Intelligent technology-based control of motion and vibration using MR dampers

Due to their intrinsically nonlinear characteristics, development of control strategies that are implementable and can fully utilize the capabilities of semiactive control devices is an important and challenging task. In this study, two control strategies are proposed for protecting buildings against dynamic hazards, such as severe earthquakes and strong winds, using one of the most promising semiactive control devices, the magnetorheological (MR) damper. The first control strategy is implemented by introducing an inverse neural network (NN) model of the MR damper. These NN models provide direct estimation of the voltage that is required to produce a target control force calculated from some optimal control algorithms. The major objective of this research is to provide an effective means for implementation of the MR damper with existing control algorithms. The second control strategy involves the design of a fuzzy controller and an adaptation law. The control objective is to minimize the difference between some desirable responses and the response of the combined system by adaptively adjusting the MR damper. The use of the adaptation law eliminates the need to acquire characteristics of the combined system in advance. Because the control strategy based on the combination of the fuzzy controller and the adaptation law doesn’t require a prior knowledge of the combined building-damper system, this approach provides a robust control strategy that can be used to protect nonlinear or uncertain structures subjected to random loads. Supported by: Hong Kong Research Grant Council Competitive Earmarked Research Grant HKUST 6218 / 99E and by the National Science Foundation under grant CMS 99-00234.     

广义回归神经网络预测加筋土支挡结构高度

土工合成材料加筋支挡结构（Geosythetics-Reinforced Retaining Wall, 简称GRW）设计方法主要是建立在似粘聚力理论基础之上的半经验设计法。由于土性及加筋机理的复杂性，常常要对它们进行人为假定，导致计算结果差强人意。神经网络方法与传统方法的不同之处在于不需要主观假定，而是模拟人脑思维，通过数据样本的学习来获得预测结果。引入神经网络技术来预测加筋土支挡结构的设计高度是一种新尝试。由于本问题具有样本容量非常有限、影响因素复杂多样的特点。因此，采用适用于稀土样本数据的广义回归网络（General Regression Neural Network)来预测加筋土支挡结构设计高度。基于MATLAB神经网络工具箱及文献[1]的挡墙离心模型试验结果，建立了一个可用于加筋支挡结构设计高度预测的GRNN网络。通过对足尺试验，实际工程及模型试验结果的检验，表明网络的学习是成功的，具有一定指导意义。     

基于GIS的细胞自动机模型与人地关系的复杂性探讨

探讨人地非线性关系可以揭示地理系统空间复杂性的许多简单本质 ,具有重要的理论意义和实践价值。以地理信息系统 (GIS)为技术支持 ,建立以细胞自动机 (CA)为核心的综合集成模型 ,将成为人地关系复杂性研究的主要方向。建议在CA GIS集成技术的基础上 ,一方面引入人工神经网络、进化算法、多重智能体系 (MAS)以及后现代数学分析方法 ,另一方面面向具体研究对象开发包括自然、人文地理要素在内的集成区域动力学模型 ,据此发展智能化综合集成模型体系 ,形成人地关系复杂性的模拟研究实验室。本文提出了开发智能化CA GIS模拟方法的初步设想。     

河南平原绿化发展研究

文章根据河南省近期（1998年）森林资源清查结构和1993－2000年年度平原绿化复查情况，分析了河南平原绿化的发展现状和存在问题，提出河南平原绿化应以建立持续，高效的平原林业生态体系为目标，坚持生态，社会，经济效益相统一，高标准建设农田林网，农林间作，城镇村庄和通道绿化，合理调整林种，树种结构，积极发展速生丰产用材林和名特优新经济林。并对河南平原绿化建设布局，内容及实现手段和策略进行了讨论。     

Neural Network-Based Estimation of Principal Metal Contents in the Hokuroku District,Northern Japan,for Exploring Kuroko-Type Deposits

The Hokuroku district, extending over 40 × 40 km² in northern Japan, is known to be dominated by kuroko-type massive sulfide deposits that have a genetic relation to submarine volcanic activity. The deposits are hosted in a specific stratigraphic zone of Miocene volcanic rocks. Because kuroko-type deposits are under exploration in several countries, it is important to integrate the geologic and geochemical data that have been accumulated in the Hokuroku district to characterize the distribution of deposits and produce a map of mineral potential. Thus, we collected data on multiple chemical components from 1917 rock cores at 143 drillhole sites and concentrated on components with relatively large amounts of data, which are SiO₂, Al₂O₃, and Fe₂O₃ as major elements and Cu, Pb, and Zn as trace elements. Although frequencies of these data can be approximated by normal or lognormal distributions, spatial correlation structures cannot be extracted from the semivariograms of each component nor from the cross-semivariograms between two components of the major or minor elements. To handle such complexity, a spatial method of modeling content distribution, SLANS, is developed by applying a feedforward neural network. The principle of SLANS is to train a network repeatedly to recognize the relation between the data value and the location and lithology of a sample point. One-hundred outputs for each element are obtained by changing the numbers of neurons in a middle layer from 1 to 10 and sample data used for training from 3 to 12, and finally one output is selected based on the estimation precision of the network which is restricted near the target point. After constructing a geologic distribution model from the geological column classified into 25 rock codes, three-dimensional distributions of Cu, Pb, and Zn contents are estimated over the study area. The content models are considered to be valid because high-content zones are located on the known mine sites and the margins of ancient volcanoes or calderas. Some zones are distributed along strikes of major deep-seated fractures in the district.     

Evaluation of approaches for forest cover estimation in the Pacific Northwest, USA, using remote sensing

The transformation of land cover, in particular coniferous forest, constitutes one of the most notable agents of regional-to-global-scale environmental change. Remote sensing provides an excellent opportunity for providing forest cover information at appropriate spatial and temporal scales. The optimal exploitation of remote sensing relies on the link between known forest cover and the remotely sensed dataset. This paper explores the accuracy of three methods – vegetation indices, regression analysis and neural networks – for estimating coniferous forest cover across the United States Pacific Northwest. All methods achieved a similar accuracy of forest cover estimation. However, in view of the benefits and limitations of each, the neural network approach is recommended for future consideration.     

长江口及其邻近海域富营养化水平评价

根据2004年4个季度2、5、8、11月的调查资料,选择化学耗氧量、溶解氧、活性磷酸盐、溶解无机氮和叶绿素a作为评价因子,利用人工神经网络模型对长江口及其邻近海域的营养水平进行评价。结果表明,富营养化区域主要集中在口门附近,富营养化程度由口门向东和东北方向递减。富营养化范围几乎均分布在盐度小于20的一侧,并随着长江冲淡水的变化而发生季节性的变化。5月和8月的富营养化比较严重,且都有转向东北的趋势,可能与5月进入丰水期长江冲淡水转向有关。断面分布表明,各个季度月由河口向东,富营养化评价等级由高到低,垂直方向则呈现复杂的变化。分析表明影响富营养化的主要评价指标是溶解无机氮。     

基于神经网络的GPS周跳探测的新方法

为了用GPS获得高精度的定位结果,周跳必须在数据处理过程中被检测和修复。通过对周跳产生原因和特点的分析,提出神经网络方法,并与传统方法进行比较。用神经网络建立模型对周跳进行预测。通过对比预测值的不同来确定周跳的大小,从而实现周跳的修复。此外,还利用实测的相位数据,验证方法的可行性与有效性。     

神经网络BP算法中的误差及其改进方法研究

人工神经网络(Artificial Neural Networks)是模仿人脑结构和功能的一种信息处理系统。该方法在处理非线性问题上具有其独特的优越性,在工程应用中越来越被人们所关注。与此同时,神经网络计算的精度和收敛速度也成为人们普遍关心的问题。本文试验发现BP算法在归一化过程中存在最值误差和区间变形误差,在此基础上,本文对常规BP网络进行了改进,提高了BP网络的预测精度。     

动态神经网络在变形预报中的应用

静态神经网络模型用于在线时间序列的预报时具有局限性,即网络的泛化能力有限,且模型不能不断地适应新增样本的变化.如果每增加一个样本对神经网络重新训练,需要大量的计算时间.针对该问题,提出了动态神经网络预报模型.在获得新增样本数据之后,通过比较预报值与实际值之差的绝对值是否大于ε敏感因子,决定模型是否需要修正.为了降低模型修正的计算时间,提出了在线动态修正方法,实现了增加样本而矩阵阶数不增加,且避免了矩阵求逆运算,理论上可以提高计算效率.通过实例表明,该方法在计算时间和预报精度两个方面都具有一定优势,可应用于在线实时变形预报及相关领域.