Using neural networks to learn hand-eye co-ordination

The work presented in this paper shows how the association of proprioceptive and exteroceptive stimuli can enable a Kohonen neural network, controlling a robot arm, to learn hand-eye co-ordination so that the arm can reach for and track a visually presented target. The approach presented in this work assumes no a priorimodel of arm kinematics or of the imaging characteristics of the cameras. No explicit representation, such as homogeneous transformations, is used for the specification of robot pose, and camera calibration and triangulation are done implicitly as the system adapts and learns its hand-eye co-ordination by experience. This research is validated on physical devices and not by simulation.     

Neural networks for contract bridge bidding

The objective of this study is to explore the possibility of capturing the reasoning process used in bidding a hand in a bridge game by an artificial neural network. We show that a multilayer feedforward neural network can be trained to learn to make an opening bid with a new hand. The game of bridge, like many other games used in artificial intelligence, can easily be represented in a machine. But, unlike most games used in artificial intelligence, bridge uses subtle reasoning over and above the agreed conventional system, to make a bid from the pattern of a given hand. Although it is difficult for a player to spell out the precise reasoning process he uses, we find that a neural network can indeed capture it. We demonstrate the results for the case of one-level opening bids, and discuss the need for a hierarchical architecture to deal with bids at all levels.     

动态模糊神经网络在大坝变形预报中的应用

针对静态模糊神经网络的局限性,提出了在线动态建模的模糊神经网络方法.当新增样本进入训练集之后,根据新样本对模型的贡献大小,在已有模型的基础上进行动态修正,这样可以减少建模的计算时间.新方法实现了增加样本而矩阵阶数不增加,避免了矩阵求逆运算,理论上可以提高计算效率.实例表明动态模糊神经网络方法是可行的,可实现持久预报,具有较强的适应能力和较高的预报精度,可应用于在线实时变形预报及相关领域.     

无线传感器网络MAC层协议的对比研究

无线传感器网络是二十一世纪新兴的网络技术，它的出现使网络的发展进入一个新的阶段。针对无线传感器网络MAC层协议的研究一直是人们普遍关注的问题。总结了近年来的研究成果并针对TDMA，IEEE802．15．4，S—MAC，T—MAC几种典型的MAC层协议进行了对比分析，根据其各自的优点提出将来工作的方向和建议。     

人工神经网络技术在板料激光弯曲中的应用

基于人工神经网络基本理论,建立在板料激光弯曲中预测材料表面最高温度、弯曲角度的BP网络模型。借助于MATLAB仿真软件中的神经网络工具箱作为开发平台,将试验样本数据和经过试验验证的数值计算结果作为补充的样本数据用于BP网络的训练,利用训练好的BP网络对非线性的样本数据规律进行拟合,实现激光加工工艺参数的优化,为实际生产和加工提供有效的依据。     

RSFM网络及其在信号滤波中的应用

介绍了一种适用于模式识别的新型神经网络模型--局部有监督特征映射（Reglonal Supervised Feature Mapping,RSFM）网络,描述了该网络的拓扑结构和学习算法,研究了网络的基本性能,最后将其应用到了信号滤波中.理论研究和仿真实验表明,该网络结构简单、算法简洁,收敛速度快、识别精度高,适用于需要大样本训练、随机干扰严重的复杂模式的分类与识别.     

Validation of a Method of Determination of Apparent Diffusivity Versus Composition in Solids

A method is presented for computing the values of apparent diffusivity in solids with respect to the concentration of the diffusing substance (water or sodium chloride). This method does not require any assumption upon the mathematical relationship between diffusivity and concentration. It can be applied to experimental measurements of local concentration versus position within the solid (profiles) with relatively few measurements (circa 10) and a mathematical smoothing of the experimental data by using an artificial neural network model. The method was first validated on simulated data obtained by using a constant diffusivity value and on experimental profiles when the relation between diffusivity and concentration was given. It was then applied to original experimental moisture profiles obtained by putting gelatin gels with different initial moisture contents into contact for up to 14 days. The method was also successfully applied to five sets of experimental moisture and sodium chloride profiles taken from the literature and obtained from different food products. Apparent diffusivities calculated by our method were found in agreement with those obtained by authors using different numerical methods to compute the diffusivity values.     

Estimation of fouling in a plate heat exchanger through the application of neural networks

Pasteurization is an important, if not the most important, process step in the packaging of milk. It is subject to alterations stemming from the variation in the temperature, pH and raw milk quality. The variability may manifest itself in changes in the formation of the deposit (fouling) in the pasteurization unit, such that there is a need for tools, both instrumentation and computational, to help in monitoring the process and keeping it on the desired course. In this paper we describe a practical procedure based on artificial neural networks (ANN) that allows prediction of the deposit thickness, the overall heat transfer coefficient and the critical time (the time that the unit has to be stopped for cleaning) for reducing the impact of fouling on such processes. The procedure determines when the cleaning operation is required once the system is under critical conditions of operations. A combination of fundamental studies and plant measurements were used for study of the operating conditions and thus evaluation of the trades‐offs between operating conditions and longer operating life span. The results are encouraging, enough to validate current operating industrial techniques. Copyright © 2005 Society of Chemical Industry     

多属性神经网络地震反演在NB油田水平井钻探中的应用

NB油田位于渤海海域,为新近系河流相稠油油田,储层横向分布不稳定,砂体厚度薄、连通性较差,油水关系复杂,开发设计部署了大量水平井。选择神经网络反演方法,建立地震属性与储层参数的非线性关系,进而根据其关系反演得到储层参数数据体,利用该数据体沿层切片提取储层预测信息,研究储层发育规律,指导该油田水平井的部署和钻探,取得了较好的效果,降低了钻探风险。用神经网络地震反演方法进行储层预测研究,指导水平井钻探,在渤海海域尚属首次。     

降雨空间分布模式识别

以广东省内186个站点的年降雨量分布为基础，把模式识别的聚类分析理论方法引入降雨空间特征分类研究中，进行降雨特征空间分布模式识别，以预测无雨量站点的降雨模式，从而分析水资源的空间分布模式，以便制订有效的水资源利用方案。结果表明，广东省年降雨量在空间上的分布可划分为6类模式；同时基于BP人工神经网络算法，建立了以高程、气温、蒸发量为主要参数的可判别和预测无雨量测站区域的降雨空间分布模式所属类别的模型，经过模型的学习和验证，效果较好。