基于神经网络的钢筋混凝土异型节点抗裂能力预测  

Prediction on anti-crack capacity of RC abnormal joints based on neural networks

作　　者：张淑云[1] 白建方[1] 白国良[1] 

机构地区：[1]西安建筑科技大学土木工程学院

出　　处：《世界地震工程》2005年第4期54-59,共6页World Earthquake Engineering

基　　金：国家电力公司"十五"重点项目(60-Y2002-03-T03);陕西省教育厅专项基金项目(03JK142)

摘　　要：利用神经网络方法研究了低周反复荷载作用下钢筋混凝土异型节点抗裂承载力与各主要影响因素之间复杂的非线性关系,建立了承载力的BP神经网络预测模型,预测结果与试验结果吻合较好。分析结果表明神经网络计算是钢筋混凝土构件力学性能研究中的一种很有潜力的新方法。Neural networks technology is applied to build the complex non-linear relationship between the anti-crack capacities of reinforced concrete abnormal joints under low reversed cyclic loading and the main factors. BP（ back propagation） neural networks model is built to predict the strength of the reinforced concrete abnormal joints. Satisfactory results are achieved by the neural networks model. Therefore, it is proven that the neurocomputing is a practical and promising tool for the analysis on mechanical properties of the reinforced concrete member.

关 键 词：神经网络 钢筋混凝土异型节点 抗裂承载力 

分 类 号：P315[天文地球—地震学]