A PCA-ELM model for better classifying expansive soil was proposed in this paper by integrating Principal Component Analysis(PCA) and Extreme Learning Machine(ELM). Four classification indexes well reflecting the swell-shrink characteristics of expansive soils, namely liquid limit, plasticity index, content of clay particles smaller than 2 μm, and free swell ratio, were selected for correlation analysis, and two principal components were determined according to accumulated variance contribution rate.Subsequently, 70% of the samples were divided as training set which was taken as the input of extreme learning machine, and 10-fold cross validation was used to optimize model parameters so as to achieve the optimal classification; 30% of the samples were chosen as test set as the input of the optimal model to obtain classification results.The classification model was validated with 32 testing examples from two engineering projects, and results suggest that the classification results agreed well with measured data, with the classification accuracy of training set and test set reaching 94.20% and 79.00%, respectively; moreover, the proposed model is of fast training speed, hence is suitable for the classification and prediction of large-scale data.
Key words
expansive soil /
extreme learning machine /
principal component analysis /
classification model /
cross validation
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] SHI B, JIANG H, LIU Z, et al. Engineering Geological Characteristics of Expansive Soils in China[J] . Engineering Geology, 2002, 67(1/2): 63-71.
[2] WANG M, LI J, GE S, et al. Moisture Migration Tests on Unsaturated Expansive Clays in Hefei, China[J] . Applied Clay Science, 2013, 79(7): 30-35.
[3] 刘 鸣, 程永辉, 童 军. 南水北调中线工程膨胀土边坡处理效果及评价[J] . 长江科学院院报, 2016, 33(3): 104-110.
[4] 陈善雄, 余 颂, 孔令伟, 等. 膨胀土判别与分类方法探讨[J] . 岩土力学, 2005, 26(12): 1895-1900.
[5] 谭罗荣, 张梅英, 邵梧敏, 等. 风干含水量W65用作膨胀土判别分类指标的可行性研究[J] . 工程地质学报, 1994, 2(1): 15-26.
[6] 马桂芝. 应用塑性图对陕西特殊土的判别[J] . 西安地质学院学报, 1995, 17(2): 87-89.
[7] 郭昱葵, 熊友山, 姚海林, 等. 模糊数学在当宜高速公路膨胀土判别和分类中的应用[J] . 岩土力学, 1999, 20(3): 61-65.
[8] YILMAZ I. Indirect Estimation of the Swelling Percent and A New Classification of Soils Depending on Liquid Limit and Cation Exchange Capacity[J] . Engineering Geology, 2006, 85(3/4): 295-301.
[9] 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.
[10] 余 颂, 陈善雄, 余 飞, 等. 膨胀土判别与分类的Fisher判别分析方法[J] . 岩土力学, 2007, 28(3): 499-504.
[11] 曾志雄, 田 海, 黄珏皓. 基于云模型的膨胀土胀缩等级分类[J] . 长江科学院院报, 2016, 33(2): 80-85.
[12] HUANG G B, ZHU Q Y, SIEW C K. Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks[C] ∥Proceedings of International Joint Conference on Neural Networks. Budapest, Hungary, July 25-29, 2004: 985-990.
[13] 裘日辉, 刘康玲, 谭海龙, 等. 基于极限学习机的分类算法及在故障识别中的应用[J] . 浙江大学学报(工学版), 2016, 50(10):1965-1972.
[14] 宋永东, 苏立君, 张崇磊, 等. 基于极限学习机的边坡可靠度分析[J] . 长江科学院院报, 2018, 35(8): 78-83.
[15] 李冬辉, 闫振林, 姚乐乐,等. 基于改进流形正则化极限学习机的短期电力负荷预测[J] . 高电压技术, 2016, 42(7):2092-2099.
[16] 朱永飞. 基于主成分分析的洪灾损失影响因子评估[J] . 长江科学院院报, 2015, 32(5):53-56.
[17] 周松林,茆美琴,苏建徽. 基于主成分分析与人工神经网络的风电功率预测[J] . 电网技术,2011,35(9):128-132.
[18] GB 50112—2013, 膨胀土地区建筑技术规范[S] . 北京: 中国建筑工业出版社, 2013.
[19] JTG D30—2004, 公路路基设计规范[S] . 北京: 人民交通出版社, 2015.
PDF(1903 KB)
