Existence of Periodic Solutions for Neutral-Type Neural Networks with Delays on Time Scales

In this paper, we employ a fixed point theorem due to Krasnosel’skii to attain the existence of periodic solutions for neutral-type neural networks with delays on a periodic time scale. Some new sufficient conditions are established to show that there exists a unique periodic solution by the contraction mapping principle.

State estimation for neural neutral-type networks with mixed time-varying delays and Markovian jumping parameters

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.

Almost sure exponential stability of neutral stochastic delayed cellular neural networks

In this paper, almost sure exponential stability of neutral delayed cellular neural networks which are in the noised environment is studied by decomposing the state space to sub-regions in view of the saturation linearity of output functions of neurons of the cellular neural networks. Some algebraic criteria are obtained and easily verified. Some examples are given to illustrate the correctness of the results obtained.

Periodic Solution for Neutral Type Neural Networks

The principle aim of this paper is to explore the existence of periodic solution of neural networks model with neutral delay. Sufficient and realistic conditions are obtained by means of an abstract continuous theorem of k-set contractive operator and some analysis technique.

Novel delay-dependent stability analysis of Takagi-Sugeno fuzzy uncertain neural networks with time varying delays

This paper presents the stability analysis for a class of neural networks with time varying delays that are represented by the Takagi^ugeno IT-S） model. The main results given here focus on the stability criteria using a new Lyapunov functional. New relaxed conditions and new linear matrix inequality-based designs are proposed that outperform the previous results found in the literature. Numerical examples are provided to show that the achieved conditions are less conservative than the existing ones in the literature.

基于信号图像化和CNN-ResNet的配电网单相接地故障选线方法

配电网发生单相接地故障时,零序电流呈现较强的非线性与非平稳性,故障选线较为困难,针对此问题,提出一种基于信号图像化和卷积神经网络-残差网络的配电网单相接地故障选线方法。首先,利用排列熵优化变分模态分解算法的参数,将零序电流信号分解成一系列固有模态函数;其次,引入新的数据预处理方式,将固有模态函数转成二维图像,获得零序电流信号的时频特征图;最后,利用一维卷积神经网络提取零序电流信号的相关性和特征,利用残差网络提取时频特征图的特征,将两个网络融合,构建混合卷积神经网络结构,实现故障选线。仿真与实验结果表明,该方法能够在高阻接地、采样时间不同步、强噪声等情况下准确地选择出故障线路,可满足配电网对故障选线准确性和可靠性的需求。

基于事件触发控制的中立型神经网络簇同步

研究了事件触发下带有Lévy噪声的中立型耦合神经网络的簇同步问题。首先,在混合时滞和不连续噪声的条件下,提出了一种事件触发机制与牵制控制方法结合的控制策略,应用于神经网络的簇同步中,以提高簇同步效率,缓解网络负担。然后,通过构建新的Lyapunov泛函,以及使用线性矩阵不等式(linear matrix inequalities,LMI)分析技术和广义Dynkin公式,得到误差系统的簇同步准则,进一步保证了耦合神经网络的簇同步。最后,通过一个数值仿真,验证了所得结论的可行性。

具有比例时滞和D算子的BAM神经网络概周期解的存在性与稳定性

为了探讨一类含比例时滞和D算子的中立型BAM神经网络的概周期解的存在性与广义指数稳定性,首先,通过构造概周期函数空间,并利用压缩不动点原理,得到确保系统概周期解存在的充分条件,其次,使用微分不等式技巧得到确保系统概周期解广义指数稳定的充分条件.发现若系统的参数满足一定的条件,那么系统的概周期解是存在的,且是广义指数稳定的,而且所得结果与比例时滞无关.所得结论推进了现有文献中的相关工作.

带有混合时滞的中立型随机神经网络的状态估计

研究了一类具有Markov跳变参数的中立型神经网络的状态估计问题,所考虑的神经网络含有Markov模态依赖的离散时滞和无穷分布时滞。通过构造模态依赖的Lyapunov-Krasovskii泛函,得到状态估计误差系统全局渐近稳定的充分条件,从而保证了所考虑神经网络的全阶状态估计器的存在。通过将非线性耦合的矩阵不等式转化为线性矩阵不等式,利用线性矩阵不等式计算状态估计器的增益矩阵,由此解决了神经网络的状态估计问题。最后,通过数值例子说明所提出设计结果的有效性。

具有随机扰动和不确定性的中立型耦合神经网络有限时间同步

研究了具有时滞、不确定性和随机扰动的中立型耦合神经网络的有限时间同步问题.在Lyapunov稳定性理论的基础上,结合不等式技术得到了有限时间同步判据.接着构造合适的状态反馈控制器,使主从系统实现了有限时间同步.最后,通过一个数值仿真验证了所提出理论的有效性.

Exponential stability analysis for neutral BAM neural networks with time-varying delays and stochastic disturbances

This paper is concerned with the global exponential stability analysis problem for a class of neutral bidi- rectional associative memory （BAM） neural networks with time-varying delays and stochastic disturbances. The stochastic disturbances are described by state-dependent stochastic processes. By utilizing an appropriately constructed Lyapunov- Krasovskii functional （LKF） and some stochastic analysis approaches, novel delay-dependent conditions are established in terms of linear matrix inequalities （LMIs）, which can be easily solved by existing convex optimization techniques. Further- more, the exponential convergence rate can be estimated based on the obtained results. An illustrate example is given to demonstrate the effectiveness of the proposed methods.

Bogdanov–Takens Bifurcation in a Neutral Delayed Hopfield Neural Network with Bidirectional Connection

In this paper,a neutral Hopfield neural network with bidirectional connection is considered.In the first step,by choosing the connection weights as parameters bifurcation,the critical point at which a zero root of multiplicity two occurs in the characteristic equation associated with the linearized system.In the second step,we studied the zeros of a third degree exponential polynomial in order to make sure that except the double zero root,all the other roots of the characteristic equation have real parts that are negative.Moreover,we find the critical values to guarantee the existence of the Bogdanov–Takens bifurcation.In the third step,the normal form is obtained and its dynamical behaviors are studied after the use of the reduction on the center manifold and the theory of the normal form.Furthermore,for the demonstration of our results,we have given a numerical example.

具比例时滞四元数值中立型Cohen-Grossberg神经网络稳定性分析

主要研究具比例时滞四元数值中立型Cohen-Grossberg神经网络的稳定性.通过利用M-矩阵理论、同胚映射原理、Lyapunov函数、线性矩阵不等式等技术,得到了系统平衡点的存在唯一性和全局指数稳定性的充分条件;最后通过数值仿真验证所得结果的有效性和正确性.

神经网络在中国“双碳”目标下碳排放量预测中的应用

通过神经网络建模拟合得到了中国能源清单数据与碳排放数据之间的关系,并对国家整体和省级层面的能源数据进行了一个较好的拟合和预测。研究预测结果显示只有通过合理调整现有的能源结构,才能实现“双碳”目标,为中国实现“双碳”目标提供了理论参考。

一类新的变时滞中立型神经网络的全局渐近稳定性条件

研究了一类激活函数的状态变量带有微分时滞的中立型神经网络的稳定性问题.通过构造李亚普诺夫函数,并利用LMI分析技巧,获得了该类中立型神经网络的全局渐近稳定性的充分条件.最后通过实际算例验证了所得结果的有效性.

具有连续分布时滞的中立型Hopfield神经网络的吸引集

给出了具有连续分布时滞的中立型Hopfield网络吸引集存在的充分条件

中立型细胞神经网络的稳定性分析

基于线性矩阵不等式(LMI)技巧对中立型细胞神经网络的稳定性问题进行了研究,给出了神经网络稳定的一个充分性条件和系统稳定中立项所必须满足的一个必要条件。仿真结果证明了所给算法的有效性,同时表明所得结论优于Y.M.ZHANG等的结果。

重庆地区混凝土构件碳化规律的神经网络描述

碳化是混凝土结构构件中普遍存在的问题,随混凝土碳化的发展可能将逐步导致钢筋产生锈蚀,从而影响构件的耐久性。影响混凝土碳化的因素较多,即使相同的影响因素,在不同地区对混凝土碳化影响程度也会有所差别。因此,考虑多因素和不同地区特点建立特定区域的混凝土碳化模型具有重要工程价值。根据部分重庆地区不同时期自然条件下混凝土构件碳化深度实测数据,采用人工神经网络方法初步建立了重庆地区自然条件下混凝土碳化模型。通过计算结果和实测数据的对比,探讨了模型的可行性和适用性,为进一步确定重庆地区自然条件下混凝土碳化规律创造了初步条件。

一类中立型神经网络概周期解的存在性及稳定性

研究一类具有分布和时变时滞的中立型神经网络的概周期解.利用Banach空间中的不动点定理以及相关分析技巧,得到了概周期解的存在性、唯一性及稳定性的新结果.最后通过实例验证了所得结果的有效性.

含有未知参数的中立型神经网络自适应同步

针对同步系统中含有未知参数的情况,讨论了一类驱动—响应系统的自适应同步控制问题,其中驱动系统和响应系统的动态均由一类中立型神经网络描述。利用Barbalat引理和自适应控制方法,设计了一个自适应控制器以及响应系统参数的自适应更新规则,给出了驱动系统和响应系统的动态达到全局同步的判定准则。该文判据以线性矩阵不等式形式给出,可以利用MATLAB-LMI工具箱求解。仿真算例验证了算法的有效性和可行性。