文章根据公路软基沉降的基本特征,提出了一种基于人工神经网络(ANN)技术的软土地基沉降预测新方法。通过对由实测资料形成的数据样本的训练学习,建立了可用于预测软土地基沉降量的Elman模型。实例检验证明,该网络的学习是成功的,具有一定的可靠性和实用性。 According to the basic characteristics of settlement of highway soft foundation, a new method of settlement prediction of soft ground based on artificial neural network (ANN) is proposed. Through the training and learning of the data samples formed by the measured data, an Elman model which can be used to predict the settlement of soft ground is established. The example test proves that the learning of this network is successful, with certain reliability and practicability.