忆阻细胞神经网络及图像去噪和边缘提取中的应用

结合忆阻器的记忆特征和细胞神经网络高效并行处理能力,将忆阻器作为可编程连接权值,提出了一种具有忆阻器特性的细胞神经网络.计算机仿真验证了提出的忆阻细胞神经网络用于图像去噪和边缘提取的有效性.     

Representing space in a PDP network: Coarse allocentric coding can mediate metric and nonmetric spatial judgements

In one simulation, an artificial neural networkwas trained to rate the distances between pairsof cities on the map of Alberta, given onlyplace names as input. Distance ratings rangedfrom 0 (when the network rated the distancebetween a city and itself) to 10. The questionof interest was the nature of therepresentations developed by the network's sixhidden units after it successfully learned tomake the desired responses. Analyses indicatedthat the network used coarse allocentric codingto solve this problem. Each hidden unit couldbe described as occupying a position on the mapof Alberta, and each connection weight feedinginto a hidden unit was related to the distanceon the map between the hidden unit and one ofthe stimulus cities. On its own, a singlehidden unit's response was a relativelyinaccurate distance measure. However, bycombining all six hidden unit responses in acoarse coding scheme, accurate responses weregenerated by the network. In a secondsimulation, a second network was trained tomake similar judgements, but was trained toviolate the minimality constraint on metricspace when trained to judge the distancebetween a city and itself. An analysis of thisnetwork indicated that it too was using coarseallocentric coding.     

集成神经网络在智能故障诊断技术上的应用

针对单子神经网络的局限性提出了将神经网络技术集成用于智能故障诊断的思想,并对集成神经网络的诊断系统的结构和工作原理进行介绍.最后,给出一个基于两个BP子网的故障诊断系统的实例,详细介绍其诊断过程,并对其结果进行了分析.     

一种用于小波网络综合的自构造算法

讨论了一种新颖算法来进行小波网络综合。这种算法拥有自构造能力。用这种方法 ,网络可以从一个空的隐层神经元开始 ,然后自动增长。仿真表明 :所提算法优于已报道的其他算法 ,并给出了部分仿真结果。     

基于神经网络的仿真输出数据的分布识别

分布识别在仿真输出数据的分析中有着重要的理论和实际价值，但长期以来一直没有很好解决，在研究和改进神经网络的基础上，提出用多层感知机ＢＰ网格进行分布识别，给出了基于ＮＮ的分布识别模型，并进行了实验检验，实验结果表明本方法识别效率高，并具有很高的可靠性，可以辅助分析者作出准确的判断。     

基于BP神经网络的软件项目成本估测方法

为进一步提高软件项目成本估测的准确度,减少在使用传统估测方法时产生的较大误差,提出了一种基于BP神经网络算法的软件项目成本估测模型。利用BP神经网络对软件项目成本进行估计,采用梯度下降自适应Ir的BP算法训练,仿真结果表明,基于算法的软件项目成本估测值与实际成本的偏差较小。     

关于压气机过渡段设计方法的探讨

 为改善压气机过渡段内的流动损失,提高设计过程的快速性和结果的准确性。首先,发展了结合气动评估与优化算法的带支板压气机过渡段的设计方法,并编制了相应程序。针对算法各自的特点将不同的气动评估方法运用到优化方法的不同阶段,求解子午平面的二维方法用于解空间的全局寻优,精确求解三维雷诺平均Navier-Stokes (RANS)方程的方法用于进行局部寻优,这使得设计流程变得快速而不失准确性,并建立了方便进行流通面积控制的过渡段参数化方法。其次,针对一算例开展了设计工作,并分析了损失来源,结果表明过渡段的设计如果不考虑支板的影响将对结果产生重大偏差;对于进出口面积相同的过渡段设计,沿流动方向先增大后减小的面积变化有助于减小过渡段支板后半段的局部快速扩压作用与凹壁面减速作用相互叠加引起的高损失区域,避免大的流动分离;过渡段流通面积扩张度有一个最佳值,其值受支板翼型、进出口面积比等因素共同影响。最后,将本文设计方法得到的过渡段规律同前人所做类似工作得到的结论进行对比,吻合较好,说明本文发展的设计方法是可行的。     

5083铝合金力学性能的球压痕法检测研究

介绍了微压痕法在航空铝合金材料力学性能检测的研究.采用球形压头通过多级循环加载方法得到了5083铝合金材料压痕深度与载荷的关系,将微压痕数据输入经过充分训练的人工神经网络模型,计算出材料力学性能参数和材料应力应变曲线,对压痕法测量得到的材料真应力应变曲线与拉伸试验得到的结果进行了比较.     

基于PSO-GA优化的TOP-HAT形态学滤波器及其应用

针对机栽红外图像中运动弱小点目标检测的难题,提出了一种基于PSO-GA训练参数的形态学滤波器.以粒子群优化算法(Particle Swarm Optimization,PSO)为主线,按PSO算法中标准的速度和位置更新,遗传算法(Genetic Algorithm,GA)采用新的区间离散化编码和自适应的主次式交叉与变异算子,将遗传算法与粒子群优化算法的自动更新特征结合在一起,通过优化搜索全局空间获得形态学滤波器的最优参数,进而确保优化的形态学滤波器具有良好的滤波性及时效性.通过对低信噪比红外图像(SNR约为2)的测试,检测概率可以达到98％以上,与利用神经网络(Neural Network,NN)训练结构元素后的Top-Hat形态学滤波器相比提高了2％ ～3％.与GA算法相对,训练算法效能提高20％,提高了搜索最佳值的能力.     

Modelling of air temperature using remote sensing and artificial neural network in Turkey

The aim of this research was to forecast monthly mean air temperature based on remote sensing and artificial neural network (ANN) data by using twenty cities over Turkey. ANN contained an input layer, hidden layer and an output layer. While city, month, altitude, latitude, longitude, monthly mean land surface temperatures were chosen as inputs, and monthly mean air temperature was chosen as output for network. Levenberg–Marquardt (LM) learning algorithms and tansig, logsig and linear transfer functions were used in the network. The data of Turkish State Meteorological Service (TSMS) and Technological Research Council of Turkey–Bilten for the period from 1995 to 2004 were chosen as training when the data of 2005 year were being used as test. Result of research was evaluated according to statistical rules. The best linear correlation coefficient (R), and root mean squared error (RMSE) between the estimated and measured values for monthly mean air temperature with ANN and remote sensing method were found to be 0.991–1.254 K, respectively.