基于径向基函数网络的加筋挡墙高度预测模型

提出了一种基于人工神经网络（ANN）技术的加筋挡墙临界高度预测方法，通过30组挡墙离心模型试验数据以及组足尺试验数据样本的训练与学习，建立了可用于加筋挡墙高度预测的径向基函数网络（RBFN）模型，采用4组挡墙离心模型试验数据和1组足尺试验数据，共5组样本作为检验样本对网络预测能力进行检验，结果表明网络的学习是成功的，同时网络能较好地适应本特定问题，推广能力较好。

Artificial Neural Network-Based Model for GRW Design Height Forecasting

This paper presents an artificial neural network-based approach to predicting the design height of GRW. A radial basis function neural network (RBFN) for forecasting the design height of GRW is trained using 31 series of centrifuge model test data. Checked by some full scale test data and case history measured values, the network is proved to be working successfully and provides satisfactory predictions for the design height, implying that the RBF is applicable for predicting design height of the reinforced soil walls.