Research on the prediction of frost heave and thaw settlement characteristics of modified soil based on wavelet neural network
ZHOU Shuqing
LIU Linlin
QI Yanqiu
WANG Zongjin
FAN Hua
LIN Jian
Abstract：In order to further explore the evolution law of freeze-thaw settlement coefficient of soil con-structed by in-situ modification and freezing method combination,experiments were conducted on the freeze-thaw settlement characteristics of modified soil with different fly ash blending ratios,and a pre-diction model for freeze-thaw settlement characteristics was established using wavelet neural network.The experimental results show that:(1)The frost heave amount is significantly affected by the ash ra-tio and cold end temperature.The frost heave amount at each cold end temperature decreases with the increase of ash ratio,and the frost heave suppression effect is most significant at an ash ratio of 9％.The frost heave amount is negatively correlated with the ash ratio;The lower the cold end tempera-ture of modified silty clay with the same ash content ratio,the greater the frost heave,and the frost heave is inversely proportional to the cold end temperature.(2)The thaw settlement coefficient de-creases with increasing ash ratio under the same cold end temperature conditions,and there is a nega-tive correlation between the thaw settlement coefficient and the ash ratio.(3)The fuzzy random pre-diction model for frost heave and thaw settlement of modified soil established has good fitting effect,and can be used to predict the frost heave and thaw settlement parameters of modified soil construction by freezing method.
Keywords：modified soilfly ashfrost heave and thaw settlementwavelet neural network
Publication Date：2025-06-15
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：10( 50-59 )