摘要
水是导致残坡积土边坡滑坡的最主要原因,因此研究水对残坡积土力学性质的影响具有重要的理论和工程实际意义。本文在普通三轴仪上进行非饱和残坡积土的强度试验,并基于试验结果建立了非饱和残坡积土强度随含水量变化的改进BP神经网络预测模型。模型计算结果与试验结果对比分析表明,该神经网络预测模型具有较高的拟和精度和良好的泛化能力,能较好地预测试验含水量范围内任意含水量下对应的非饱和残坡积土应力-应变关系,从而能够弥补室内试验由于设计方案等自身缺陷引起的不足。研究结果可为工程应用提供参考。
A study of the mechanical properties of an unsaturated residual slope soil is of the engineering significance.General laboratory triaxial tests are carried out to obtain the stress-strain relationship between the unsaturated residual slope soil and the changes in water content.Improved BP neural network prediction model is established based on test data.The results from comparing predicted values and measured values show that this network prediction model has good fitting precision and good generalization ability.The method can better predict the unsaturated residual slope soil strength under any corresponding water content.The results can also provide a reference for engineering applications.
出处
《水文地质工程地质》
CAS
CSCD
北大核心
2011年第2期79-83,101,共6页
Hydrogeology & Engineering Geology
基金
国家自然科学基金资助项目(50878082)
交通部西部交通科技项目(200631880237)
湖南省自然科学基金重点项目(09JJ3104)
关键词
非饱和残坡积土
吸力
含水量
三轴试验
BP神经网络
unsaturated residual slope soil
suction pressure
water content
triaxial test
BP neural network
