长江科学院院报 ›› 2018, Vol. 35 ›› Issue (12): 96-101.DOI: 10.11988/ckyyb.20170674

• 岩土工程 • 上一篇    下一篇

膨胀土分类的PCA-ELM模型及应用

陈建宏1, 李小龙1,2, 梁伟章1   

  1. 1.中南大学 资源与安全工程学院,长沙 410083;
    2.中国人民解放军91292部队,河北 高碑店 074000
  • 收稿日期:2017-06-12 出版日期:2018-12-01 发布日期:2018-12-18
  • 通讯作者: 李小龙(1988-),男,山东济南人,硕士研究生,主要从事岩土力学等领域研究。E-mail: 511898943@qq.com
  • 作者简介:陈建宏(1963-),男,湖南长沙人,教授,博士,主要从事岩土工程等领域研究。E-mail:cjh@263.net
  • 基金资助:
    国家自然科学基金项目(51374242,51404305)

PCA-ELM Model for Classification of Expansive Soil and Its Application

CHEN Jian-hong1, LI Xiao-long1,2, LIANG Wei-zhang1   

  1. 1.School of Resources and Safety Engineering, Central South University, Changsha 410083, China;
    2.The 91292 Troops of PLA, Gaobeidian 074000, China
  • Received:2017-06-12 Online:2018-12-01 Published:2018-12-18

摘要: 为更合理确定膨胀土类别,将主成分分析(PCA)与极限学习机(ELM)相结合,提出一种膨胀土分类的PCA-ELM模型。选取能充分反映膨胀土类别的液限、塑性指数、<2 μm胶粒含量与自由膨胀率4项指标进行分析,运用主成分分析对各指标进行相关性处理,依据方差累计贡献率得出2个主成分。将70%的样本划分为训练集,30%划分为测试集,将训练集作为极限学习机输入,并采用十折交叉验证以优化模型参数,从而得到最优分类模型。然后将测试集作为最优模型输入,得到分类结果。最后,选用2个工程实例共32个样本对所建立模型进行验证,结果表明:该模型分类结果与实际较吻合;训练集与测试集分类精度分别达94.20%和79.00%,并具有较快的训练速度。PCA-ELM模型适用于大规模数据的分类预测。

关键词: 膨胀土, 极限学习机, 主成分分析, 分类模型, 交叉验证

Abstract: 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

中图分类号: