Max—min神经网络的一种有效学习算法

本文在Ａ．Ｂｌａｎｃｏ等人的算法的基础上，提出了ｍａｘ－ｍｉｎ神经网络的一种改进了的反馈学习算法，严格证明了该算法的迭代收敛性，理论分析及实例计算结果均表明，本文算法具有算法简单，收敛速度快，输出误差小等显著特点。     

混沌的模糊神经网络逆系统控制

提出用Sugeno型的模糊推理神经网络建立混沌系统的逆系统模型,并采用逆系统方法进行混沌的控制.这种方法的特点是可以不必建立混沌系统的解析模型,通过模糊神经网络学习混沌系统的运动规律,通过学习获得的规律对混沌进行有效的控制,并且该控制方法可以控制混沌系统以一定精度跟踪连续变化的给定信号.理论分析及针对虫口模型和Henon模型仿真研究证明了该方法的有效性 关键词： 混沌 模糊神经网络 逆系统控制     

Intelligent Control Mechanism of Part Picking Operations of Automated Warehouse

This paper studies the part picking operations of a ut omated warehouse. It assumed the demand of picking orders of automated warehouse are dynamic generated. Once the picking orders of certain period of time are kn own, it is necessary to decide an efficient order picking sequence and routing t o minimize the total travel distance to complete those orders. Assumed there are n i items to be picked in order O i. Each item in the picking ord er is located in different locations in the warehouse. Since i...     

基于微观渗流机理的宏观油藏数值模拟研究

处于高含水开发期油藏的剩余油分布主要受流体性质和岩石孔隙结构的影响，而经典数值模拟并没有考虑微观孔喉特征的影响。为此建立了描述微观孔喉特征的地层孔隙网络模型，并对构成网络的基本连线单元进行改进，使网络模型能更细致地描述油水分布特征和水驱油微观机理。利用逾渗理论计算了基于微观渗流机理的相对渗透率曲线，并将其应用到经典数值模拟计算中，实现了微观渗流机理与宏观数值模拟计算的结合。实例分析表明，利用该数值模拟计算方法得到的基于微观特征的剩余油分布更符合地下实际流体分布，其结果可为调剖堵水、化学驱提供技术参数。     

运输网络中最小饱和流的求解

运输网络中常常由于流量的不可控易发生堵塞现象.网络发生堵塞时的饱和流值达不到最大流值.最小饱和流是运输网络,尤其是紧急疏散网络设计中很重要的一个参数.通过建立网络的割集矩阵来确定网络的堵塞截面,基于此提出了求解最小饱和流的线性规划模型及算法.举例分析表明,利用该算法计算网络最小饱和流更加简便、更加实用.     

求解通信网节点间全部路由的逻辑代数化算法

经典的D IJKSTRA和BELLM AN-F LOYD通信网络路由算法,只能根据特定网络参数得到最佳路由,却无法获得网络存在的全部可用路由,而通信网理论研究及网络管理等方面,往往需要获得节点之间的全部可用路由.研究出一种路由新算法,遵循逻辑代数运算规则、采用关联矩阵中行与行之间整合与删除方式计算,N个节点的网络只需N-1次整合及删除运算,就能得到源节点到任意节点两点之间全部路由结果.详细论证了算法的正确性与合理性,简介了算法的并行运算可行性及与经典路由算法的兼容性等问题.通过算例详细说明算法的计算过程,并验证其正确性.     

神经网络在可靠性分析中的应用

应用人工神经网络对舰炮发生故障的发射炮弹数进行了预测。借助前馈神经网络对非线性函数的逼近能力，对发生故障的发射炮弹数进行了单步预测，并与使用灰色数列预测的结果进行了对比，验证了人工神经网络进行可靠性预测的可行性。     

A new method for constructing infinite families of k-tight optimal double loop networks

The double loop network (DLN) is a circulant digraph with n nodes and outdegree 2. DLN has been widely used in the designing of local area networks and distributed systems. In this paper, a new method for constructing infinite families of k-tight optimal DLN is presented. For k = 0,1,…,40, the infinite families of k-tight optimal DLN can be constructed by the new method, where the number nk(t,a) of their nodes is a polynomial of degree 2 in t and contains a parameter a. And a conjecture is proposed.     

Effect of Notoginsenoside-Rg1 on the Expression of Several Proteins in the Striatum of Rat Models with Parkinson＇s Disease

After establishing hemi-Parkinsonian rat models, the relationships between neuron death and the expression of several proteins, such as c-Fos, GFAP, GDNF, NF-κB and some cytokines were determined. Therapeutics experiments with notoginsenoside-Rg1 were carried out. The research results show that the expressions of GFAP, NF-Kκ and c-Fos will obviously increase in the lesion side of the striatum and the expression of GDNF will decrease, which implies that the signal transduction pathway may participate in the apoptosis in neurons. The levels of some cytokines such as TNF-α, IL-1β in the striatum of PD rat models increased compared to those of normal rats. The results of the therapeutics experiments show that notoginsenoside-Rg1 may repress the immune inflammation response and regulate the immune function through the neuro-immune molecular network. Therefore, notoginsenoside-Rg1 can be used as an effective drug for anti-oxidation and anti-inflammation, and can be used in the therapy of Parkinson＇s disease（PD）.     

Temperature effect on deposition rate of silicon nitride films

Temperature effects on deposition rate of silicon nitride films were characterized by building a neural network prediction model. The silicon nitride films were deposited by using a plasma enhanced chemical vapor deposition system and process parameter effects were systematically characterized by 2⁶⁻¹ fractional factorial experiment. The process parameters involved include a radio frequency power, pressure, temperature, SiH₄, N₂, and NH₃ flow rates. The prediction performance of generalized regression neural network was drastically improved by optimizing multi-valued training factors using a genetic algorithm. Several 3D plots were generated to investigate parameter effects at various temperatures. Predicted variations were experimentally validated. The temperature effect on the deposition rate was a complex function of parameters but N₂ flow rate. Larger decreases in the deposition rate with the temperature were only noticed at lower SiH₄ (or higher NH₃) flow rates. Typical effects of SiH₄ or NH₃ flow rate were only observed at higher or lower temperatures. A comparison with the refractive index model facilitated a selective choice of either SiH₄ or NH₃ for process optimization.