基于人工神经网络的软土沉降预测分析

依据人工神经网络较强的非线性映射能力和学习能力，提出基于人工神经网络的软土地基最终沉降量的预测新方法。本方法利用实测资料直接建模，可避免传统方法计算过程中各种人为因素的干扰，所建立的模型预测精度高、简便易行，因而具有广泛的工程价值。

Settlement Forecast of A Typical Soft Soil Based on Artificial Neural Network

A new method for evaluating final settlement of soft ground for expressway is presented taking advantage of the strong nonlinear mapping and learning ability of artificial neural networks. Model is established directly on the basis of measured data through this method. It can avoid the mistakes due to factitiousness in traditional methods. It is proved that the prediction model is accurate and easy to operate, so the method has widely practical engineering value.