最小二乘支持向量机-粒子群算法在地下厂房围岩参数反分析中的应用
|
摘要
为准确确定地下厂房围岩的弹性模量、泊松比、黏聚力、内摩擦角、侧压力系数等参数,以正交设计、最小二乘支持向量机和粒子群算法等现代数学方法为基本手段,建立基于位移增量的围岩参数反分析方法。以CCS水电站大型地下厂房为研究背景,通过工程地质条件研究选取8#机组剖面作为分析对象,采用二维弹塑性有限元方法建立地质结构分析模型。以地下厂房洞室群分层开挖多点位移计实测位移增量为依据,对CCS水电站地下厂房区域围岩力学特性及地应力场特征进行反分析。研究结果表明:主厂房第Ⅵ层与第Ⅰ层开挖和主变室第4层与第1层开挖所产生的位移增量计算值与多点位移计实测值吻合较好,最大相对误差小于10%,说明采用最小二乘支持向量机和粒子群算法相结合的反分析方法在工程上是可行的,且效果较为显著。
In order to accurately determine the surrounding rock parameters of underground powerhouse, i. e.deformation modulus,Poisson' s ratio,cohesion,angle of internal friction and lateral pressure coefficient,the back analysis method for surrounding rock parameters based on displacement increment is established by modern mathematical methods like orthogonal design,least squares support vector machine and particle swarm algorithm. According to engineering geological condition analysis,the cross-section of unit No. 8 of Coca-Codo Sinclair( CCS) Hydropower Station is selected as the study object,and the geological structural analysis model is established by 2 D elastic-plastic finite element method. The back analysis of mechanical characteristics of surrounding rock and geostress field of CCS Hydropower Station is carried out based on monitored displacement increments of layered excavation of underground powerhouse caverns. The study results show that the computation values of displacement increments caused by the excavation at layer Ⅵ and Ⅰ of main powerhouse and layer 4 and 1 of converter room coincide with that of the monitoring values,and the maximum relative error is less than 10%,which indicates that the back analysis method of least squares support vector machine and particle swarm algorithm is feasible and effective.
In order to accurately determine the surrounding rock parameters of underground powerhouse, i. e.deformation modulus,Poisson' s ratio,cohesion,angle of internal friction and lateral pressure coefficient,the back analysis method for surrounding rock parameters based on displacement increment is established by modern mathematical methods like orthogonal design,least squares support vector machine and particle swarm algorithm. According to engineering geological condition analysis,the cross-section of unit No. 8 of Coca-Codo Sinclair( CCS) Hydropower Station is selected as the study object,and the geological structural analysis model is established by 2 D elastic-plastic finite element method. The back analysis of mechanical characteristics of surrounding rock and geostress field of CCS Hydropower Station is carried out based on monitored displacement increments of layered excavation of underground powerhouse caverns. The study results show that the computation values of displacement increments caused by the excavation at layer Ⅵ and Ⅰ of main powerhouse and layer 4 and 1 of converter room coincide with that of the monitoring values,and the maximum relative error is less than 10%,which indicates that the back analysis method of least squares support vector machine and particle swarm algorithm is feasible and effective.
引文
[1]姚显春,李宁,陈莉静,等.拉西瓦水电站地下厂房洞室群分层开挖过程仿真反演分析[J].岩石力学与工程学报,2011,30(增刊1):3052.YAO Xianchun, LI Ning, CHEN Lijing, et al. Back analysis of surrounding rock stability based on excavation process of underground powerhouse at Laxiwa Hydropower Station[J]. Chinese Journal of Rock Mechanics and Engineering,2011,30(S1):3052.
[2]李金河,伍文锋,李建川.溪洛渡水电站超大型地下厂房洞室群岩体工程控制与监测[J].岩石力学与工程学报,2013,32(1):8.LI Jinhe, WU Wenfeng, LI Jianchuan. Control and monitoring of rock mass engineering of super large underground powerhouse cavern groups at Xiluodu Hydropower Station[J]. Chinese Journal of Rock Mechanics and Engineering,2013,32(1):8.
[3]闫静雅,张子新,黄宏伟.京珠高速公路温泉隧道的施工监测及位移反分析[J].公路交通科技,2005,22(8):65.YAN Jingya,ZHANG Zixin,HUANG Hongwei. Monitoring and back analysis of displacement of Jing-Zhu Expressway Wenquan Tunnel[J]. Journal of Highway and Transportation Research and Development,2005,22(8):65.
[4]李立新,王建党,李造鼎.神经网络模型在非线性位移反分析中的应用[J].岩土力学,1997,18(2):62.LI Lixin, WANG Jiandang, LI Zaoding. Application of neural network model in non-linear displacement back analysis[J]. Rock and Soil Mechanics,1997,18(2):62.
[5]贾超,刘宁,肖树芳.洞室岩体参数的位移正演反分析[J].岩土力学,2003,24(3):450.JIA Chao,LIU Ning,XIAO Shufang. Application of direct displacement inverse analysis to rockmass parameters of caverns[J]. Rock and Soil Mechanics,2003,24(3):450.
[6]王长虹,杨有海.弹性位移反分析法在乌鞘岭隧道工程中的应用[J].兰州交通大学学报(自然科学版),2005,24(6):24.WANG Changhong,YANG Youhai. Application of elastic displacement back analysis in Wushaoling Tunnel[J].Journal of Lanzhou Jiaotong University(Natural Sciences),2005,24(6):24.
[7]丁德馨,张志军,孙钧.弹塑性位移反分析的遗传算法研究[J].工程力学,2003,20(6):1.DING Dexin, ZHANG Zhijun, SUN Jun. The geneticalgorithm-based approach to back analysis of displacement parameters of elasto-plastic model for rock mass[J].Engineering Mechanics,2003,20(6):1.
[8]闻学,刘新荣,易立.神经网络反分析在柳山隧道中的应用[J].地下空间与工程学报,2009,5(5):1025.WEN Xue,LIU Xinrong,YI Li. Application of the ANN approach for back analysis in Liushan Tunnel[J]. Chinese Journal of Underground Space and Engineering, 2009,5(5):1025.
[9]刘英棨,张谢东,陈卫东,等.多位移反分析浅埋偏压隧道初期支护荷载分布研究[J].隧道建设,2016,36(7):832.LIU Yingqi, ZHANG Xiedong, CHEN Weidong, et al.Study of load distribution rules of primary support of shallowcoverd unsymmetrically pressured tunnel by using multidisplacement back analysis method[J]. Tunnel Construction,2016,36(7):832.
[10]江宗斌,姜谙男,胡雪峰,等.基于位移-应力多元信息的公路隧道智能反分析研究[J].现代隧道技术,2017,54(1):145.JIANG Zongbin, JIANG Annan, HU Xuefeng, et al.Displacement-stress based multi-information intelligent back analysis in highway tunnel[J]. Modern Tunnelling Technology,2017,54(1):145.
[11]张研,苏国韶,燕柳斌.隧洞围岩损失位移估计的智能优化反分析[J].岩土力学,2013,34(5):1383.ZHANG Yan,SU Guoshao,YAN Liubin. An intelligent optimization method of back analysis for loss displacement of surrounding rocks of tunnel[J]. Rock and Soil Mechanics,2013,34(5):1383.
[12]文建华,吴代华,陈军明,等.地下洞室黏弹性位移反分析模式分层运算[J].岩土力学,2010,31(3):967.WEN Jianhua, WU Daihua, CHEN Junming, et al.Parameter inversion of viscoelastic cavern displacements based on hierarchical pattern search[J]. Rock and Soil Mechanics,2010,31(3):967.
[13]邬凯,盛谦,梅松华,等. PSO-LSSVM模型在位移反分析中的应用[J].岩土力学,2009,30(4):1109.WU Kai,SHENG Qian,MEI Songhua,et al. A model of PSO-LSSVM and its application to displacement back analysis[J]. Rock and Soil Mechanics, 2009,30(4):1109.
[14]牛文林,李天斌,熊国斌,等.基于支持向量机的围岩定性智能分级[J].工程地质学报,2011,19(1):88.NIU Wenlin,LI Tianbin,XIONG Guobin,et al. Support vector machines based intelligent rock mass classification method[J]. Journal of Engineering Geology, 2011,19(1):88.
[15]李波,徐宝松,武金坤,等.基于最小二乘支持向量机的大坝力学参数反演[J].岩土工程学报,2008,30(11):1722.LI Bo,XU Baosong,WU Jinkun,et al. Back analysis of dam mechanical parameters based on least squares support vector machine[J]. Chinese Journal of Geotechnical Engineering,2008,30(11):1722.
[16]陆有忠,高永涛,吴顺川,等.基于进化支持向量机的岩土体位移反分析[J].辽宁工程技术大学学报,2006,25(3):381.LU Youzhong, GAO Yongtao, WU Shunchuan, et al.Inversion of displacement based on evolutionary support vector machine[J]. Journal of Liaoning Technical University,2006,25(3):381.
[17]何竹叶,任旭华,刘燕.基于FLAC3D和粒子群优化算法的初始地应力场反演[J].水电能源科学,2010,28(8):46.HE Zhuye,REN Xuhua,LIU Yan. Back analysis of initial ground stress based on FLAC3D and particle swarm optimization[J]. Water Resources and Power,2010,28(8):46.
[18]李晓龙,王复明,李晓楠.岩土工程弹塑性反分析的改进粒子群算法算法[J].采矿与安全工程学报,2009,26(1):50.LI Xiaolong, WANG Fuming, LI Xiaonan. Improved partical swarm optimization for elastoplastic back analysis in geotechnical engineering[J]. Journal of Mining&Safety Engineering,2009,26(1):50.
[19]杨继华,郭卫新,齐三红,等. CCS水电站地下厂房围岩分类方法研究[J].隧道建设,2014,34(7):623.YANG Jihua,GUO Weixin,QI Sanhong,et al. Study of classification methods of surrounding rock of underground powerhouse of CCS Hydropower Station[J]. Tunnel Construction,2014,34(7):623.
[20]董志宏,丁秀丽,卢波,等.大型地下洞室考虑开挖卸荷效应的位移反分析[J].岩土力学, 2008,29(6):1562.DONG Zhihong,DING Xiuli,LU Bo,et al. Displacement back analysis of rock mechanical parameters of large-scale underground powerhouse with unloading surrounding rockmass[J]. Rock and Soil Mechanics, 2008,29(6):1562.
[21]田华,肖明.地下厂房围岩参数场位移反分析[J].武汉大学学报(工学版),2007,40(2):38.TIAN Hua,XIAO Ming. Displacement back analysis of surrounding rocks for parameter-field of underground powerhouses[J]. Engineering Journal of Wuhan University,2007,40(2):38.
[2]李金河,伍文锋,李建川.溪洛渡水电站超大型地下厂房洞室群岩体工程控制与监测[J].岩石力学与工程学报,2013,32(1):8.LI Jinhe, WU Wenfeng, LI Jianchuan. Control and monitoring of rock mass engineering of super large underground powerhouse cavern groups at Xiluodu Hydropower Station[J]. Chinese Journal of Rock Mechanics and Engineering,2013,32(1):8.
[3]闫静雅,张子新,黄宏伟.京珠高速公路温泉隧道的施工监测及位移反分析[J].公路交通科技,2005,22(8):65.YAN Jingya,ZHANG Zixin,HUANG Hongwei. Monitoring and back analysis of displacement of Jing-Zhu Expressway Wenquan Tunnel[J]. Journal of Highway and Transportation Research and Development,2005,22(8):65.
[4]李立新,王建党,李造鼎.神经网络模型在非线性位移反分析中的应用[J].岩土力学,1997,18(2):62.LI Lixin, WANG Jiandang, LI Zaoding. Application of neural network model in non-linear displacement back analysis[J]. Rock and Soil Mechanics,1997,18(2):62.
[5]贾超,刘宁,肖树芳.洞室岩体参数的位移正演反分析[J].岩土力学,2003,24(3):450.JIA Chao,LIU Ning,XIAO Shufang. Application of direct displacement inverse analysis to rockmass parameters of caverns[J]. Rock and Soil Mechanics,2003,24(3):450.
[6]王长虹,杨有海.弹性位移反分析法在乌鞘岭隧道工程中的应用[J].兰州交通大学学报(自然科学版),2005,24(6):24.WANG Changhong,YANG Youhai. Application of elastic displacement back analysis in Wushaoling Tunnel[J].Journal of Lanzhou Jiaotong University(Natural Sciences),2005,24(6):24.
[7]丁德馨,张志军,孙钧.弹塑性位移反分析的遗传算法研究[J].工程力学,2003,20(6):1.DING Dexin, ZHANG Zhijun, SUN Jun. The geneticalgorithm-based approach to back analysis of displacement parameters of elasto-plastic model for rock mass[J].Engineering Mechanics,2003,20(6):1.
[8]闻学,刘新荣,易立.神经网络反分析在柳山隧道中的应用[J].地下空间与工程学报,2009,5(5):1025.WEN Xue,LIU Xinrong,YI Li. Application of the ANN approach for back analysis in Liushan Tunnel[J]. Chinese Journal of Underground Space and Engineering, 2009,5(5):1025.
[9]刘英棨,张谢东,陈卫东,等.多位移反分析浅埋偏压隧道初期支护荷载分布研究[J].隧道建设,2016,36(7):832.LIU Yingqi, ZHANG Xiedong, CHEN Weidong, et al.Study of load distribution rules of primary support of shallowcoverd unsymmetrically pressured tunnel by using multidisplacement back analysis method[J]. Tunnel Construction,2016,36(7):832.
[10]江宗斌,姜谙男,胡雪峰,等.基于位移-应力多元信息的公路隧道智能反分析研究[J].现代隧道技术,2017,54(1):145.JIANG Zongbin, JIANG Annan, HU Xuefeng, et al.Displacement-stress based multi-information intelligent back analysis in highway tunnel[J]. Modern Tunnelling Technology,2017,54(1):145.
[11]张研,苏国韶,燕柳斌.隧洞围岩损失位移估计的智能优化反分析[J].岩土力学,2013,34(5):1383.ZHANG Yan,SU Guoshao,YAN Liubin. An intelligent optimization method of back analysis for loss displacement of surrounding rocks of tunnel[J]. Rock and Soil Mechanics,2013,34(5):1383.
[12]文建华,吴代华,陈军明,等.地下洞室黏弹性位移反分析模式分层运算[J].岩土力学,2010,31(3):967.WEN Jianhua, WU Daihua, CHEN Junming, et al.Parameter inversion of viscoelastic cavern displacements based on hierarchical pattern search[J]. Rock and Soil Mechanics,2010,31(3):967.
[13]邬凯,盛谦,梅松华,等. PSO-LSSVM模型在位移反分析中的应用[J].岩土力学,2009,30(4):1109.WU Kai,SHENG Qian,MEI Songhua,et al. A model of PSO-LSSVM and its application to displacement back analysis[J]. Rock and Soil Mechanics, 2009,30(4):1109.
[14]牛文林,李天斌,熊国斌,等.基于支持向量机的围岩定性智能分级[J].工程地质学报,2011,19(1):88.NIU Wenlin,LI Tianbin,XIONG Guobin,et al. Support vector machines based intelligent rock mass classification method[J]. Journal of Engineering Geology, 2011,19(1):88.
[15]李波,徐宝松,武金坤,等.基于最小二乘支持向量机的大坝力学参数反演[J].岩土工程学报,2008,30(11):1722.LI Bo,XU Baosong,WU Jinkun,et al. Back analysis of dam mechanical parameters based on least squares support vector machine[J]. Chinese Journal of Geotechnical Engineering,2008,30(11):1722.
[16]陆有忠,高永涛,吴顺川,等.基于进化支持向量机的岩土体位移反分析[J].辽宁工程技术大学学报,2006,25(3):381.LU Youzhong, GAO Yongtao, WU Shunchuan, et al.Inversion of displacement based on evolutionary support vector machine[J]. Journal of Liaoning Technical University,2006,25(3):381.
[17]何竹叶,任旭华,刘燕.基于FLAC3D和粒子群优化算法的初始地应力场反演[J].水电能源科学,2010,28(8):46.HE Zhuye,REN Xuhua,LIU Yan. Back analysis of initial ground stress based on FLAC3D and particle swarm optimization[J]. Water Resources and Power,2010,28(8):46.
[18]李晓龙,王复明,李晓楠.岩土工程弹塑性反分析的改进粒子群算法算法[J].采矿与安全工程学报,2009,26(1):50.LI Xiaolong, WANG Fuming, LI Xiaonan. Improved partical swarm optimization for elastoplastic back analysis in geotechnical engineering[J]. Journal of Mining&Safety Engineering,2009,26(1):50.
[19]杨继华,郭卫新,齐三红,等. CCS水电站地下厂房围岩分类方法研究[J].隧道建设,2014,34(7):623.YANG Jihua,GUO Weixin,QI Sanhong,et al. Study of classification methods of surrounding rock of underground powerhouse of CCS Hydropower Station[J]. Tunnel Construction,2014,34(7):623.
[20]董志宏,丁秀丽,卢波,等.大型地下洞室考虑开挖卸荷效应的位移反分析[J].岩土力学, 2008,29(6):1562.DONG Zhihong,DING Xiuli,LU Bo,et al. Displacement back analysis of rock mechanical parameters of large-scale underground powerhouse with unloading surrounding rockmass[J]. Rock and Soil Mechanics, 2008,29(6):1562.
[21]田华,肖明.地下厂房围岩参数场位移反分析[J].武汉大学学报(工学版),2007,40(2):38.TIAN Hua,XIAO Ming. Displacement back analysis of surrounding rocks for parameter-field of underground powerhouses[J]. Engineering Journal of Wuhan University,2007,40(2):38.