单层钢筋混凝土柱工业厂房震害非线性预测模型及应用.pdfVIP

学兔兔 2011年第 11期(总第 265期 ) 混 凝 土 实 用 技 术 Number 11 in 2011(TotalNo．265) Concrete PRACTICAL TECHN0L0GY doi：10．3969~．issn．1002-3550．201 1．1 1．043 单层钢筋混凝土柱工业厂房震害非线性 预测模型及应用 何慧荣 (鹤壁职业技术学院 建筑工程学院，河南 鹤壁 458030) 摘 要：将RBF人工神经网络理论应用于等高单层钢筋混凝土柱工业厂房的震害预测。在分析震害特点的基础上，将震害影响因子分为精 确性和规律性两大类，提出以地震反应指标、天窗类型、支撑情况、建筑材料作为主要的影响指标。然后将震害等级作为输出结果，构造了 震害预测的非线性预测模型。通过对52个实际震害实例的检验，网络的准确率高，可见该模型是有效可靠的。 关键词：工业厂房；震害预测；RBF人工神经网络；非线性 ． 中图分类号：TU528．01 文献标志码：A 文章编号：1002—3550(2011)l1-0135—03 Seismic damage prediction nonlinear model for single-stow reinforced concrete industrial building HEHui-rong (Vocational and Technical School ofArchitec~ne Engineering ofHenan Hebi City，HeN 458030，China) Abstract： The RBF artificial neural network is applied to predict seismic damage of single—story reinforced concrete industrial building．Based on the analysis of characteristics of seismic damage，it is found that earthquake response index，type of sky light，bracing system and building material are the ma in factors affecting seismic damage．The four factors can be classified into two types：precise factors and regular factors．Th e corresponding spans of factors ate suggested and applied to engineering examples．Thus the RBF artificial neural network is developed．with factors affecting seismic dam age as input and seismic dam age grade as output．It was verified by 52 engineering examples．It is concluded that the RBF artificial neural network developed in this paper is applicable to predictseismic dam ag