PREDICTION MODEL OF LOESS COLLAPSIBILITY IN GONGLIU COUNTY OF ILI RIVER VALLEY
-
摘要: 由于湿陷性黄土地区地质灾害防治工程地基处理不当,使得黄土地区的非均匀湿陷性对地质灾害的防治工程造成一定威胁。因此,选取合适的参数建立黄土湿陷性预测模型能为黄土地区地质灾害防治工程的基础设计提供理论依据。本文以伊犁河谷地区巩留县黄土为研究对象,在前期收集该地区69组土工试验参数的基础上,借助数理统计的方法对该地区黄土湿陷系数和土性指标参数的相关性进行了分析,并采用多元线性回归理论和神经网络理论建立了该地区黄土湿陷性评价的预测模型。研究结果表明:研究区土体微观结构多表现为絮凝状结构,以支架接触方式为主,矿物颗粒多呈现薄片状,孔隙结构多呈现孔状或不规则状;研究区黄土湿陷系数与含水率、密度、干密度、饱和度、孔隙比、孔隙率相关系数在0.645~0.857之间,具有强或极强的相关性;通过对研究区建立的黄土湿陷性多元线性回归模型和RBF神经网络模型的综合对比,RBF神经网络模型更具有适用性、可信性和准确性,其准确性达到94.20%。因此,建立的RBF神经网络模型精度能够满足实际工程的需要,为解决该地区黄土湿陷性评价问题提供了新的思路。Abstract: Due to the improper foundation treatment of geological disaster prevention and control project in collapsible loess area,the non-uniform collapsibility of loess area poses a certain threat to the prevention and control project of geological disaster. Therefore,selecting appropriate parameters to establish a loess collapsibility prediction model can provide a theoretical basis for the basic design of geological disaster prevention and control projects in loess areas. In this paper,the loess of Gongliu County in the Ili River Valley is taken as the research object. On the basis of collecting a large number of geotechnical test parameters in the area in the early stage,the correlation between the loess collapsibility coefficient and the soil index parameters in the area is analyzed by means of mathematical statistics. The prediction model of loess collapsibility evaluation in the area is established using multiple linear regression theory and neural network theory. The results show that the microstructure of the soil in the study area is the mostly flocculated structure,mainly in the way of support contact. The mineral particles are mostly flaky,and the pore structure is mostly porous or irregular. The material composition is mainly sandstone,albite,calcite and dolomite. The correlation coefficient between loess collapsibility coefficient and these of water content,density,dry density,saturation,void ratio and porosity in the study area is between 0.645 and 0.857,which has strong or extremely strong correlation. Through the comprehensive comparison of the loess collapsibility multiple linear regression model and the RBF neural network model established in the study area,the RBF neural network model is more applicable,credible and accurate,and its accuracy reaches 94.20%. Therefore,the accuracy of the established RBF neural network model can meet the needs of practical engineering,which provides a new idea for solving the problem of collapsibility evaluation of loess in this area.
-
Key words:
- Loess collapsibility /
- Soil indicators /
- Correlation /
- Prediction model /
- Ili River Valley
-
表 1 研究区湿陷性黄土土性分析表
Table 1. Analysis table of collapsible loess soil in the study area
指标 平均值 标准差 变异系数 取样深度h/m 3.03 3.26 1.08 含水量ω/% 13.32 6.09 0.46 密度ρ/g·cm-3 1.55 0.24 0.16 干密度ρd/g·cm-3 1.36 0.16 0.12 孔隙比e 1.01 0.23 0.23 饱和度Sr/% 40.25 25.93 0.64 孔隙率n/% 49.45 6.06 0.12 液限ωL/% 25.47 2.07 0.08 塑限ωp/% 16.92 1.62 0.10 塑性指数Ip 8.54 1.05 0.12 液性指数IL -0.40 0.77 -1.91 压缩系数a/MPa-1 0.36 0.29 0.81 压缩模量Es/MPa 8.32 4.78 0.57 表 2 巩留县黄土湿陷系数与各土性参数之间相关性分析
Table 2. Correlation analysis between loess collapsibility and soil parameters in Gongliu County
相关性指标 回归方程 显著性值 相关系数 相关性 δs-ρ δs=-0.174ρ+0.328 0 -0.857 极强 δs-e δs=0.183e-0.126 0 0.849 极强 δs-n δs=0.007n-0.277 0 0.830 极强 δs-ρd δs=-0.251ρd+0.399 0 -0.829 极强 δs-Sr δs=-0.001Sr+0.116 0 -0.752 强 δs-ω δs=-0.005ω+0.128 0 -0.645 强 δs-IL δs=-0.037IL+0.043 0 -0.580 中等 δs-ωL δs=0.006ωL-0.095 0.019 0.251 弱 δs-ωP δs=0.006ωp-0.047 0.047 0.203 弱 δs-Es δs=-0.002Es+0.075 0.050 -0.200 无 δs-IP δs=0.009Ip-0.015 0.068 0.181 无 δs-a δs=0.029a+0.047 0.077 0.173 无 δs-h δs=-0.001 52h+0.064 32 0.293 -0.067 无 表 3 常量统计
Table 3. Constant statistics
模型 R R2 R2 标准估计的误差S 1 0.900 0.809 0.800 0.022 42 表 4 回归系数及检验
Table 4. Regression coefficient and test
模型 参数 非标准化系数 标准系数 t Sig B 标准误差 1 (常数) 1.863 1.663 1.121 0.02 含水率ω -0.002 0.006 -0.278 -0.374 0.00 密度ρ -0.835 0.609 -4.103 -1.373 0.01 饱和度Sr 0.004 0.001 2.083 3.483 0.00 孔隙率n -0.013 0.017 -1.590 -0.766 0.00 表 5 数据值处理摘要
Table 5. Data value processing summary
数据信息 样本数N/组 百分比 训练 35 50.7% 测试 30 43.5% 保留 4 5.8% 有效 69 100% 已排除 0 总计 69 -
Chen K, Zhang S, Liang C, et al. 2021. Study on correlations of physical and mechanical property indexes of the major layer in Urumqi city[J]. China Mining Magazine, 30 (4): 224-228. Chen Y G. 2011. Geographical mathematics method: basis and application[M]. Beijing: Science Press. Dong G Y, Nie Z M, Chen X, et al. 2022. Correlation analysis between loess collapsibility and physical-mechanical indexes: a case study of loess in Yili area of Xinjiang[J]. World Geology, 41 (4): 751-762. Editorial Office of Engineering Geological Handbook. 2018. Engineering Geological Handbook[M]. 5th ed. Beijing: China Architecture & Building Press. Garakani A A, Haeri S M, Khosravi A, et al. 2015. Hydro-mechanical behavior of undisturbed collapsible loessial soils under different stress state conditions[J]. Engineering Geology, 195 : 28-41. doi: 10.1016/j.enggeo.2015.05.026 Li D H, Wang Y. 2011. Settlement prediction model comparison under small deformation in collapsibleloess region[J]. Shanxi Construction, 37 (30): 146-148. Li J Q, Wang Z X, Hou X W, et al. 2020. Correlation analysis and prediction of collapsibility and physical properties of loess-like soils in southern Hebei province[J]. Geological Survey and Research, 43 (3): 259-264. Li X C, Sun D A, Xu Y F. 2019. Study on correlations of physical and mechanical property indexes of Yangzhou clays[J]. Chinese Journal of Engineering Geology, 27 (2): 333-340. Liu Z D. 1994. Analysis of factors affecting loess collapsibility coefficient[J]. Geotechnical Investigation & Surveying, (5): 6-11. Qian J G. 2015. Soil science and soil mechanics[M]. Beijing: China Communication Press. Qiu X P. 2020. Neural network and deep learning[M]. Beijing: Mechanical Industry Press. Ren W B, Liu Y L, Li J J, et al. 2022. Evaluation of loess collapsibility based on discrete binomial coefficient combination model[J]. Science Technology and Engineering, 22 (12): 4945-4953. Shao S J, Yang C M, Ma X T, et al. 2013. Correlation analysis of collapsible parameters and independent physical indices of loess[J]. Rock and Soil Mechanics, 34 (S2): 27-34. Shi B D, Liang Q G, Zhao T, et al. 2021. Relationship between collapsibility and physical properties of loess before and after disturbance[J]. China Earthquake Engineering Journal, 43 (4): 977-982, 988. Tang H, Zhang R S, Gao J Z. 2023. Correlation analysis between collapsibility and physical properties of loess in Yan'an New District[J]. Journal of Ground Improvement, 5 (1): 19-24. The National Standards Compilation Group of People's Republic of China. 2019. Standard for Soil Test Methods(GBT 50123-2019)[S]. Beijing: China Planning Press. Wang J Q, Lei S Y, Li X L, et al. 2013. Correlation of wet collapsibility coefficient and physical property parameters of loess[J]. Coal Geology & Exploration, 41 (3): 42-45, 50. Wang L Q, Shao S J, She F T. 2020. A new method for evaluating loess collapsibility and its application[J]. Engineering Geology, 264: 105376. doi: 10.1016/j.enggeo.2019.105376 Xi N, Mei G, Xu N X. 2019. Correlation study of rock physical and mechanical parameters based on statistics[J]. Journal of Engineering Geology, 27 (S1): 425-430. Xing J X. 2004. Analysis of factors affecting loess collapsibility[D]. Xi'an: Chang'an University. Xiong R Q, Liu L J, Liu G H, et al. 2023. Prediction of loess collapsibility based on PSO-SVM[J]. Building Technology Development, 50 (1): 61-63. Yang X H, Huang X F, Zhu Y P, et al. 2014. Experimental study on collapsibility evaluation and treatment depths of collapsible loess upon self weight with thick depth[J]. Chinese Journal of Rock Mechanics and Engineering, 33 (5): 1063-1074. Ye W. 2000. The mineral characteristics of loess and depositing environment in Yili Area, Xinjiang[J]. Arid Zone Research, 17 (4): 1-10. Yin G H, Wang L M, Yuan Z X, et al. 2009. Physicalindex, dynamic property and landslides of Ili loess[J]. Arid Land Geography, 32 (6): 899-905. Zhang W, Zhang A J, Chen J M, et al. 2017. Effects of moisture content and density on collapsibilitycoefficient of Ili loess[J]. Journal of Northwest A & F University(Natural Science Edition), 45 (5): 211-220. Zhang Y, Zhang X M, Zhou Z J. 2020. Analysis of loess collapsibility and the influencing factors[J]. Highway, 65 (8): 69-75. 陈凯, 张森, 梁冲, 等. 2021. 乌鲁木齐市主要岩土层物理力学性质指标相关性分析[J]. 中国矿业, 30 (4): 224-228. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGKA202104039.htm 陈彦光. 2011. 地理数学方法: 基础和应用[M]. 北京: 科学出版社. 董贵宇, 聂中明, 陈希, 等. 2022. 黄土湿陷性与物理力学指标的相关性分析: 以新疆伊犁地区黄土为例[J]. 世界地质, 41 (4): 751-762. https://www.cnki.com.cn/Article/CJFDTOTAL-SJDZ202204006.htm 《工程地质手册》编委会. 2018. 工程地质手册[M]. 5版. 北京: 中国建筑工业出版社. 李德厚, 王圆. 2011. 湿陷性黄土地区小变形下的沉降预测模型对比[J]. 山西建筑, 37 (30): 146-148. https://www.cnki.com.cn/Article/CJFDTOTAL-JZSX201130089.htm 李金秋, 王振兴, 侯新伟, 等. 2020. 冀南黄土状土湿陷性与物性指标相关性分析及预测[J]. 地质调查与研究, 43 (3): 259-264. https://www.cnki.com.cn/Article/CJFDTOTAL-QHWJ202003009.htm 李旭昶, 孙德安, 徐永福. 2019. 扬州土物理与力学性质指标的相关性分析[J]. 工程地质学报, 27 (2): 333-340. doi: 10.13544/j.cnki.jeg.2017-486 刘祖典. 1994. 影响黄土湿陷系数因素的分析[J]. 工程勘察, (5): 6-11. https://www.cnki.com.cn/Article/CJFDTOTAL-GCKC405.001.htm 钱建国. 2015. 土质学与土力学[M]. 北京: 人民交通出版社. 邱锡鹏. 2020. 神经网络与深度学习[M]. 北京: 机械工业出版社. 任文博, 刘云龙, 李佳佳, 等. 2022. 基于离散型二项式系数组合模型的黄土湿陷性评估[J]. 科学技术与工程, 22 (12): 4945-4953. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202212034.htm 邵生俊, 杨春鸣, 马秀婷, 等. 2013. 黄土的独立物性指标及其与湿陷性参数的相关性分析[J]. 岩土力学, 34 (S2): 27-34. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX2013S2005.htm 史宝东, 梁庆国, 赵涛, 等. 2021. 场地黄土扰动前后的湿陷性与其物性指标的关系[J]. 地震工程学报, 43 (4): 977-982, 988. https://www.cnki.com.cn/Article/CJFDTOTAL-ZBDZ202104031.htm 唐辉, 张瑞松, 高建中. 2023. 延安新区黄土湿陷性与其物性指标的相关性分析[J]. 地基处理, 5 (1): 19-24. https://www.cnki.com.cn/Article/CJFDTOTAL-DJCL202301003.htm 王吉庆, 雷胜友, 李肖伦, 等. 2013. 黄土湿陷系数与物理性质参数的相关性[J]. 煤田地质与勘探, 41 (3): 42-45, 50. https://www.cnki.com.cn/Article/CJFDTOTAL-MDKT201303013.htm 席宁, 梅钢, 徐能雄. 2019. 基于统计的岩石物理力学参数相关性研究[J]. 工程地质学报, 27 (S1): 425-430. doi: 10.13544/j.cnki.jeg.2019092 邢姣秀. 2004. 影响黄土湿陷性因素分析研究[D]. 西安: 长安大学. 熊汝全, 刘凌军, 刘国辉, 等. 2023. 基于PSO-SVM的黄土湿陷性预测研究[J]. 建筑技术开发, 50 (1): 61-63. https://www.cnki.com.cn/Article/CJFDTOTAL-JZKF202301020.htm 杨校辉, 黄雪峰, 朱彦鹏, 等. 2014. 大厚度自重湿陷性黄土地基处理深度和湿陷性评价试验研究[J]. 岩石力学与工程学报, 33 (5): 1063-1074. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201405022.htm 叶玮. 2000. 新疆伊犁地区黄土矿物特征与沉积环境[J]. 干旱区研究, 17 (4): 1-10. https://www.cnki.com.cn/Article/CJFDTOTAL-GHQJ200004000.htm 尹光华, 王兰民, 袁中夏, 等. 2009. 新疆伊犁黄土的物性指标、动力学特性与滑坡[J]. 干旱区地理, 32 (6): 899-905. https://www.cnki.com.cn/Article/CJFDTOTAL-GHDL200906013.htm 张婉, 张爱军, 陈佳玫, 等. 2017. 含水率和密度对伊犁黄土湿陷系数的影响[J]. 西北农林科技大学学报(自然科学版), 45 (5): 211-220. https://www.cnki.com.cn/Article/CJFDTOTAL-XBNY201705029.htm 张瑜, 张兴明, 周志军. 2020. 黄土湿陷性及其影响因素分析[J]. 公路, 65 (8): 69-75. https://www.cnki.com.cn/Article/CJFDTOTAL-GLGL202008014.htm 中华人民共和国国家标准编写组. 2019. 土工试验方法标准(GBT 50123-2019)[S]. 北京: 中国计划出版社. -