img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2018, Vol. 26 ›› Issue (1): 49-55.doi: 10.11872/j.issn.1005-2518.2018.01.049

• 采选技术与矿山管理 • 上一篇    下一篇

岩体质量分类的PCA-RF模型及应用

刘强,李夕兵,梁伟章*   

  1. 中南大学资源与安全工程学院,湖南 长沙 410083
  • 收稿日期:2016-12-12 修回日期:2017-02-26 出版日期:2018-02-28 发布日期:2018-05-19
  • 通讯作者: 梁伟章(1992-),男,江西抚州人,硕士研究生,从事采矿与岩土工程方面的研究工作。1246585711@qq.com
  • 作者简介:刘强(1988-),男,湖南邵阳人,硕士研究生,从事采矿研究工作。450762362@qq.com
  • 基金资助:

    国家自然科学基金重点项目“深部资源开采诱发岩体动力灾害机理与防控方法研究”(编号:41630642)和国家自然科学基金面上项目“深部硬岩开挖卸荷的动态响应机理研究”(编号:11472311)联合资助 

PCA-RF Model for the Classification of Rock Mass Quality and Its Application

LIU Qiang,LI Xibing,LIANG Weizhang   

  1. chool of Resources and Safety Engineering,Central South University,Changsha    410083,Hunan,China
  • Received:2016-12-12 Revised:2017-02-26 Online:2018-02-28 Published:2018-05-19

摘要:

为了更合理地确定岩体质量类别,将主成分分析(PCA)与随机森林(RF)算法相结合,提出一种岩体质量分类的PCA-RF模型。选取能够充分反映岩体质量类别的5项指标进行分析,运用主成分分析法对各指标进行相关性处理,依据方差累计贡献率得出3个主成分,从而消除指标间的相关性,减少模型输入。然后采用随机森林模型对岩体质量进行分类,选用现场20组数据作为训练样本、10组数据作为测试样本,利用交叉验证的方法估计泛化误差。结果表明,该方法分类结果与实际结果较吻合,平均准确率达96.7%,同时得出岩体质量所处类别的概率分布,进一步反映岩体质量的复杂度,为工程建设提供更详细的参考依据。

关键词: 岩体质量, 主成分分析, 随机森林, 指标相关性, 交叉验证, 泛化误差

Abstract:

In order to determine the classification of rock mass quality more reasonably,PCA-RF classification model of rock mass quality was proposed which combined with principal component analysis and random forest algorithm.Five classification indexes were chosen which can fully reflect the rock mass quality category.The correlation analysis of indexes was calculated by principal component analysis,and three principal components were abtained by accumulated variance devoted rate,which can eliminate the correlation between each index and reduce the inputs of model.Then,the classification of rock mass quality was determined by random forest model.Twenty sets field data were chosen as training samples,and ten sets field data were chosen as testing samples.The generalization errors were estimated by cross-validation method.The results show that the classification results satisfyingly agree with the actual results at the average accuracy of 96.7%,and the probability distribution of classifications that can reflect the complexity of rock mass quality was calculated simultaneously,which can provide more detailed reference for engineering construction.

Key words: rock mass quality, principal component analysis, random forest, correlation of index, cross-validation, generalization errors, classification

中图分类号: 

  • TU457
[ 1 ] Cai M,Kaiser P K.Visualization of rock mass classification systems[J].Geotechnical and Geological Engineering,2006,24(4):1089-1102.
[ 2 ] 蔡美峰. 岩石力学与工程[M].北京:科学出版社,2002:10-25.Cai Meifeng.Rock Mechanics and Engineering[M].Beijing:Science Press,2002:10-25.
[ 3 ] 陈昌彦,王贵荣.各类岩体质量评价方法的相关性探讨[J].岩石力学与工程学报,2002,21(12):1894-1900.Chen Changyan,Wang Guirong.Discussion on the interrelation of various rock mass quality classification systems at home and abroad[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(12):1894-1900.
[ 4 ] 江飞飞,李向东,盛佳,等.软弱破碎岩体工程地质调查与质量评价[J].黄金科学技术,2016,24(3):94-99.Jiang Feifei,Li Xiangdong,Sheng Jia,et al.Engineering geological investigation and quality evaluation of soft fractured rock[J].Gold Science and Technology,2016,24(3):94-99.
[ 5 ] 赵明阶,吴德伦.工程岩体的超声波分类及强度预测[J].岩石力学与工程学报,2000,19(1):89-92.Zhao Mingjie,Wu Delun.The ultrasonic identification of rock mass classification and rock mass strength prediction[J].Chinese Journal of Rock Mechanics and Engineering,2000,19(1):89-92.
[ 6 ] 董金奎,申延,邱俊刚.焦家金矿寺庄矿区岩体节理裂隙调查与矿岩稳定性分析[J].黄金科学技术,2012,20(2):58-61.Dong Jinkui,Shen Yan,Qiu Jungang.Investigation of joint fissure and analysis of ore-rock stability in Sizhuang mining of Jiaojia gold deposit[J].Gold Science and Technology,2012,20(2):58-61.
[ 7 ] Palmstrom A,Broch E.Use and misuse of rock mass classification systems with particular reference to the Q-system[J].Tunneling and Underground Space Technology,2006,21(6):575-593.
[ 8 ] 贾明涛,王李管.基于区域化变量及RMR评价体系的金川Ⅲ矿区矿岩质量评价[J].岩土力学,2010,31(6):1907-1912.Jia Mingtao,Wang Liguan.Evaluation of rock mass quality based on regionalization variable optimal estimation theory and RMR system in Jinchuan mine No.3[J].Rock and Soil Mechanics,2010,31(6):1907-1912.
[ 9 ] 邬爱清,汪斌.基于岩体质量指标BQ的岩质边坡工程岩体分级方法[J].岩石力学与工程学报,2014,33(4):699-706.Wu Aiqing,Wang Bin.Engineering rock mass classification method based on rock mass quality index BQ for rock slope[J].Chinese Journal of Rock Mechanics and Engineering,2014,33(4):699-706.
[ 10 ] 连建发,慎乃齐,张杰坤.分形理论在岩体质量评价中的应用研究[J].岩石力学与工程学报,2001,20(增):1695-1698.Lian Jianfa,Shen Naiqi,Zhang Jiekun.Application research on fractal theory in rock mass quality evaluation[J].Chinese Journal of Rock Mechanics and Engineering,2001,20(Supp.):1695-1698.
[ 11 ] 钱兆明,任高峰,褚夫蛟,等. 基于PCA法和Fisher判别分析法的岩体质量等级分类[J].岩土力学,2016,37(增2):427-432.Qian Zhaoming,Ren Gaofeng,Chu Fujiao,et al. Rock mass quality classification based on PCA and Fisher discrimination analysis[J].Rock and Soil Mechanics,2016,37(Supp.2):427-432.
[ 12 ] 李强.BP神经网络在工程岩体质量分级中的应用研究[J].西北地震学报,2002,24(3):220-224.Li Qiang.Study on the application of BP nervous network in classification of rock mass quality[J].Northwestern Seismological Journal,2002,24(3):220-224.
[ 13 ] 吴肖坤,刘敦文,江帆,等.基于特征值域的可拓学理论的工程岩体质量评价[J].黄金科学技术,2015,23(2):68-74.Wu Xiaokun,Liu Dunwen,Jiang Fan,et al. Extension theory of engineering rock mass quality evaluation based on the feature range[J].Gold Science and Technology,2015,23(2):68-74.
[ 14 ] 胡建华,尚俊龙,雷涛.基于RS-TOPSIS法的地下工程岩体质量评价[J].中南大学学报(自然科学版),2012,43(11):4412-4419.Hu Jianhua,Shang Junlong,Lei Tao.Rock mass quality evaluation of underground engineering based on RS-TOPSIS method[J].Journal of Central South University (Science and Technology),2012,43(11):4412-4419.
[ 15 ] Breiman L. Random forests[J].Machine Learning,2001,45(1):5-32.
[ 16 ] Peters J,Baets B D,Verhoest N,et al.Random forests as a tool for ecohydrological distribution modelling[J].Ecological Modelling,2007,207(2/3/4):304−318.
[ 17 ] Lee S L,Kouzani A Z,Hu E J.Random forest based lung nodule classification aided by clustering[J].Computerized Medical Imaging & Graphics,2010,34(7):535-542.
[ 18 ] 王茵茵,齐雁冰,陈洋,等.基于多分辨率遥感数据与随机森林算法的土壤有机质预测研究[J].土壤学报,2016,53(2):342-354.Wang Yinyin,Qi Yanbing,Chen Yang,et al.Prediction of soil organic matter based on multi-resolution remote sensing data and random forest algorithm[J].Acta Pedologica Sinica,2016,53(2):342-354.
[ 19 ] Pearson K. Principal components analysis[J].The London,Edinburgh and Dublin Philosophical Magazine and Journal,1901,6(2):566.
[ 20 ] 李夕兵,朱玮,刘伟军,等.基于主成分分析法与RBF神经网络的岩体可爆性研究[J].黄金科学技术,2015,23(6):58-63.Li Xibing,Zhu Wei,Liu Weijun,et al. Research on rock mass blastability based on principal component analysis and RBF neural network[J].Gold Science and Technology,2015,23(6):58-63.
[ 21 ] 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.Zhou Songlin,Mao Meiqin,Su Jianhui.Prediction of wind power based on principal component analysis and artificial neural network[J].Power System Technology,2011,35(9):128-132.
[ 22 ] 曹正凤. 随机森林算法优化研究[D].北京:首都经济贸易大学,2014.Cao Zhengfeng. Study on Optimization of Random Forests Algorithm[D].Beijing:Capital University of Economics and Business,2014.
[ 23 ] 中华人民共和国国家标准编写组.工程岩体分级标准:GB50218-94[S].北京:中国计划出版社,1995.The National Standards Compilation Group of People’s Republic of China.Standard for engineering classification of rock masses:GB50218-94[S].Beijing:China Planning Press,1995.
 
[1] 马凤山,郭捷,李克蓬,卢蓉,张洪训,李威. 三山岛海底金矿开采充填体与顶板岩层的变形监测研究[J]. 黄金科学技术, 2016, 24(4): 66-72.
[2] 李克蓬,马凤山,郭捷,卢蓉,张洪训,李威. 三山岛海底金矿开采充填体与围岩变形规律的数值模拟[J]. 黄金科学技术, 2016, 24(4): 73-80.
[3] 刘科伟,曾庆田,刘栋. 边坡复杂地质结构三维可视化及数值模型构建[J]. 黄金科学技术, 2016, 24(2): 83-89.
[4] 郭广军,刘明君,徐咏彬,程蔚,叶延龄,郑小礼,高海峰,赵荣欣. 山东焦家金矿床工程岩体稳定性分类研究[J]. J4, 2012, 20(4): 71-75.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!