人工神经网络在钢管砼增强高强砼柱抗剪承载力预报中的应用

APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO THE PREDICTION OF ULTIMATE SHEAR STRENGTH OF HIGH STRENGTH CONCRETE COLUMNS REINFORCED WITH CONCRETE FILLED STEEL TUBE

探索应用人工神经网络对截面核心用钢管砼增强的高强砼柱的抗剪承载力进行评估的可能性,利用该柱剪切性能试验的结果,其中的24组数据作为学习样本,另外的6组数据则作为测试样本,训练了一个三层BP网络,进行了柱抗剪承载力的预报,结果和试验值吻合良好。进而利用该网络模型分析了不同参数对柱抗剪承载力的影响,表明采用钢管混凝土作核心对增强高强混凝土柱的抗剪承载力有很好的效果,分析还表明随着体积配箍率的增大,柱的抗剪承载力也相应地得到提高。

This paper investigates the feasibility of using neural networks to evaluate the ultimate shear strength of high strength concrete columns reinforced with concrete filled steel tube in the core of section. A three-layer back-propagation network is trained using the experimental data of the columns in shearing test, among which 24 groups are used for training sample while the remaining 6 groups are used for testing sample, to predict the ultimate shear strength of the columns. The results agree well with the test results. In the further analysis about the influence of various parameters on the ultimate shear strength, it is found that it is significant to put concrete filled steel tube in the core of section for the high strength concrete columns in improving its ultimate shear strength. And it is shown that with the increase of volume stirrup ratio, the ultimate shear strength is also improved accordingly.