基于深度学习的黄土干湿循环损伤分析

宋佳, 白杨, 王小林

长江科学院院报 ›› 2023, Vol. 40 ›› Issue (2) : 87-94.

PDF(7170 KB)
PDF(7170 KB)
长江科学院院报 ›› 2023, Vol. 40 ›› Issue (2) : 87-94. DOI: 10.11988/ckyyb.20210908
岩土工程

基于深度学习的黄土干湿循环损伤分析

  • 宋佳, 白杨, 王小林
作者信息 +

Damage Analysis of Loess under Dry-Wet Cycles Based on Deep Learning

  • SONG Jia, BAI Yang, WANG Xiao-lin
Author information +
文章历史 +

摘要

为研究干湿循环条件下黄土的微观结构变化规律,以西安市黄土为例,先基于灰度共生矩阵提取黄土灰度图像纹理特征,计算土壤的微观裂纹和孔隙面积占比,然后通过深度学习时序回归预测模型建立起灰度纹理特征和微观裂纹与孔隙面积占比之间的联系,计算土壤干湿循环损伤因子判断土壤干湿循环损伤程度。研究表明:在2次干湿循环内,土壤团粒边缘结构破坏,微观裂纹和孔隙急剧增加;在5次干湿循环内,土壤结构纹理化走向逐渐明显,趋近于平行水分迁移方向;经历4次干湿循环后,土壤的干湿循环损伤破坏比例达到93.10%;经过6次干湿循环后,土壤的干湿循环损伤已不再增大,即土壤微观结构纹理化已经趋于稳定。

Abstract

The aim of this study is to investigate the changes in the microstructure of loess under dry-wet cycles.The gray-scale image texture features of Xi’an loess were extracted based on the gray-level co-occurrence matrix,and the area of cracks and pores in the loess was calculated based on the percentage of the area of cracks and pores.The relationship between the gray-scale texture characteristics and the proportion of cracks and pore areas was established through the deep learning time-series regression prediction model,and the damage degree of loess under dry-wet cycles was determined by calculating the damage factor.Our study revealed that within two dry-wet cycles,the edge structure of soil aggregates was destroyed,and cracks and pores increased sharply;within five dry-wet cycles,the texturing trend of soil structure became more obvious,approaching the direction of parallel water migration;after four times of dry-wet cycle,the damage ratio of loess under dry-wet cycle reached 93.10%;after six dry-wet cycles,the damage no longer increased,which means that the microstructure texturing of the loess stabilized.

关键词

黄土 / 干湿循环 / 微观结构 / 灰度共生矩阵 / 深度学习

Key words

loess / dry-wet cycle / microstructure / gray-level co-occurrence matrix / deep learning

引用本文

导出引用
宋佳, 白杨, 王小林. 基于深度学习的黄土干湿循环损伤分析[J]. 长江科学院院报. 2023, 40(2): 87-94 https://doi.org/10.11988/ckyyb.20210908
SONG Jia, BAI Yang, WANG Xiao-lin. Damage Analysis of Loess under Dry-Wet Cycles Based on Deep Learning[J]. Journal of Changjiang River Scientific Research Institute. 2023, 40(2): 87-94 https://doi.org/10.11988/ckyyb.20210908
中图分类号: TU431   

参考文献

[1] 洪 勃,李喜安,王 力,等.毛细管渗流模型在黄土渗透性中的应用探讨[J].工程地质学报,2018,26(5):1250-1256.
[2] 康尘云,王少凯,潘登丽,等.黄土垂直和构造节理的几何差异性及拓扑学研究[J].长江科学院院报,2020,37(9):115-121,127.
[3] 穆青翼,党影杰,董 琪,等.原状和压实黄土持水特性及湿陷性对比试验研究[J].岩土工程学报,2019,41(8):1496-1504.
[4] 赖金星,邱军领,牛方园,等.浅埋偏压黄土隧道塌方处治及效果分析[J].现代隧道技术,2017,54(2):194-201.
[5] 王 刚,孙 萍,吴礼舟,等.降雨诱发浅表层黄土滑坡机理实验研究[J].工程地质学报,2017,25(5):1252-1263.
[6] 胡玉定,姚继涛,韩晓雷,等.黄土地区某事故建筑物不均匀沉降机理分析[J].西安建筑科技大学学报(自然科学版),2012,44(3):345-350.
[7] 王 飞,李国玉,穆彦虎,等.干湿循环条件下压实黄土变形特性试验研究[J].岩土力学,2016,37(8):2306-2312,2320.
[8] LIU Guan-shi,TOLL D G,KONG Ling-wei,et al.Matric Suction and Volume Characteristics of Compacted Clay Soil under Drying and Wetting Cycles[J].Geotechnical Testing Journal,2019,43(2):464-479.
[9] CHEN Rui,XU Tao,LEI Wei-dong,et al.Impact of Multiple Drying-Wetting Cycles on Shear Behaviour of an Unsaturated Compacted Clay[J].Environmental Earth Sciences,2018,77:683.
[10] CHU C F,ZHAN M H,FENG Q,et al.Effect of Drying-Wetting Cycles on Engineering Properties of Expansive Soils Modified by Industrial Wastes[J].Advances in Materials Science and Engineering,2020,doi:10.1155/2020/5602163.
[11] LIU W H,TANG X W,YANG Q,et al.Influence of Drying/Wetting Cycles on the Mechanical Cyclic Behaviours of Silty Clay[J].European Journal of Environmental and Civil Engineering,2015,19(7):867-883.
[12] 叶万军,吴云涛,杨更社,等.干湿循环作用下古土壤细微观结构及宏观力学性能变化规律研究[J].岩石力学与工程学报,2019,38(10):2126-2137.
[13] 赵贵涛,韩 仲,邹维列,等.干湿、冻融循环对膨胀土土-水及收缩特征的影响[J].岩土工程学报,2021,43(6):1139-1146.
[14] 胡长明,袁一力,王雪艳,等.干湿循环作用下压实黄土强度劣化模型试验研究[J].岩石力学与工程学报,2018,37(12):2804-2818.
[15] 万 勇,薛 强,吴 彦,等.干湿循环作用下压实黏土力学特性与微观机制研究[J].岩土力学,2015,36(10):2815-2824.
[16] 袁志辉,倪万魁,唐 春,等.干湿循环下黄土强度衰减与结构强度试验研究[J].岩土力学,2017,38(7):1894-1902,1942.
[17] 朱 琳,党发宁,丁卫华,等.基于CT技术和灰度共生矩阵理论研究不同荷载作用下混凝土的细观损伤演化过程[J].土木工程学报,2020,53(8):97-107.
[18] 代杰杰,宋 辉,盛戈皞,等.采用LSTM网络的电力变压器运行状态预测方法研究[J].高电压技术,2018,44(4):1099-1106.

PDF(7170 KB)

Accesses

Citation

Detail

段落导航
相关文章

/