A data-driven model for predicting shear strength indexes of normally consolidated soils

WANG Yuke; FENG Shuang; ZHONG Yanhui; ZHANG Bei

doi:10.11779/CJGE2023S20025

Volume 45 Issue S2

Turn off MathJax

Article Contents

Abstract

References

Chinese Journal of Geotechnical Engineering > 2023 > 45(S2): 183-188. > DOI: 10.11779/CJGE2023S20025

WANG Yuke, FENG Shuang, ZHONG Yanhui, ZHANG Bei. A data-driven model for predicting shear strength indexes of normally consolidated soils[J]. Chinese Journal of Geotechnical Engineering, 2023, 45(S2): 183-188. DOI: 10.11779/CJGE2023S20025

Citation:

PDF (1705 KB)

A data-driven model for predicting shear strength indexes of normally consolidated soils

WANG Yuke^{1, 2, 3,},
FENG Shuang^{1, 2, 3},
ZHONG Yanhui^{1, 2, 3},
ZHANG Bei^{1, 2, 3}

1.
School of Water Conservancy and Transportation, Zhengzhou University, Zhengzhou 450001, China
2.
National Local Joint Engineering Laboratory of Major Infrastructure Testing and Rehabilitation Technology, Zhengzhou 450001, China
3.
Provincial and Ministerial Collaborative Innovation Center for Underground Engineering Disaster Prevention and Control, Zhengzhou 450001, China

More Information

Received Date: November 29, 2023
Available Online: April 19, 2024

Graphical Abstract

Abstract

Abstract

The accurate determination of shear strength indexes is crucial for engineering soils. Currently, the strength indexes determined by the test method depend too much on engineering experience, which leads to the uncertainty of the final value. The ensemble learning is a subclass of machine learning that exhibits strong performance when dealing with complex data and tasks. To enhance the precision of the shear strength indexes, based on the normally consolidated soils, a model is established using the diverse ensemble learning algorithms for predicting the shear strength indexes of soils. Various models are assessed for their generalization capability using the root mean square error (RMSE), coefficient of determination (R²) and absolute value error (MAE). The Adaboost algorithm is employed for the sensitivity analysis of input parameters. The findings indicate that the Adaboost algorithm yields the best generalization for the shear strength the RF for the internal friction angle, and the Adaboost algorithm for the cohesion, achieving respective test-set R² values of 0.925, 0.965 and 0.942. The sensitivity analyses reveal that the dry density, moisture content and normal stress exert the most significant influence on the shear strength, while the key factors for the internal friction angle are the coefficient of curvature, viscous grain content and water content. The water content, dry density and liquid limit are identified as the primary influencers on the cohesion. The data-driven model established herein offers guidance for selecting the shear strength indexes in engineering and investigating strength parameters of soils through the machine learning methods.
- normally consolidated soil,
- shear strength index,
- ensemble learning,
- machine learning,
- sensitivity analysis

FullText(HTML)

References (23)

References

[1]	VANAPALLI S K, FREDLUND D G. Comparison of different procedures to predict unsaturated soil shear strength[C]// Advances in Unsaturated Geotechnics. Denver, 2000.
[2]	雷洁, 张国明, 刘连友, 等. 土壤抗剪强度测定与影响因素研究进展[J]. 北京师范大学学报(自然科学版), 2016, 52(4): 486-492. https://www.cnki.com.cn/Article/CJFDTOTAL-BSDZ201604014.htm LEI Jie, ZHANG Guoming, LIU Lianyou, et al. Measuring soil shear strength and impact factors[J]. Journal of Beijing Normal University (Natural Science), 2016, 52(4): 486-492. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BSDZ201604014.htm
[3]	雷国辉, 高翔, 徐可, 等. 饱和软黏土固结过程中的不排水抗剪强度特性[J]. 岩土工程学报, 2019, 41(1): 41-49. doi: 10.11779/CJGE201901004 LEI Guohui, GAO Xiang, XU Ke, et al. Behavior of undrained shear strength of saturated soft clay under consolidation[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(1): 41-49. (in Chinese) doi: 10.11779/CJGE201901004
[4]	胡海军, 魏丽敏, 冷伍明. 黏土强度指标的测定和选取[J]. 岩土力学, 2007, 28(12): 2698-2704. doi: 10.3969/j.issn.1000-7598.2007.12.042 HU Haijun, WEI Limin, LENG Wuming. Determination and choice of strength index of clay[J]. Rock and Soil Mechanics, 2007, 28(12): 2698-2704. (in Chinese) doi: 10.3969/j.issn.1000-7598.2007.12.042
[5]	闫澍旺, 封晓伟, 侯晋芳, 等. 用十字板强度推算软黏土抗剪强度指标的方法及应用[J]. 岩土工程学报, 2009, 31(12): 1805-1810. doi: 10.3321/j.issn:1000-4548.2009.12.001 YAN Shuwang, FENG Xiaowei, HOU Jinfang, et al. Deduction and application of strength parameters of soft clay by use of vane strength[J]. Chinese Journal of Geotechnical Engineering, 2009, 31(12): 1805-1810. (in Chinese) doi: 10.3321/j.issn:1000-4548.2009.12.001
[6]	ZHANG P, YIN Z Y, JIN Y F. Machine learning-based modelling of soil properties for geotechnical design: review, tool development and comparison[J]. Archives of Computational Methods in Engineering, 2022, 29(2): 1229-1245. doi: 10.1007/s11831-021-09615-5
[7]	ZHANG W G, LI H R, LI Y Q, et al. Application of deep learning algorithms in geotechnical engineering: a short critical review[J]. Artificial Intelligence Review, 2021, 54(8): 5633-5673. doi: 10.1007/s10462-021-09967-1
[8]	LI Y Y, RAHARDJO H, SATYANAGA A, et al. Soil database development with the application of machine learning methods in soil properties prediction[J]. Engineering Geology, 2022, 306: 106769. doi: 10.1016/j.enggeo.2022.106769
[9]	ZHANG Q, BARRI K, JIAO P, et al. Genetic programming in civil engineering: advent, applications and future trends[J]. The Artificial intelligence review, 2021, 54(3): 1863-1885. doi: 10.1007/s10462-020-09894-7
[10]	DAS S K, BASUDHAR P K. Prediction of residual friction angle of clays using artificial neural network[J]. Engineering Geology, 2008, 100(3/4): 142-145.
[11]	PHAM B T, SON L H, HOANG T A, et al. Prediction of shear strength of soft soil using machine learning methods[J]. Catena, 2018, 166: 181-191. doi: 10.1016/j.catena.2018.04.004
[12]	刘晓燕, 蔡国军, 邹海峰, 等. 基于CPTU数据融合技术的黏性土应力历史与强度特性评价研究[J]. 岩土工程学报, 2019, 41(7): 1270-1278. doi: 10.11779/CJGE201907011 LIU Xiaoyan, CAI Guojun, ZOU Haifeng, et al. Prediction of stress history and strength of cohesive soils based on CPTU and data fusion techniques[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(7): 1270-1278. (in Chinese) doi: 10.11779/CJGE201907011
[13]	RABBANI A, SAMUI P, KUMARI S. A novel hybrid model of augmented grey wolf optimizer and artificial neural network for predicting shear strength of soil[J]. Modeling Earth Systems and Environment, 2023, 9(2): 2327-2347. doi: 10.1007/s40808-022-01610-4
[14]	顾春生, 唐鑫, 朱常坤, 等. 基于主成分分析法优化神经网络的滆湖组黏性土抗剪强度预测[J]. 科学技术与工程, 2023, 23(28): 11980-11989. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202328008.htm GU Chunsheng, TANG Xin, ZHU Changkun, et al. Prediction of shear strength of cohesive soil in Gehu formation based on back propagation neural network optimized by principal component analysis[J]. Science Technology and Engineering, 2023, 23(28): 11980-11989. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202328008.htm
[15]	黄鑫中. 不同击实功下非饱和黄土强度特性研究[D]. 西安: 长安大学, 2021. HUANG Xinzhong. Study on Strength Characteristics of Unsaturated Loess Under Different Compaction Work[D]. Xi'an: Changan University, 2021. (in Chinese)
[16]	雷昊楠. 黄土剪切面特征及抗剪强度影响因素试验研究[D]. 西安: 长安大学, 2021. LEI Haonan. Research for Loess Shear Surface Characteristics and Influencing Factors of Shear Strength[D]. Xi'an: Changan University, 2021. (in Chinese)
[17]	朱志坤. 干密度和含水率对太原重塑黄土强度及强度参数影响的研究[D]. 太原: 太原理工大学, 2018. ZHU Zhikun. Effect of Dry Density and Water Content on the Stregth and Strength Parameters of Remolded Loess in Taiyuan[D]. Taiyuan: Taiyuan University of Technology, 2018. (in Chinese)
[18]	陈梦芸. 击实黏土抗拉强度研究[D]. 南京: 南京大学, 2014. CHEN Mengyun. Study on Tensile Strength of Compacted Clay[D]. Nanjing: Nanjing University, 2014. (in Chinese)
[19]	杨永亮. 不同击实因素对黄土状粉土击实特性及抗剪强度影响的试验研究[D]. 太原: 太原理工大学, 2019. YANG Yongliang. Effect of Different Compaction Factors on Compaction Characteristics and Shear Strength of Loess Silt[D]. Taiyuan: Taiyuan University of Technology, 2019. (in Chinese)
[20]	DE WINTER J C F, GOSLING S D, POTTER J. Comparing the Pearson and Spearman correlation coefficients across distributions and sample sizes: a tutorial using simulations and empirical data[J]. Psychological Methods, 2016, 21(3): 273-290. doi: 10.1037/met0000079
[21]	SHRESTHA D L, SOLOMATINE D P. AdaBoost RT: a boosting algorithm for regression problems[J]. Proceedings of the IEEE International Joint Conference on Neural Networks, 2004, 2: 1163-1168.
[22]	GONG H R, SUN Y R, SHU X, et al. Use of random forests regression for predicting IRI of asphalt pavements[J]. Construction and Building Materials, 2018, 189: 890-897. doi: 10.1016/j.conbuildmat.2018.09.017
[23]	WEI P F, LU Z Z, SONG J W. Variable importance analysis: a comprehensive review[J]. Reliability Engineering & System Safety, 2015, 142: 399-432.