采用BP神经网络研究C-F键核自旋偶合常数

通常理论研究核自旋偶合常数的方法是基于线性模型进行拟合和预测，该方法在拟合和预测中仍有较大误差. 本文在前面工作的基础上，提出了基于非线性模型对C-F键核自旋偶合常数进行研究的观点，采用BP神经网络方法对C-F键核自旋偶合常数的函数关系式进行拟合，并用拟合结果对4种化合物的偶合常数进行预测. 结果表明，采用非线性的BP神经网络方法其训练效果与预测效果均优于线性模型方法；其预测误差对文中的4种化合物不超过0.40%.     

人工神经网络在配煤过程状态建模中的应用研究

本文详细介绍了人工神经网络应用于状态建模的方法．对神经网络应用中的一些难点提出了切实可行且有效的解决措施，并举例作了应用示范．同时还介绍了神经网络方法应用于优化动力配煤的情况，并就神经网络方法在优化动力配煤中的进一步应用作了展望．     

Solution of a diffusion equation of smoke molecules due to constant point source in gravitational field

From both the Langevin equation, including a gravitational term, the Fokker-Planck equation based on the dynamical behavior of Brownian particles, and equation of smoke molecular diffusion due to a constant point source is introduced and is solved by applying the Laplace transformation with the convolution theorem.The solution is expressed by the complementary error function with a mean pathway of smoke molecules affected by gravity and is proved to be reduced to conventional forms by a certain restriction neglecting gravity without any forced term.     

基于加强型BP算法的神经网络故障诊断研究

文章给出了利用神经网络进行故障诊断的可行性、基本原理、诊断过程分析、和参数优化过程 ,并得出较为理想的诊断结果 .     

一元非线性系统的BP算法研究

详细研究了一种一元非线性系统的BP算法,提出并证明了该算法的收敛性定理,给出了该算法的应用实例.计算机仿真结果表明:对于随机给定的初始点,该算法都能稳定收敛到它的一个实根,而且计算精度可控,因此,该算法是有效的.与传统的计算方法相比,本文算法不仅具有收敛速度快,而且计算精度可控以及初始点随机给定的集中优点.     

Polymer synthesis in the presence of bis(cyclopentadienyl) derivatives of Group IV–VI transition metal dichlorides: a quantum chemical study of particular reaction stages

Key pathways of interaction between growing radicals of vinyl monomers and bis(cyclopentadienyl) derivatives of Group IV–VI transition metal dichlorides were studied by the BP86/6-31G(d) and B3LYP/LanL2DZ quantum chemical methods. Prospects for use of these organometallic compounds as chain growth regulators in controlled polymerization were assessed. The character of the interaction of the compounds studied with the growing radicals is mainly determined by the metal atom. Dedicated to Academician G. A. Abakumov on the occasion of his 70th birthday. Published in Russian in Izvestiya Akademii Nauk. Seriya Khimicheskaya, No. 9, pp. 1690–1694, September, 2007.     

基于AR模型与神经网络的核爆与闪电电磁脉冲信号识别

 对平稳随机信号功率谱估计的AR模型,分别利用自相关函数法和Burg算法求该模型系数,作为核爆炸和闪电电磁脉冲信号的特征值;采用BP神经网络作为分类器以及不同的隐含层数和隐含层节点数,对核爆和闪电电磁脉冲实测数据进行识别研究。结果表明：AR参数模型法对两类信号特征值提取是非常有效的,采用Burg算法来求AR模型参数,其特征值提取效果优于自相关函数法。     

On the convergence of modified Noor iterations with errors for asymptotically nonexpansive mappings

In this paper, several weak and strong convergence theorems are established for a modified Noor iterative scheme with errors for three asymptotically nonexpansive mappings in Banach spaces. Mann-type, Ishikawa-type, and Noor-type iterations are covered by the new iteration scheme. Our results extend and improve the recently announced ones [B.L. Xu, M.A. Noor, Fixed point iterations for asymptotically nonexpansive mappings in Banach spaces, J. Math. Anal. Appl. 267 (2002) 444-453; Y.J. Cho, H. Zhou, G. Guo, Weak and strong convergence theorems for three-step iterations with errors for asymptotically nonexpansive mappings, Comput. Math. Appl. 47 (2004) 707-717] and many others.     

Three-way analysis of imprecise data

Data are often affected by uncertainty. Uncertainty is usually referred to as randomness. Nonetheless, other sources of uncertainty may occur. In particular, the empirical information may also be affected by imprecision. Also in these cases it can be fruitful to analyze the underlying structure of the data. In this paper we address the problem of summarizing a sample of three-way imprecise data. In order to manage the different sources of uncertainty a twofold strategy is adopted. On the one hand, imprecise data are transformed into fuzzy sets by means of the so-called fuzzification process. The so-obtained fuzzy data are then analyzed by suitable generalizations of the Tucker3 and CANDECOMP/PARAFAC models, which are the two most popular three-way extensions of Principal Component Analysis. On the other hand, the statistical validity of the obtained underlying structure is evaluated by (nonparametric) bootstrapping. A simulation experiment is performed for assessing whether the use of fuzzy data is helpful in order to summarize three-way uncertain data. Finally, to show how our models work in practice, an application to real data is discussed.     

一种快速且全局收敛的BP神经网络学习算法

目前误差反向传播(BP)算法在训练多层神经网络方面有很多成功的应用.然而,BP算法也有一些不足:收敛缓慢和易陷入局部极小点等.提出一种快速且全局收敛的BP神经网络学习算法,并且对该优化算法的全局收敛性进行分析和详细证明.实证结果表明提出的算法比标准的BP算法效率更高且更精确.