AUTHOR=Zhang Hongyang , Li Xuan , Liu Jianlong , Han Pengju , Yang Yige , Ding Zelin , Han Liwei , Zhang Xianqi , Wang Shunsheng TITLE=Study on wetting deformation model of coarse-grained materials based on P-Z model and BP neural network JOURNAL=Frontiers in Earth Science VOLUME=11 YEAR=2023 URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2023.1187032 DOI=10.3389/feart.2023.1187032 ISSN=2296-6463 ABSTRACT=

The wetting deformation of coarse-grained materials can seriously affect the safety of earth and rock dams during initial water storage. The wetting model formulas are expressed in various forms and have complex parameters. Only a small amount of test data is fitted by mathematical statistics, and the universality of the obtained wetting model is unknown. Duncan-Chang E-B constitutive model cannot accurately reflect the wetting deformation characteristics of coarse-grained materials. Through the double-line wetting test of coarse-grained materials, the wetting model proposed by predecessors was verified and analyzed. Based on the indoor wetting test data, the parameters of each wetting model were fitted to analyze the accuracy of each wetting model in describing the wetting deformation characteristics. According to the P-Z model in the elastic-plastic theory and the wetting model formula, the P-Z wetting model is established, and the BP artificial neural network is introduced to establish the artificial neural network wetting deformation prediction model based on the P-Z model. The results show that the relationship between wetting axial strain and wetting stress level is best expressed by the exponential function. The relationship between wetting volumetric strain and wetting stress level is best described by Cheng’s linear function. The relative errors between the predicted and experimental values of the proposed neural network prediction model are all within 6%. The relationship between wetting axial strain and wetting stress level is exponential function, and the relationship between wetting volumetric strain and wetting stress level is linear function. The P-Z wetting model proposed in this research can better reflect the wetting deformation characteristics of coarse-grained materials under complex stress paths. The artificial neural network prediction model based on P-Z wetting model is more reliable and accurate, which can meet the prediction requirements of actual engineering for wetting deformation of coarse-grained materials.