基于网格搜索法优化支持向量机的围岩稳定性分类模型
|
摘要
为科学评价围岩稳定性,本次研究借助支持向量机(SVM)处理小样本、非线性问题能力强的特性,对围岩的稳定性进行了分类。选取16组围岩数据作为学习样本,以岩石质量指标、岩石单轴饱和抗压强度、完整性系数、结构面强度系数和地下水渗水量5个指标作为模型输入,围岩稳定程度为模型输出,建立了基于支持向量机的围岩稳定性分类模型。为增强模型的推广性能,提高其预测准确率,运用改进的网格搜索方法(GSM)寻找最优的支持向量机参数,并对8组围岩数据进行预测,并同BP神经网络模型的预测结果进行对比。结果表明,建立的GSM-SVM模型对预测样本的评判结果与实际结果一致,其预测精度较BP神经网络有很大的提升。
In order to make a scientific evaluation of surrounding rock stability,this work used the characteristics of support vector machine( SVM) for dealing with small samples and nonlinear problems to classify surrounding rock stability. Sixteen groups of surrounding rock data were chosen as learning samples,five indexes including rock quality,rock uniaxial saturated compressive strength,structural surface intensity coefficient and amount of groundwater seepage as the model input,and surrounding rock stability as a model output,thus the classification model for surrounding rock stability based on support vector machine was established. In order to improve generalization and prediction accuracy of SVM model,the SVM parameters were optimized by improved grid search method( GSM). Then eight groups of roadway surrounding rock data were predicted and results were compared with those of the BP neural network model. The results show that the stability classification results by GSM-SVM model for surrounding rock accord with the actual results,and the prediction accuracy of GSM-SVM model is greatly improved than that of BP neural network.
In order to make a scientific evaluation of surrounding rock stability,this work used the characteristics of support vector machine( SVM) for dealing with small samples and nonlinear problems to classify surrounding rock stability. Sixteen groups of surrounding rock data were chosen as learning samples,five indexes including rock quality,rock uniaxial saturated compressive strength,structural surface intensity coefficient and amount of groundwater seepage as the model input,and surrounding rock stability as a model output,thus the classification model for surrounding rock stability based on support vector machine was established. In order to improve generalization and prediction accuracy of SVM model,the SVM parameters were optimized by improved grid search method( GSM). Then eight groups of roadway surrounding rock data were predicted and results were compared with those of the BP neural network model. The results show that the stability classification results by GSM-SVM model for surrounding rock accord with the actual results,and the prediction accuracy of GSM-SVM model is greatly improved than that of BP neural network.
引文
Deng Shengjun,Lu Xiaomin,Huang Xiaoyang.2013.A brief summary of analysis methods for the stability of underground surrounding rock masses[J].Geology and Exploration,49(3):541-547(in Chinese with English abstract).
Fu Wenjie,Hong Jinyi,Zhu Guchang.2006.Extracting altered and mineralized rock information from remote sensing image based on support vector machine spectral similarity scale[J].Geology and Exploration,42(2):69-73(in Chinese with English abstract).
Guo Chao,Song Weihua,Wei Wei.2014.Slope roof stability prediction based on both SVM and grid-search method[J].China Safety Science Journal,24(8):31-36.
Guo Rui,Xu Guanglu.2013.Research on coal mine gas concentration Multi-sensor prediction model based on information fusion and GA-SVM[J].China Safety Science Journal,23(9):33-38(in Chinese with English abstract).
Jiang Jinquan,Feng Zengqiang,Han Jisheng.1999.Classification of structural stability of surrounding rocks of roadway affected by overhead mining and decision making of support parameters[J].Chinese Journal of Rock Mechanics and Engineering,18(1):81-85(in Chinese with English abstract).
Liu Bihong,Liu He.2016.Short-wave infrared spectroscopy study on wall rock alteration of the Gan-zhuershande silver-lead-zinc deposit in Inner Mongolia[J].Geology and Exploration,52(4):703-711(in Chinese with English abstract).
Liu Jun'e,Yang Xiaofan,Guo Zhanglin.2013.Prediction of coal mine gas concentration based on FIG-SVM[J].China safety Science Journal,23(2):80-84(in Chinese with English abstract).
Ma Fangbin,Du Yangsong,Li Dapeng,Tu Wei,Wang Kaihu,Bai Yu.2016.Geochemical characteristics of the Zhibo iron deposit in West Tianshan of China and geological implications[J].Geology and Exploration,52(1):01-13(in Chinese with English abstract).
Ning Yuncai,Xing Zhongguang.1997.Grey fuzzy assemblage analysis and its application in rock stability classification of gateway in mine[J].Systems Engineering Theory&Practice,17(8):115-124.
Niu Wenlin,Li Tianbin,Xiong Guobin,Zhang Guangyang.2011.Support vector machines based intelligent rock mass classification method[J].Journal of Engineering Geology,19(1):88-92(in Chinese with English abstract).
Qiu Daohong,Li Shucai,Xue Yiguo,Tian Hao,Yan Maowang.2014.Advanced prediction of surrounding rock classification based on digital drilling technology and QGA-RBF neural network[J].Rock and Soil Mechanics,35(7):2013-2018(in Chinese with English abstract).
Qiu Daohong,Li Shucai,Zhang Wenle,Xue Yiguo,Su Maoxin.2010.Prediction of surrounding rock classification in advance based on TSP203 system and GA-SVM[J].Chinese Journal of Rock Mechanics and Engineering,29(S1):3221-3226(in Chinese with English abstract).
Steve R Gunn.1998.Support Vector Machines for classification and regression[R].University of Southampton:23-65.
Vapnik V N.1995.The nature of statistical learning theory[M].New York:Springer-Verlag:23-105.
Wang Hongde,Cao Yinghao.2013.Evaluation of surrounding rock stability based on improved matter-element extension model with variable weight[J].China Safety Science Journal,23(8):23-29(in Chinese with English abstract).
Wang Kai,Yang Fan,Li Feng,Jian Runtang,Sun Yuhai,Yang Tao,Li Furong.2016.Study on the hydrothermal alteration and vein systems of the Pulang porphyry copper deposit in Yunnan Province[J].Geology and Exploration,52(3):417-428(in Chinese with English abstract).
Zhang Guoyun.2006.Research on support vector machine algorithm and its application[D].Changsha:Hunan University:1-33(in Chinese with English abstract).
Zhang Jianming,Zeng Jianwu,Xie Lei,Wang Shuqing.2007.Fault diagnosis based on RS and SVM[J].Journal of Tsinghua University(Science and Technology),47(S2):1774-1777(in Chinese with English abstract).
Zhang Wenhua.2013.Rock classification recognition of coal mine roadway bolt supporting based on fuzzy mathematical method[J].Coal Technology,32(6):74-76(in Chinese with English abstract).
Zhao Hongbo.2005.Recognition of collapse type of surrounding rock mass based on support vector machine[J].Rock and Soil Mechanics,26(2):235-238(in Chinese with English abstract).
Zhao Yanhui,Zhang Lewen,Qiu Daohong,Zhong Xiaojie.2011.Tunnel surrounding rock classification with fuzzy comprehensive assessment based on rough set[J].Sichuan Building Science,37(2):125-128(in Chinese with English abstract).
Zhou Shengquan,Wu Jiwen.2012.Tunnel surrounding rock stability classification based on artificial neural networks[J].Journal of Anhui University of Science and Technology(Natural Science),32(3):7-11(in Chinese with English abstract).
Zhu Yiding,Ma Wentao.2006.Method of supportvector machines for classifying surrounding rocks of gateways[J].Journal of Mining&Safety Engineering,23(3):362-365(in Chinese with English abstract).
邓声君,陆晓敏,黄晓阳.2013.地下洞室围岩稳定性分析方法简述[J].地质与勘探,49(3):541-547.
傅文杰,洪金益,朱谷昌.2006.基于光谱相似尺度的支持向量机蚀变信息提取[J].地质与勘探,42(2):69-73.
郭超,宋卫华,魏威.2014.基于网格搜索-支持向量机的采场顶板稳定性预测[J].中国安全科学学报,24(8):31-36.
郭瑞,徐广璐.2013.基于信息融合与GA-SVM的煤矿瓦斯浓度多传感器预测模型研究[J].中国安全科学学报,23(9):33-38.
蒋金泉,冯增强,韩继胜.1999.跨采巷道围岩结构稳定性分类与支护参数决策[J].岩石力学与工程学报,18(1):81-85.
刘碧洪,刘鹤.2016.内蒙古干珠尔善德银铅锌矿床的短波红外光谱研究[J].地质与勘探,52(4):703-711.
刘俊娥,杨晓帆,郭章林.2013.基于FIG-SVM的煤矿瓦斯浓度预测[J].中国安全科学学报,23(2):80-84.
马方彬,杜杨松,李大鹏,涂伟,王开虎,白玉.2016.西天山智博铁矿地球化学特征及地质意义[J].地质与勘探,52(1):0001-0013.
宁云才,邢中光.1997.煤矿矿区回采巷道围岩稳定性分类的灰色Fuzy聚类分析及应用[J].系统工程理论与实践,17(8):115-124.
牛文林,李天斌,熊国斌,张广洋.2011.基于支持向量机的围岩定性智能分级研究[J].工程地质学报,19(1):88-92.
邱道宏,李术才,薛翊国,田昊,闫茂旺.2014.基于数字钻进技术和量子遗传-径向基函数神经网络的围岩类别超前识别技术研究[J].岩土力学,35(7):2013-2018.
邱道宏,李术才,张乐文,薛翊国,苏茂鑫.2010.基于TSP203系统和GA-SVM的围岩超前分类预测[J].岩石力学与工程学报,29(S1):3221-3226.
王凯,杨帆,李峰,坚润堂,孙玉海,杨涛,李芙蓉.2016.铜矿床热液蚀变及脉体系统研究[J].地质与勘探,52(3):0417-0428.
王洪德,曹英浩.2013.基于改进变权物元可拓模型的围岩稳定性评价[J].中国安全科学学报,23(8):23-29.
张国云.2006.支持向量机算法及其应用研究[D].长沙:湖南大学:1-33.
张建明,曾建武,谢磊,王树青.2007.基于粗糙集的支持向量机故障诊断[J].清华大学学报(自然科学版),47(S2):1774-1777.
张文华.2013.基于模糊数学法的煤矿巷道锚杆支护围岩分类识别[J].煤炭技术,32(6):74-76.
赵洪波.2005.围岩破坏模式识别的支持向量机研究[J].岩土力学,26(2):235-238.
赵彦辉,张乐文,邱道宏,仲晓杰.2011.基于粗糙集理论的隧道围岩模糊综合评判[J].四川建筑科学研究,37(2):125-128.
周盛全,吴基文.2012.基于人工神经网络的隧道围岩稳定性分类[J].安徽理工大学学报(自然科学版),32(3):7-11.
朱一丁,马文涛.2006.回采巷道围岩分类的支持向量机方法[J].采矿与安全工程学报,23(3):362-365.
Fu Wenjie,Hong Jinyi,Zhu Guchang.2006.Extracting altered and mineralized rock information from remote sensing image based on support vector machine spectral similarity scale[J].Geology and Exploration,42(2):69-73(in Chinese with English abstract).
Guo Chao,Song Weihua,Wei Wei.2014.Slope roof stability prediction based on both SVM and grid-search method[J].China Safety Science Journal,24(8):31-36.
Guo Rui,Xu Guanglu.2013.Research on coal mine gas concentration Multi-sensor prediction model based on information fusion and GA-SVM[J].China Safety Science Journal,23(9):33-38(in Chinese with English abstract).
Jiang Jinquan,Feng Zengqiang,Han Jisheng.1999.Classification of structural stability of surrounding rocks of roadway affected by overhead mining and decision making of support parameters[J].Chinese Journal of Rock Mechanics and Engineering,18(1):81-85(in Chinese with English abstract).
Liu Bihong,Liu He.2016.Short-wave infrared spectroscopy study on wall rock alteration of the Gan-zhuershande silver-lead-zinc deposit in Inner Mongolia[J].Geology and Exploration,52(4):703-711(in Chinese with English abstract).
Liu Jun'e,Yang Xiaofan,Guo Zhanglin.2013.Prediction of coal mine gas concentration based on FIG-SVM[J].China safety Science Journal,23(2):80-84(in Chinese with English abstract).
Ma Fangbin,Du Yangsong,Li Dapeng,Tu Wei,Wang Kaihu,Bai Yu.2016.Geochemical characteristics of the Zhibo iron deposit in West Tianshan of China and geological implications[J].Geology and Exploration,52(1):01-13(in Chinese with English abstract).
Ning Yuncai,Xing Zhongguang.1997.Grey fuzzy assemblage analysis and its application in rock stability classification of gateway in mine[J].Systems Engineering Theory&Practice,17(8):115-124.
Niu Wenlin,Li Tianbin,Xiong Guobin,Zhang Guangyang.2011.Support vector machines based intelligent rock mass classification method[J].Journal of Engineering Geology,19(1):88-92(in Chinese with English abstract).
Qiu Daohong,Li Shucai,Xue Yiguo,Tian Hao,Yan Maowang.2014.Advanced prediction of surrounding rock classification based on digital drilling technology and QGA-RBF neural network[J].Rock and Soil Mechanics,35(7):2013-2018(in Chinese with English abstract).
Qiu Daohong,Li Shucai,Zhang Wenle,Xue Yiguo,Su Maoxin.2010.Prediction of surrounding rock classification in advance based on TSP203 system and GA-SVM[J].Chinese Journal of Rock Mechanics and Engineering,29(S1):3221-3226(in Chinese with English abstract).
Steve R Gunn.1998.Support Vector Machines for classification and regression[R].University of Southampton:23-65.
Vapnik V N.1995.The nature of statistical learning theory[M].New York:Springer-Verlag:23-105.
Wang Hongde,Cao Yinghao.2013.Evaluation of surrounding rock stability based on improved matter-element extension model with variable weight[J].China Safety Science Journal,23(8):23-29(in Chinese with English abstract).
Wang Kai,Yang Fan,Li Feng,Jian Runtang,Sun Yuhai,Yang Tao,Li Furong.2016.Study on the hydrothermal alteration and vein systems of the Pulang porphyry copper deposit in Yunnan Province[J].Geology and Exploration,52(3):417-428(in Chinese with English abstract).
Zhang Guoyun.2006.Research on support vector machine algorithm and its application[D].Changsha:Hunan University:1-33(in Chinese with English abstract).
Zhang Jianming,Zeng Jianwu,Xie Lei,Wang Shuqing.2007.Fault diagnosis based on RS and SVM[J].Journal of Tsinghua University(Science and Technology),47(S2):1774-1777(in Chinese with English abstract).
Zhang Wenhua.2013.Rock classification recognition of coal mine roadway bolt supporting based on fuzzy mathematical method[J].Coal Technology,32(6):74-76(in Chinese with English abstract).
Zhao Hongbo.2005.Recognition of collapse type of surrounding rock mass based on support vector machine[J].Rock and Soil Mechanics,26(2):235-238(in Chinese with English abstract).
Zhao Yanhui,Zhang Lewen,Qiu Daohong,Zhong Xiaojie.2011.Tunnel surrounding rock classification with fuzzy comprehensive assessment based on rough set[J].Sichuan Building Science,37(2):125-128(in Chinese with English abstract).
Zhou Shengquan,Wu Jiwen.2012.Tunnel surrounding rock stability classification based on artificial neural networks[J].Journal of Anhui University of Science and Technology(Natural Science),32(3):7-11(in Chinese with English abstract).
Zhu Yiding,Ma Wentao.2006.Method of supportvector machines for classifying surrounding rocks of gateways[J].Journal of Mining&Safety Engineering,23(3):362-365(in Chinese with English abstract).
邓声君,陆晓敏,黄晓阳.2013.地下洞室围岩稳定性分析方法简述[J].地质与勘探,49(3):541-547.
傅文杰,洪金益,朱谷昌.2006.基于光谱相似尺度的支持向量机蚀变信息提取[J].地质与勘探,42(2):69-73.
郭超,宋卫华,魏威.2014.基于网格搜索-支持向量机的采场顶板稳定性预测[J].中国安全科学学报,24(8):31-36.
郭瑞,徐广璐.2013.基于信息融合与GA-SVM的煤矿瓦斯浓度多传感器预测模型研究[J].中国安全科学学报,23(9):33-38.
蒋金泉,冯增强,韩继胜.1999.跨采巷道围岩结构稳定性分类与支护参数决策[J].岩石力学与工程学报,18(1):81-85.
刘碧洪,刘鹤.2016.内蒙古干珠尔善德银铅锌矿床的短波红外光谱研究[J].地质与勘探,52(4):703-711.
刘俊娥,杨晓帆,郭章林.2013.基于FIG-SVM的煤矿瓦斯浓度预测[J].中国安全科学学报,23(2):80-84.
马方彬,杜杨松,李大鹏,涂伟,王开虎,白玉.2016.西天山智博铁矿地球化学特征及地质意义[J].地质与勘探,52(1):0001-0013.
宁云才,邢中光.1997.煤矿矿区回采巷道围岩稳定性分类的灰色Fuzy聚类分析及应用[J].系统工程理论与实践,17(8):115-124.
牛文林,李天斌,熊国斌,张广洋.2011.基于支持向量机的围岩定性智能分级研究[J].工程地质学报,19(1):88-92.
邱道宏,李术才,薛翊国,田昊,闫茂旺.2014.基于数字钻进技术和量子遗传-径向基函数神经网络的围岩类别超前识别技术研究[J].岩土力学,35(7):2013-2018.
邱道宏,李术才,张乐文,薛翊国,苏茂鑫.2010.基于TSP203系统和GA-SVM的围岩超前分类预测[J].岩石力学与工程学报,29(S1):3221-3226.
王凯,杨帆,李峰,坚润堂,孙玉海,杨涛,李芙蓉.2016.铜矿床热液蚀变及脉体系统研究[J].地质与勘探,52(3):0417-0428.
王洪德,曹英浩.2013.基于改进变权物元可拓模型的围岩稳定性评价[J].中国安全科学学报,23(8):23-29.
张国云.2006.支持向量机算法及其应用研究[D].长沙:湖南大学:1-33.
张建明,曾建武,谢磊,王树青.2007.基于粗糙集的支持向量机故障诊断[J].清华大学学报(自然科学版),47(S2):1774-1777.
张文华.2013.基于模糊数学法的煤矿巷道锚杆支护围岩分类识别[J].煤炭技术,32(6):74-76.
赵洪波.2005.围岩破坏模式识别的支持向量机研究[J].岩土力学,26(2):235-238.
赵彦辉,张乐文,邱道宏,仲晓杰.2011.基于粗糙集理论的隧道围岩模糊综合评判[J].四川建筑科学研究,37(2):125-128.
周盛全,吴基文.2012.基于人工神经网络的隧道围岩稳定性分类[J].安徽理工大学学报(自然科学版),32(3):7-11.
朱一丁,马文涛.2006.回采巷道围岩分类的支持向量机方法[J].采矿与安全工程学报,23(3):362-365.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |