人工神经网络在钢管核心柱设计参数预报中应用

探索运用人工神经网络对截面核心用钢管混凝土增强的高强混凝土柱的力学性能进行评估的可能性，利用该柱抗震性能试验的结果，训练一个三层BP网络，进行了柱抗震延性的预报，预报值和试验值吻合良好，进而利用该网络模型2分析了各种参数对柱延性的影响，表明采用钢管混凝土做核心对改善高强混凝土柱的抗震性能有很好的效果。

Application of artificial neural networks to prediction of design parameters for high strength concrete columns reinforced with concrete filled steel tube

The feasibility of applying neural networks to evaluation of the performance of high strength concrete columns reinforced with concrete filled steel tube in the core of section was investigated. A three layer back propagation network is trained using the earthquake resistant behavior experimental data of the columns to predict the ductility of the columns. The predicted results agree well with the test results. In the further analysis about the influence of various parameters on the ductility, the results show that it is significant to put concrete filled steel tube in the core of section for the high strength concrete columns in improving its earthquake resistant performance.