摘要
通过水泥搅拌土室内试验,研究了水泥搅拌土的各种物理力学特性,根据试验数据建立了水泥搅拌土无侧限抗压强度、灰土比与养护条件、养护时间、纵波波速、横波波速的神经网络模型,然后对水泥土的强度和灰土比进行计算和预测。研究结果表明,神经网络模型不仅可以综合考虑各种因素的影响,而且具有较高的预测精度,是一种很好的无损检测信息处理工具,在岩土工程无损检测中具有广阔的应用前景。
The authors conducted laboratory tests on the characteristics of soilcement mixing and established a BP neural network model of computation of compressive strength and the relative factors, such as cementsoil ratio,curing condition and duration, compression wave speed and shear wave speed. Evaluation and forecasting of the compressive strength and cement content was made with the model.The neural network model covers various effective factors and the results is accurate in forecasting.The method will have a broad prospect of application in the geotechnical engineering harmless survey.
出处
《水利学报》
EI
CSCD
北大核心
2003年第5期84-87,共4页
Journal of Hydraulic Engineering
关键词
神经网络
水泥搅拌土
岩土工程无损检测
抗压强度
neural-network
soil-cement
geotechnical harmless survey
compressive-strength
