基于C4.5决策树算法的土质边坡稳定性评价研究

胡 杰; 綦春明; 孙 冰; 聂春龙

doi:10.11988/ckyyb.20140543

PDF(1060 KB)

长江科学院院报 ›› 2015, Vol. 32 ›› Issue (12) : 82-86. DOI: 10.11988/ckyyb.20140543

岩土工程

基于C4.5决策树算法的土质边坡稳定性评价研究

胡杰,綦春明,孙冰,聂春龙

作者信息 +

Study on Stability Evaluation of Soil Slope Based on C4.5 DecisionTree Algorithm

HU Jie,QI Chun-ming,SUN Bing,NIE Chun-long

Author information +

文章历史 +

摘要

采用神经网络进行土质边坡稳定性评价时,差异性较大的训练样本往往会使评价结果不太理想。针对这一问题引入C4.5决策树算法,采用多个土质边坡工程的实测数据,运用信息增益率进行分类属性的选择,并对建立好的树体结构进行剪枝操作,建立基于决策树的土质边坡稳定性评价模型。将该模型与BP神经网络和LVQ(Learning Vector Quantization,学习向量量化)神经网络进行对比分析,结果显示决策树模型分类正确率最高,达到90%,模型所用时间为2.24 s,表明把决策树用于土质边坡稳定性评价是合理的。

Abstract

When the soil slope stability is evaluated by neural network model,varieties of training samples always make the evaluation result unsatisfactory.In order to solve the problem,we introduce the C4.5 decision tree algorithm,build an evaluation model of soil slope stability based on decision tree classifier,and prune the tree structure established.Furthermore,we adopt measured data in several soil slope projects and select classification attributes according to gain ratio of information in this model.Compared with BP neural network and LVQ(Learning Vector Quantization) neural network,the result shows that decision tree algorithm has the highest accuracy for classification,up to 90%,and the computation time of this model is 2.24 seconds.Finally,it is feasible to introduce decision tree algorithm for stability evaluation in soil slope.

导出引用

胡杰,綦春明,孙冰,聂春龙. 基于C4.5决策树算法的土质边坡稳定性评价研究[J]. 长江科学院院报. 2015, 32(12): 82-86 https://doi.org/10.11988/ckyyb.20140543

HU Jie,QI Chun-ming,SUN Bing,NIE Chun-long. Study on Stability Evaluation of Soil Slope Based on C4.5 DecisionTree Algorithm[J]. Journal of Changjiang River Scientific Research Institute. 2015, 32(12): 82-86 https://doi.org/10.11988/ckyyb.20140543

中图分类号： TU444

参考文献

[1] 冯夏庭.智能岩石力学导论[M].北京:科学出版社,2000.(FENG Xia-ting.Introduction to Intelligent Rock Mechanics[M].Beijing:Science Press,2000.(in Chinese))
[2] 陈乐求,彭振斌,陈伟,等.基于模糊控制的人工神经网络模拟在土质边坡安全预测中的应用[J].中南大学学报(自然科学版),2009,40(5):1381-1387.(CHEN Le-qiu,PENG Zhen-bin,CHEN Wei,et al.Artificial Neural Network Simulation on Prediction of Clay Slope Stability Based on Fuzzy Controller[J].Journal of Central South University (Science and Technology),2009,40(5):1381-1387.(in Chinese))
[3] 姜德义,李光扬,谢世平,等.基于神经网络法预测重庆高速公路边坡稳定性[J].地下空间与工程学报,2008,4(1):152-156.(JIANG De-yi,LI Guang-yang,XIE Shi-ping,et al.Forecast of Expressway Slope Stability in Chongqing Area Based on the Neural Network[J].Chinese Journal of Underground Space and Engineering,2008,4(1):152-156.(in Chinese))
[4] 胡军,钟龙,杨昕光.基于水平条分任意滑动面的边坡稳定性分析上限法[J].土木工程学报,2013,46(6):117-121.(HU Jun,ZHONG Long,YANG Xin-guang.Upper Bound Approach for Slope Stability Analysis Based on Arbitrary Sliding Surface and Horizontal Slices[J].China Civil Engineering Journal,2013,46(6):117-121.(in Chinese))
[5] 王根龙,伍法权,张军慧.非均质土坡稳定性分析评价的刚体单元上限法[J].岩石力学与工程学报,2008,27(增2):3425-3430.(WANG Gen-long,WU Fa-quan,ZHANG Jun-hui.Upper Bound Approach of Rigid Elements for Inhomogeneous Soil Slope Stability Analysis[J].Chinese Journal of Rock Mechanics and Engineering,2008,27(Sup.2):3425-3430.(in Chinese))
[6] 刘海波,刘玉丽,林大超,等.基于Bishop法基础上的土质边坡有限元强度折减法的适用性探讨[J].公路,2010,(3):15-18.(LIU Hai-bo,LIU Yu-li,LIN Da-chao,et al.Discussion About Applicability of Strength Reduction FEM Method of Soil Slope Based on Bishop Method[J].Highway,2010,(3):15-18.(in Chinese))
[7] BRUNER J R,GOODNOW J J,AUSTIN G A.A Study of Thinking[M].New York:John Wiley & Sons,1957:98-120.
[8] 何诚,董志海,张思玉,等.基于决策树系统的遥感植被分类技术[J].测绘科学,2014,39(1):83-86.(HE Cheng,DONG Zhi-hai,ZHANG Si-yu,et al.Vegetation Classification Technology of Hyperspectral Remote Sensing Based on Decision Tree Tool[J].Science of Surveying and Mapping,2014,39(1):83-86.(in Chinese))
[9] 崔珂瑾,程昌秀,李晓岚.基于决策树的耕地转建设用地分析与预测——以北京房山区为例[J].地理与地理信息科学,2014,30(1):60-64.(CUI Ke-jin,CHENG Chang-xiu,LI Xiao-lan.Analysis and Forecast of Land Change from Cultivated Land to Construction Land Based on Decision Trees:A Case Study of Fangshan District,Beijing[J].Geography and Geo-Information Science,2014,30(1):60-64.(in Chinese))
[10]李楠,段隆振,陈萌.决策树C4.5算法在数据挖掘中的分析及其应用[J].计算机与现代化,2008,(12):160-163.(LI Nan,DUAN Long-zhen,CHEN Meng.Research and Application of Data Mining Algorithm Based on Decision Tree[J].Computer and Modernization,2008,(12):160-163.(in Chinese))
[11]陈辉林,夏道勋.基于CART决策树数据挖掘算法的应用研究[J].煤炭技术,2011,30(10):164-166.(CHEN Hui-lin,XIA Dao-xun.Applied Research on Data Mining Based on CART Decision Tree Algorithm[J].Coal Technology,2011,30(10):164-166.(in Chinese))
[12]王黎明.决策树学习及其剪枝算法研究[D].武汉:武汉理工大学,2007.(WANG Li-ming.Research on Learning and Pruning Algorithm of Decision Tree[D].Wuhan:Wuhan University of Technology,2007.(in Chinese))
[13]TAN Pang-ning,Michael Steinbach,Vipin Kumar.数据挖掘导论[M].范明,范宏建,译.北京:人民邮电出版社,2009.(TAN Pang-ning,STEINBACH M,KUMAR V.Introduction to Data Mining[M].Translated by FAN Ming,FAN Hong-jian.Beijing:Posts & Telecom Press,2009.(in Chinese))
[14]肖桃李,李新平,米健.土质边坡稳定性影响因素的研究[J].地质灾害与环境保护,2007,18(2):89-93.(XIAO Tao-li,LI Xin-ping,MI Jian.A Study of the Effect Factor on Slope Stability[J].Journal of Geological Hazards and Environment Preservation, 2007,18(2):89-93.(in Chinese))
[15]李靖,周欣华,党进谦.黄土边坡稳定性图解法[J].岩土工程学报,1998,20(4):40-43.(LI Jing,ZHOU Xin-hua,DANG Jin-qian.Graphic Method for the Stability of Loess Slopes[J].Chinese Journal of Geotechnical Engineering,1998,20(4):40-43.(in Chinese))
[16]高建勇,邢义川,陈艳霞.黄土高边坡稳定性预测模型研究[J].岩土工程学报,2011,33(增1):163-169.(GAO Jian-yong,XING Yi-chuan,CHEN Yan-xia.Prediction Model for Stability of High Loess Slopes[J].Chinese Journal of Geotechnical Engineering,2011,33(Sup.1):163-169.(in Chinese))
[17]郭杜峰,毛彦龙,高德彬,等.基于人工神经网络的公路黄土高边坡稳定性预测研究[J].公路交通科技,2005,22(9):59-62.(GUO Du-feng,MAO Yan-long,GAO De-bin,et al.Study on Artificial Neural Network Method for Stability Prediction in Loess High Slope and Stability of the Highway[J].Journal of Highway and Transportation Research and Development,2005,22(9):59-62.(in Chinese))
[18]于旭.模式分类中训练样本集的构造方法研究[D].哈尔滨:哈尔滨工程大学,2012.(YU Xu.Research on Construction Method of Training Set in Pattern Classification[D].Harbin:Harbin Engineering University,2012.(in Chinese))