机构地区: 湘潭工学院
出 处: 《地下空间》 2003年第1期33-35,44,共4页
摘 要: 利用BP神经网络较强的高次非线性映射能力和学习功能 ,建立了基于人工神经网络的单桩极限承载力与沉降量的预测模型。该模型依据现场实测资料建模 ,避免了计算过程中各种人为因素的影响。通过静载荷试验成果的学习与预测检验 ,证明其预测精度良好、适用性强 。 By use of the strong nonlinear mapping and learning ability of the back propagation neural network, a new model based on this neural network to predict the ultimate bearing capacity and settlement of single pile has been presented in this paper. Since the model is directly based on in situ test data, the errors due to artificially imposed factors can be avoided and a good predicting accuracy can be obtained, so it can be widely used in practice.