PREDICTING SETTLEMENT OF SHALLOW FOUNDATIONS USING NEURAL NETWORKS
PREDICTING SETTLEMENT OF SHALLOW FOUNDATIONS USING NEURAL NETWORKS
复制标题
DOI：
10.1061/(asce)1090-0241(2002)128:9(785
复制
发表时间：
2002-09
影响因子：
3.9
通讯作者：
M. Shahin;H. Maier;M. Jaksa
中科院分区：
文献类型：
--
作者：
M. Shahin;H. Maier;M. Jaksa
多年来，人们提出了许多方法来预测无粘性土上浅基础的沉降。然而，尚未制定出具有所需准确度和一致性的预测方法。由于沉降而不是承载力通常控制着基础设计，因此沉降的准确预测至关重要。在本文中，人工神经网络（ANN）被用来试图获得更准确的沉降预测。一个大的数据库的实际测量沉降是用来开发和验证的神经网络模型。通过利用人工神经网络发现的预测沉降与三个最常用的传统方法预测的值进行了比较。结果表明，人工神经网络是一种有用的技术，用于预测无粘性土上的浅基础的沉降，因为他们优于传统的方法。
Over the years, many methods have been developed to predict the settlement of shallow foundations on cohesionless soils. However, methods for making such predictions with the required degree of accuracy and consistency have not yet been developed. Accurate prediction of settlement is essential since settlement, rather than bearing capacity, generally controls foundation design. In this paper, artificial neural networks (ANNs) are used in an attempt to obtain more accurate settlement prediction. A large database of actual measured settlements is used to develop and verify the ANN model. The predicted settlements found by utilizing ANNs are compared with the values predicted by three of the most commonly used traditional methods. The results indicate that ANNs are a useful technique for predicting the settlement of shallow foundations on cohesionless soils, as they outperform the traditional methods.