Predicting of swelling-shrinking level of expansive soil using support vector regression

ZHOU Suhua; ZHOU Shuaikang; ZHANG Yunqiang; NIE Zhihong; LEI Yu

doi:10.16031/j.cnki.issn.1003-8035.2021.01.16

2021 Vol. 32, No. 1

Article Contents

Article navigation > The Chinese Journal of Geological Hazard and Control > 2021 > 32(1): 117-126

Next Article Previous Article

ZHOU Suhua, ZHOU Shuaikang, ZHANG Yunqiang, NIE Zhihong, LEI Yu. Predicting of swelling-shrinking level of expansive soil using support vector regression[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32(1): 117-126. doi: 10.16031/j.cnki.issn.1003-8035.2021.01.16

Citation:

ZHOU Suhua, ZHOU Shuaikang, ZHANG Yunqiang, NIE Zhihong, LEI Yu. Predicting of swelling-shrinking level of expansive soil using support vector regression[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32(1): 117-126. doi: 10.16031/j.cnki.issn.1003-8035.2021.01.16

Predicting of swelling-shrinking level of expansive soil using support vector regression

1.
College of Civil Engineering, Hunan University, Changsha, Hunan　410082, China
2.
Key Laboratory of Building Safety and Energy Efficiency, Changsha, Hunan　410082, China
3.
College of Civil Engineering, Central South University, Changsha, Hunan　410075, China
4.
China Road & Bridge Corporation, Beijing　100010, China

Received Date: 06 April 2020

Revised Date: 26 May 2020

Publish Date: 25 February 2021

Abstract

Abstract

Level scaling of expansive soil is of significant importance in practical engineering. In this study, a support vector regression (SVR)-based predicting model of expansive soil level was proposed. Using the laboratory test dataset of expansive soil in Kenya, two training models with different predictors were built. Seven parameters, including liquid limit, plastic limit, plastic index, particle percentage of three different particle sizes (< 0.075、0.075～0.25、0.25～0.5), and soil type, were used in model I, while five parameters, including liquid limit, plastic limit, plastic index, percentage of particles with size < 0.075 and soil type, were used in model II. For each model, four kernels namely, Linear, Polynomial, RBF and Sigmoid, were used. The result had shown that all training models become stable when the sampling number reached 1000.The results show that with the increase of the number of randomly selected training samples, when the number of predictions reaches 1000, the prediction accuracy obtained by the SVR models with 4 different kernel functions basically stabilizes. The prediction effect is better when the RBF function and Linear function are used, followed by the Sigmoid kernel function. The prediction accuracy of the above three is more than 70% in scheme one, and prediction accuracy of the above three is more than 70% in scheme two. When Linear function, Sigmoid function, and RBF function are used as kernel function models to predict 44 groups of unknown expansive scale soil samples, the number of identical prediction results accounts for 73% in scheme one. The prediction scale of the remaining sets of soil samples is the same or adjacent, there is no "crossing" phenomenon. The number of identical prediction results accounts for 73% in scheme two, and there is no "crossing" phenomenon. The results of the study can provide a basis for the prediction and treatment of the scale of the expansion soil in the construction of Kenya and other regions.
- expansive soil /
- expansive scale /
- SVR /
- free swelling rate /
- prediction accuracy

FullText(HTML)

References

[1]	CHENG Y Z, HUANG X M. Effect of mineral additives on the behavior of an expansive soil for use in highway subgrade soils[J]. Applied Sciences,2018,9(1):30. doi: 10.3390/app9010030 CrossRef Google Scholar
[2]	徐锴, 耿之周, 李雄威. 脱湿速率对膨胀土堑坡稳定性的影响分析[J]. 岩土工程学报, 2017, 39(增刊1): 131-134. Google Scholar XU Kai, GENG Zhizhou, LI Xiongwei. Influence of different drying rates on stability of cut slope of expansive soils[J]. Chinese Journal of Geotechnical Engineering, 2017, 39(Sup1): 131-134. (in Chinese with English abstract) Google Scholar
[3]	尹鑫, 王迎超, 高杰, 等. 基于直觉模糊集的膨胀土胀缩性评价[J]. 土木工程学报,2018,51(5):103 − 111. [YIN Xin, WANG Yingchao, GAO Jie, et al. Evaluation on the swelling-shrinkage of expansive soil based on intuitionistic fuzzy set[J]. China Civil Engineering Journal,2018,51(5):103 − 111. (in Chinese with English abstract) Google Scholar
[4]	孔令伟, 陈正汉. 特殊土与边坡技术发展综述[J]. 土木工程学报,2012,45(5):141 − 161. [KONG Lingwei, CHEN Zhenghan. Advancement in the techniques for special soils and slopes[J]. China Civil Engineering Journal,2012,45(5):141 − 161. (in Chinese with English abstract) Google Scholar
[5]	WANG Z B, HUANG B, TAN F, et al. Characteristic analysis on swelling-shrinkage grade of expansive soil[C]//Proceedings of the 2014 International Conference on Mechanics and Civil Engineering. Atlantis Press, 2014. Google Scholar
[6]	宫凤强, 李夕兵. 膨胀土胀缩等级分类中的距离判别分析法[J]. 岩土工程学报,2007,29(3):463 − 466. [GONG Fengqiang, LI Xibing. Distance discriminant analysis to the classification of the grade of shrink and expansion for the expansive soils[J]. Chinese Journal of Geotechnical Engineering,2007,29(3):463 − 466. (in Chinese with English abstract) doi: 10.3321/j.issn:1000-4548.2007.03.026 CrossRef Google Scholar
[7]	WANG M W, CHEN G Y. A novel coupling model for risk analysis of swell and shrinkage of expansive soils[J]. Computers & Mathematics with Applications,2011,62(7):2854 − 2861. Google Scholar
[8]	曾志雄, 田海, 江名金. 基于遗传投影寻踪模型的膨胀土胀缩等级分类[J]. 南水北调与水利科技,2017,15(1):155 − 160. [ZENG Zhixiong, TIAN Hai, JIANG Mingjin. Classification of the swelling-shrinkage grade of expansive soils based on genetic projection pursuit model[J]. South-to-North Water Transfers and Water Science & Technology,2017,15(1):155 − 160. (in Chinese with English abstract) Google Scholar
[9]	中华人民共和国住房和城乡建设部. 膨胀土地区建筑技术规范: GB 50112—2013[S]. 北京: 中国建筑工业出版社, 2013. Google Scholar Ministry of Housing and Urban-Rural Development of the People's Republic of China. Technical code for building in expansive soil regions: GB 50112—2013[S]. Beijing: China Architecture & Building Press, 2013. (in Chinese) Google Scholar
[10]	黄卫, 钟理. 路基膨胀土胀缩等级的模糊评判[J]. 岩土工程学报,1999,21(4):408 − 413. [HUANG Wei, ZHONG Li. Fuzzy judgment about the grade of shrink and expansion for the expansive soil in the subgrade[J]. Chinese Journal of Geotechnical Engineering,1999,21(4):408 − 413. (in Chinese with English abstract) doi: 10.3321/j.issn:1000-4548.1999.04.006 CrossRef Google Scholar
[11]	IKIZLER S B, AYTEKIN M, VEKLI M, et al. Prediction of swelling pressures of expansive soils using artificial neural networks[J]. Advances in Engineering Software,2010,41(4):647 − 655. doi: 10.1016/j.advengsoft.2009.12.005 CrossRef Google Scholar
[12]	汪明武, 赵奎元, 张立彪. 基于联系期望的膨胀土和改良土胀缩性评价模型[J]. 岩土工程学报,2014,36(8):1553 − 1557. [WANG Mingwu, ZHAO Kuiyuan, ZHANG Libiao. A novel evaluation model based on connectional expectation for swelling-shrinkage grade of untreated and treated expansive clay[J]. Chinese Journal of Geotechnical Engineering,2014,36(8):1553 − 1557. (in Chinese with English abstract) doi: 10.11779/CJGE201408023 CrossRef Google Scholar
[13]	汪明武, 金菊良, 李丽. 可拓学在膨胀土胀缩等级评判中的应用[J]. 岩土工程学报,2003,25(6):754 − 757. [WANG Mingwu, JIN Juliang, LI Li. Application of extension method to the evaluation of the grade of shrinkage and expansion for the expansive soil[J]. Chinese Journal of Geotechnical Engineering,2003,25(6):754 − 757. (in Chinese with English abstract) doi: 10.3321/j.issn:1000-4548.2003.06.024 CrossRef Google Scholar
[14]	VAPNIK V. The Nature of Statistical Learning Theory[M]. New York: Springer-Verlag, 1995. Google Scholar
[15]	YANG H Y, LIU Y. Methods of support vector machine on classification of expansive soils[J]. Advanced Materials Research,2012,531:562 − 565. doi: 10.4028/www.scientific.net/AMR.531.562 CrossRef Google Scholar
[16]	苏治, 傅晓媛. 核主成分遗传算法与SVR选股模型改进[J]. 统计研究,2013,30(5):54 − 62. [SU Zhi, FU Xiaoyuan. Kernel principal component genetic algorithm and improved SVR stock selection model[J]. Statistical Research,2013,30(5):54 − 62. (in Chinese with English abstract) doi: 10.3969/j.issn.1002-4565.2013.05.008 CrossRef Google Scholar
[17]	张骏, 吴志敏, 潘雨帆, 等. 基于SVR模型的驾驶简单反应时间预测方法[J]. 中国公路学报,2017,30(4):127 − 132. [ZHANG Jun, WU Zhimin, PAN Yufan, et al. Predicting method of simple reaction time of driver based on SVR model[J]. China Journal of Highway and Transport,2017,30(4):127 − 132. (in Chinese with English abstract) doi: 10.3969/j.issn.1001-7372.2017.04.015 CrossRef Google Scholar
[18]	王芬, 刘阳, 郝建斌, 等. 基于MABC-SVR的边坡安全系数预测模型[J]. 安全与环境工程,2019,26(2):178 − 183. [WANG Fen, LIU Yang, HAO Jianbin, et al. Prediction model of slope safety factor based on MABC-SVR[J]. Safety and Environmental Engineering,2019,26(2):178 − 183. (in Chinese with English abstract) Google Scholar
[19]	林荣安, 孙钰丰, 戴振华, 等. 基于RS-SVR的上软下硬地层盾构施工地表沉降预测[J]. 中国公路学报,2018,31(11):130 − 137. [LIN Rongan, SUN Yufeng, DAI Zhenhua, et al. Predicting for ground surface settlement induced. By shield tunneling in upper-soft and lower-hard ground based on RS-SVR[J]. China Journal of Highway and Transport,2018,31(11):130 − 137. (in Chinese with English abstract) doi: 10.3969/j.issn.1001-7372.2018.11.014 CrossRef Google Scholar
[20]	国家铁路局. 铁路工程岩土分类标准: TB 10077—2019[S]. 北京: 中国铁道出版社, 2019. Google Scholar Nation Railway Administration of the People’s Republice of China. Code for Rock and Soil Classfication of Railway Engineering : TB 10077—2019[S]. Beijing: China Railway Publishing House, 2019. (in Chinese) Google Scholar