摘要
以沉降控制复合桩基础的沉降为研究对象,介绍了有限元和神经网络法的数值分析方法,并运用这两种方法对桩的沉降量进行了预测,对比了它们的结果,分析其产生差异的原因,结果表明:两种方法的沉降预测数据与实测数据误差均小于10%,说明预测精度较高,可以在节省资源的情况下获得较理想的预测结果.
The settlement of piled foundation is the subject of research. The finite element method and neural network method are introduced and both of them are used for settlement prediction. The results are compared and they indicate that prediction data is close to the measured data, both methods are proved reasonable and feasible.
出处
《南华大学学报（自然科学版）》
2009年第2期107-110,共4页
Journal of University of South China：Science and Technology
基金
国家自然科学基金资助项目(50490270)
关键词
桩基础
有限单元法
神经网络
沉降预测
piled foundation
finite element method
neural network method
settlement prediction
