet flow and valve opening. This method of estimate can significantly increase the control effect. 展开更多
关键词 state estimation stable control Method fusion Wavelet neural network Unscented Kalman filter
下载PDF
H_∞ State Estimation for Stochastic Markovian Jumping Neural Network with Time-varying Delay and Leakage Delay
10
作者 Ya-Jun Li Zhao-Wen Huang Jing-Zhao Li 《International Journal of Automation and computing》 EI CSCD 2019年第3期329-340,共12页
The H_∞state estimation problem for a class of stochastic neural networks with Markovian jumping parameters and leakage delay is investigated in this paper.By employing a suitable Lyapunov functional and inequality t... The H_∞state estimation problem for a class of stochastic neural networks with Markovian jumping parameters and leakage delay is investigated in this paper.By employing a suitable Lyapunov functional and inequality technic,the suffcient conditions for exponential stability as well as prescribed H_∞norm level of the state estimation error system are proposed and verified,and all obtained results are expressed in terms of strict linear matrix inequalities(LMIs).Examples and simulations are presented to show the effectiveness of the proposed methods,at the same time,the effect of leakage delay on stability of neural networks system and on the attenuation level of state estimator are discussed. 展开更多
关键词 H_∞ filtering state estimation Markovian JUMP exponential stability linear matrix inequality(LMI) neural networks time-varying delay LEAKAGE delay
原文传递
忆阻耦合异构忆阻细胞神经网络的多稳态与相位同步研究
11
作者 武花干 边逸轩 +1 位作者 陈墨 徐权 《电子与信息学报》 EI CAS CSCD 北大核心 2024年第9期3818-3826,共9页
忆阻具有天然的可塑性,可实现与生物神经元和突触所具有的相似或相同机制的硅基神经元和纳米突触。将忆阻用作突触耦合两个异构的忆阻细胞神经网络,该文构建了一个忆阻耦合异构忆阻细胞神经网络。该耦合网络含有一个与忆阻突触初值条件... 忆阻具有天然的可塑性,可实现与生物神经元和突触所具有的相似或相同机制的硅基神经元和纳米突触。将忆阻用作突触耦合两个异构的忆阻细胞神经网络,该文构建了一个忆阻耦合异构忆阻细胞神经网络。该耦合网络含有一个与忆阻突触初值条件和子网初值条件相关的空间平衡点集,可呈现出复杂的动力学演化。利用数值仿真方法,揭示了耦合网络依赖于初值条件而存在的稳定点、周期、混沌、超混沌以及无界振荡等多稳态行为。此外,在忆阻突触的调控下,两个异构子网可达成相位同步。最后,基于STM32单片机硬件平台完成了电路实验验证。 展开更多
关键词 忆阻 细胞神经网络 异构网络 多稳态 相位同步
下载PDF
Convergence of neutral type proportional-delayed HCNNs with D operators 被引量:3
12
作者 Yanli Xu Jiaming Zhong 《International Journal of Biomathematics》 SCIE 2019年第1期33-41,共9页
This paper is concerned with neutral type high-order cellular neural networks(HCNNs)involving proportional delays and D operators.Some criteria are established for the global exponential convergence of the addressed m... This paper is concerned with neutral type high-order cellular neural networks(HCNNs)involving proportional delays and D operators.Some criteria are established for the global exponential convergence of the addressed models by using differential inequality techniques.Moreover,an example and its numerical simulations are employed to illustrate the main results. 展开更多
关键词 EXPONENTIAL convergence NEUTRAL type HIGH-ORDER cellular neural networks proportional delay D OPERATOR
原文传递
Legendre Neural Network for Solving Linear Variable Coefficients Delay Differential-Algebraic Equations with Weak Discontinuities 被引量:3
13
作者 Hongliang Liu Jingwen Song +2 位作者 Huini Liu Jie Xu Lijuan Li 《Advances in Applied Mathematics and Mechanics》 SCIE 2021年第1期101-118,共18页
In this paper,we propose a novel Legendre neural network combined with the extreme learning machine algorithm to solve variable coefficients linear delay differential-algebraic equations with weak discontinuities.Firs... In this paper,we propose a novel Legendre neural network combined with the extreme learning machine algorithm to solve variable coefficients linear delay differential-algebraic equations with weak discontinuities.First,the solution interval is divided into multiple subintervals by weak discontinuity points.Then,Legendre neural network is used to eliminate the hidden layer by expanding the input pattern using Legendre polynomials on each subinterval.Finally,the parameters of the neural network are obtained by training with the extreme learning machine.The numerical examples show that the proposed method can effectively deal with the difficulty of numerical simulation caused by the discontinuities. 展开更多
关键词 convergence delay differential-algebraic equations Legendre activation function neural network.
原文传递
延迟离散Hopfield型神经网络异步收敛性 被引量:9
14
作者 邱深山 徐晓飞 +1 位作者 刘明珠 王亚东 《计算机研究与发展》 EI CSCD 北大核心 1999年第5期546-552,共7页
离散Hopfield型神经网络的一个重要性质是异步运行方式下总能收敛到稳定态;同步运行方式下总能收敛到周期不超过2的极限环.它是该模型可以用于联想记忆设计、组合优化计算的理论基础.文中给出了延迟离散Hopfield型... 离散Hopfield型神经网络的一个重要性质是异步运行方式下总能收敛到稳定态;同步运行方式下总能收敛到周期不超过2的极限环.它是该模型可以用于联想记忆设计、组合优化计算的理论基础.文中给出了延迟离散Hopfield型网络的收敛性定理.在异步运行方式下,证明了对称连接权阵的收敛性定理,推广了已有的离散Hop-field型网络的收敛性结果,给出了能量函数极大值点与延迟离散Hopfield型网络的稳定态的关系及稳定态邻域的演化特征,得到了能量函数收敛与异步运行时网络达到稳定的协调关系. 展开更多
关键词 神经网络 延迟 收敛性 稳定态 HOPFIELD网络
下载PDF
飞机液压系统热分析方法的研究 被引量:10
15
作者 习仁国 刘卫国 +1 位作者 陈焕明 范开华 《机床与液压》 北大核心 2011年第23期41-44,共4页
分析飞机液压系统高压化状态下的发热问题,采用稳态热分析来估算液压系统的平衡温度,采用瞬态热分析来预测系统温度变化的规律。通过这两种方法的比较,介绍一种新的液压系统热分析方法,即神经网络分析方法,并进行初步的热分析计算,为液... 分析飞机液压系统高压化状态下的发热问题,采用稳态热分析来估算液压系统的平衡温度,采用瞬态热分析来预测系统温度变化的规律。通过这两种方法的比较,介绍一种新的液压系统热分析方法,即神经网络分析方法,并进行初步的热分析计算,为液压系统的散热设计提供依据。 展开更多
关键词 液压系统 稳态 瞬态 热分析 神经网络
下载PDF
延迟离散Hopfield-型网络广义异步收敛性分析 被引量:2
16
作者 邱深山 刘永清 +1 位作者 刘明珠 宁殿双 《系统工程与电子技术》 EI CSCD 2000年第2期4-6,16,共4页
给出了延迟离散Hopfield -型神经网络的收敛性定理。在广义异步运行方式下 ,证明了对称连接权阵 (只要w0 对称 )条件下的收敛性定理 ,推广了已有的延迟离散Hopfield -型神经网络的收敛性结果 ,表明网络收敛滞后于能量函数收敛最多 2n+1... 给出了延迟离散Hopfield -型神经网络的收敛性定理。在广义异步运行方式下 ,证明了对称连接权阵 (只要w0 对称 )条件下的收敛性定理 ,推广了已有的延迟离散Hopfield -型神经网络的收敛性结果 ,表明网络收敛滞后于能量函数收敛最多 2n+1步。最后给出了能量函数的极大值点与延迟离散Hopfield -型神经网络的稳定态的关系。 展开更多
关键词 异步收敛性 HOPFIELD 神经网络 人工智能
下载PDF
Hopfield-型网络求解优化问题的一般演化规则 被引量:2
17
作者 邱深山 邓飞其 刘永清 《自动化学报》 EI CSCD 北大核心 2004年第4期507-515,共9页
基于离散Hopfield-型网络和延迟离散Hopfield-型网络求解优化问题提出了两种一般演化规则,演化序列的动态阈值是这些规则的重要特征,并获得了收敛性定理.推广了已有的离散Hopfield-型网络和延迟离散Hopfield-型网络的收敛性结果,给出了... 基于离散Hopfield-型网络和延迟离散Hopfield-型网络求解优化问题提出了两种一般演化规则,演化序列的动态阈值是这些规则的重要特征,并获得了收敛性定理.推广了已有的离散Hopfield-型网络和延迟离散Hopfield-型网络的收敛性结果,给出了能量函数局部极大值点与延迟离散Hopfield-型网络的稳定态的关系的充分必要条件.鉴于延迟离散Hopfield-型网络更有效地应用于优化计算问题,给出了一般分解策略.实验表明与离散Hopfield-型网络的算法相比,文中提出的算法既有较高的收敛率又缩短了演化时间. 展开更多
关键词 离散Hopfield-型网络 延迟 收敛性 稳定态
下载PDF
Hopfield网络的全局指数稳定性 被引量:6
18
作者 朱培勇 孙世新 《控制理论与应用》 EI CAS CSCD 北大核心 2006年第2期302-305,共4页
在研究Hopfield神经网络时通常都假设输出响应函数是光滑的增函数.但实际应用中遇到的大多数函数都是非光滑函数.因此,本文将通常论文中Hopfield神经网络的输出响应函数连续可微的假设削弱为满足L ipschitz条件.通过引入Lyapunov函数的... 在研究Hopfield神经网络时通常都假设输出响应函数是光滑的增函数.但实际应用中遇到的大多数函数都是非光滑函数.因此,本文将通常论文中Hopfield神经网络的输出响应函数连续可微的假设削弱为满足L ipschitz条件.通过引入Lyapunov函数的方法,证明了Hopfield神经网络全局指数收敛的一个充分性定理.并且由此定理获得该类网络全局指数稳定的几个判据.这定理与判据是近期相应文献主要结果的极大改进. 展开更多
关键词 HOPFIELD网络 全局指数收敛 全局指数稳定 平衡点 LIPSCHITZ条件
下载PDF
延迟离散Hopfield网络的动态特征分析 被引量:2
19
作者 马润年 张强 许进 《计算机研究与发展》 EI CSCD 北大核心 2003年第4期550-555,共6页
神经网络的稳定性被认为是神经网络各种应用的基础 主要利用网络的状态转移方程和能量函数来研究带有延迟项的离散Hopfield神经网络动力学行为 给出了延迟离散Hopfield神经网络收敛于周期小于等于 2的极限环的一些充分条件 给出了延... 神经网络的稳定性被认为是神经网络各种应用的基础 主要利用网络的状态转移方程和能量函数来研究带有延迟项的离散Hopfield神经网络动力学行为 给出了延迟离散Hopfield神经网络收敛于周期小于等于 2的极限环的一些充分条件 给出了延迟网络收敛于周期为 2和 4的特殊极限环的一些充分条件 同时 ,得到了网络不存在任何稳定点的一些必要条件 所获结果不仅推广了一些已有的结论 。 展开更多
关键词 延迟离散Hopfield网络 神经网络 动态特征分析 稳定性 动力学行为
下载PDF
二进Hopfield型神经网络的记忆容量 被引量:4
20
作者 梁学斌 吴立德 《电子学报》 EI CAS CSCD 北大核心 1996年第4期21-23,共3页
本文证明了具有N个神经元的二进Hopfield型神经网络可存储的记忆模式的最大数目为2N.对于任意K(1≤K≤2N)个N维二进值向量,给出了它们成为具有N个神经元的二进Hopfield型神经网络稳定态的充要条件.文中... 本文证明了具有N个神经元的二进Hopfield型神经网络可存储的记忆模式的最大数目为2N.对于任意K(1≤K≤2N)个N维二进值向量,给出了它们成为具有N个神经元的二进Hopfield型神经网络稳定态的充要条件.文中指出了一个二进Hopfield型神经网络有可能没有任何稳定态,这是与连续Hopfield型神经网络的一个重要区别.最后。 展开更多
关键词 二进Hopfield型 神经网络 记忆模式 稳定态
下载PDF
上一页 1 2 3 下一页 到第
使用帮助 返回顶部