分岔隧道设计施工优化与稳定性评价
|
摘要
分岔隧道是一类由大跨变断面段、连拱段和小间距段共同构成的组合隧道形式,其线形设计上的多断面、多尺度和施工工序及围岩荷载频繁转换的特点导致其开挖支护体系在复杂应力空间中表现为一个难度自增值系统。如何对该系统进行全局性、准确性的描述和决策,并提出一套能够服务于此类隧道开挖与支护方案优化的普适性方法是本文需要解决的核心问题。在此,本文以胶州湾海底隧道陆域段左线分岔隧道为工程背景,综合三维数值计算、仿生优化、核机器学习和突变理论等方法,提出分岔隧道洞室稳定性分析与全局智能优化的新方法。该方法首先将仿生优化算法与弹塑性数值计算相融合,完成工程区域围岩力学参数反演；其次,基于主元分析和位移增量基础信息分别建立多权重综合评价体系和洞室稳定性的突变判据,继而采用新的智能全局优化方法在开挖与支护方案各种组合的全局空间下搜索出最优施工方案,成功地解决了分岔隧道开挖与支护方案优化过程中的多目标决策和洞室稳定性评价问题。具体研究内容及成果如下：
1.核学习机方法及仿生优化算法研究
(1)作为第三代核机器代表的高斯过程具有小样本、概率推理、泛化性能好的优势,将其应用于边坡和隧道位移非线性时间序列的建模分析表明：高斯过程较人工神经元网络和支持向量机在网络训练精度和预测精度上都有显著提高。
(2)利用模拟退火算法兼具“上山性”和“下山性”的特性克服标准粒子群算法易陷入局部最优的缺陷,提出基于二者串行编程的混合优化算法—粒子群-模拟退火算法。其函数测试结果表明：该算法能够适用于高非线性问题的优化求解。
(3)为克服传统共轭梯度法在核参数优化过程中的不足,实现混合算法与高斯过程的程序耦合。针对典型滑坡变形预测问题,与基于遗传算法进化的高斯过程等算法进行了对比研究,前者在程序简易性和测试效果两方面均有较大优势。
2.基于计算智能方法的分岔段开挖与支护方案优化研究
(1)采用FLAC内置FISH语言,构建了粒子群算法与FLAC2D耦合的进化有限差分方法—粒子群-FLAC2D,继而提出了围岩物理力学参数的位移智能反演方法及实现步骤。工程实践表明：该方法在计算效率和优化精度上都具有较大优势。
(2)利用主元分析方法解决多目标优化过程中优化指标的权重分配问题,在保存评价指标基础信息的前提下既可达到降维、简化评价体系的目的,又可以避免权重确定的人为因素；同时,首次提出将基于位移增量步的突变判据作为洞室稳定性评价新标准和多目标决策优化过程的约束条件。
(3)针对洞室开挖与支护全局优化问题,为避免大量三维数值计算带来的成本消耗,提出了开挖与支护方案的全局智能优化方法：粒子群-模拟退火-高斯过程-数值计算方法。该方法融合了计算智能全局并行搜索和学习机黑箱推理的特性,能高效率、高精度的处理多目标决策问题。同时,在工程方案决策过程中避免了于几种预选方案中择优的不合理性和局限性,为解决此类工程决策问题提供一种新的有效途径。
3.变速段的线形优化及断面轮廓设计研究
首先结合基于位移增量信息的突变判据和传统位移、应力指标分析,给出变速段线路过渡方案应以台阶式为最佳过渡方式的结论；其次,考虑匝道及主隧的不同行车速度、发动机制动加速度等因素,提出了线路汇流和分流情况下修正了的变速段长度计算公式和台阶过渡方式下的线路平面线形设计公式；最后,基于作图法原理,给出了变速段各台阶断面的空间布局设计方法及其轮廓设计公式。
4.胶州湾海底隧道陆域分岔隧道设计施工优化研究
基于进化有限差分方法及其相应的智能位移反演步骤,成功地实现了工程区域围岩力学参数的位移智能反演；接着,集成全局智能优化方法(程序)和ANSYS、TECPLOT等常用优秀前后处理软件技术完成了分岔段的开挖与支护方案优化和洞室稳定性分析,在施工技术许可的前提下提出了合理的支护设计参数和施工方法,继而根据线形优化设计方法确定出变速段的断面尺度及其空间布局。
Forked tunnel is a kind of combining from tunnel that consists of large-arch, multi-arch, neighborhood and transition tunnel. The special structure type and conversion of stress and operation sequence frequently leads to the fact that its excavation and support system is an accumulative difficulty system in complex stress space in tunnel construction. This paper concentrates on how to bring up a global and accuracy description and assessment on the design and construction scheme and further get a universal method. For this purpose, under the background of construction of kiaochow bay subsea tunnel, stability analysis and intelligent global optimization method for forked tunnel is proposed by integrating different theory and technology, such as 3D numerical simulation, bionic optimization, kernel machine learning and catastrophe theory. Specific steps are as follows:Bionic optimization algorithm firstly couples with FLAC for displacement back-analysis of mechanical parameters of surrounding rock. Moreover, PCA and catastrophe criterion are used to cope with weight distribution and stability evaluation respectively. Finally, the global optimum excavation sequence and support parameters are obtained by the new intelligent global optimization method. Thus, the problem mentioned above could be solved successfully based on the new method. Detailed research results include the followings:
1. Study on the kernel machine learning and bionic optimization algorithm
(1) Gaussian process (GP), the third generation kernel machine, has advantages of small samples, probabilistic reasoning and good generalization capability. The analysis results of displacement nonlinear time series of tunnel and slope indicate it notably improves on the accuracy and efficiency of prediction compared with ANN and SVM.
(2) Simulated annealing (SA) with characteristics of'uphill'and'downhill' simultaneously is introduced to improve the standard particle swarm optimization (PSO) for modifying the population diversity and then the new coupling algorithm PSO-SA is proposed. Its application results of function test state clearly that the algorithm is applicable to solve the highly nonlinear problems.
(3) For overcoming the shortcomings of conjugate gradient during the process of optimizing the kernel function of machine learning, the PSO-SA instead couples with GP for forming the new PSO-SA-GP algorithm. Compared with the GA-GP algorithm, the new algorithm demonstrates advantages in two areas, namely simplicity and efficiency of code, aiming at predicting the displacement of typical landslide.
2. Study on excavation and support optimization based on computation intelligence
(1) PSO is used to couple with FLAC2D in order to form the new evolutional finite difference method. Then it is adopted to cope with the back-analysis of mechanical parameters of surrounding rock with the advantages of computational efficiency and optimization accuracy.
(2) PCA and catastrophe criterion are used to handle the weight distribution and stability evaluation during the process of optimization on excavation and support scheme respectively. The former can achieve the goal of simplifying the evaluation system and dimension reduction and the latter can be served as a new evaluation index and constraints for multi-objective decision making.
(3) Aiming at the global optimization of excavation and support scheme, a new PSO-SA-GPR-FLAC3D method with global parallel search and black-box reasoning is put forward for reducing the cost of large-scale 3D numerical simulation. It can handle the multi-objective decision making well and used as a new way for similar engineering.
3. Study on line-shape optimization of transition section and contour design of cross-section
Firstly, the stepped layout is decided as optimum transition mode based on catastrophe criterion and traditional analysis indexes. Secondly, considering the different speed between main tunnel and ramp tunnel new modified formulas for the lengths of transition section and horizontal line-shape are proposed. Finally, the spatial layout and contour design method of stepped cross-section is got by mapping principle.
4. Study on the optimization of design and construction of forked section of kiaochow bay subsea tunnel
Mechanical parameters of surrounding rock in tunnel site are obtained by PSO-FLAC2D. Then the optimization of excavation and support scheme and stability of tunnels are done by the integrated global intelligent method including the AI, ANSYS and TECPLOT etc. Finally, reasonable supporting parameters, construction sequence, section scale and its spatial layout are provided for builders.
1.核学习机方法及仿生优化算法研究
(1)作为第三代核机器代表的高斯过程具有小样本、概率推理、泛化性能好的优势,将其应用于边坡和隧道位移非线性时间序列的建模分析表明：高斯过程较人工神经元网络和支持向量机在网络训练精度和预测精度上都有显著提高。
(2)利用模拟退火算法兼具“上山性”和“下山性”的特性克服标准粒子群算法易陷入局部最优的缺陷,提出基于二者串行编程的混合优化算法—粒子群-模拟退火算法。其函数测试结果表明：该算法能够适用于高非线性问题的优化求解。
(3)为克服传统共轭梯度法在核参数优化过程中的不足,实现混合算法与高斯过程的程序耦合。针对典型滑坡变形预测问题,与基于遗传算法进化的高斯过程等算法进行了对比研究,前者在程序简易性和测试效果两方面均有较大优势。
2.基于计算智能方法的分岔段开挖与支护方案优化研究
(1)采用FLAC内置FISH语言,构建了粒子群算法与FLAC2D耦合的进化有限差分方法—粒子群-FLAC2D,继而提出了围岩物理力学参数的位移智能反演方法及实现步骤。工程实践表明：该方法在计算效率和优化精度上都具有较大优势。
(2)利用主元分析方法解决多目标优化过程中优化指标的权重分配问题,在保存评价指标基础信息的前提下既可达到降维、简化评价体系的目的,又可以避免权重确定的人为因素；同时,首次提出将基于位移增量步的突变判据作为洞室稳定性评价新标准和多目标决策优化过程的约束条件。
(3)针对洞室开挖与支护全局优化问题,为避免大量三维数值计算带来的成本消耗,提出了开挖与支护方案的全局智能优化方法：粒子群-模拟退火-高斯过程-数值计算方法。该方法融合了计算智能全局并行搜索和学习机黑箱推理的特性,能高效率、高精度的处理多目标决策问题。同时,在工程方案决策过程中避免了于几种预选方案中择优的不合理性和局限性,为解决此类工程决策问题提供一种新的有效途径。
3.变速段的线形优化及断面轮廓设计研究
首先结合基于位移增量信息的突变判据和传统位移、应力指标分析,给出变速段线路过渡方案应以台阶式为最佳过渡方式的结论；其次,考虑匝道及主隧的不同行车速度、发动机制动加速度等因素,提出了线路汇流和分流情况下修正了的变速段长度计算公式和台阶过渡方式下的线路平面线形设计公式；最后,基于作图法原理,给出了变速段各台阶断面的空间布局设计方法及其轮廓设计公式。
4.胶州湾海底隧道陆域分岔隧道设计施工优化研究
基于进化有限差分方法及其相应的智能位移反演步骤,成功地实现了工程区域围岩力学参数的位移智能反演；接着,集成全局智能优化方法(程序)和ANSYS、TECPLOT等常用优秀前后处理软件技术完成了分岔段的开挖与支护方案优化和洞室稳定性分析,在施工技术许可的前提下提出了合理的支护设计参数和施工方法,继而根据线形优化设计方法确定出变速段的断面尺度及其空间布局。
Forked tunnel is a kind of combining from tunnel that consists of large-arch, multi-arch, neighborhood and transition tunnel. The special structure type and conversion of stress and operation sequence frequently leads to the fact that its excavation and support system is an accumulative difficulty system in complex stress space in tunnel construction. This paper concentrates on how to bring up a global and accuracy description and assessment on the design and construction scheme and further get a universal method. For this purpose, under the background of construction of kiaochow bay subsea tunnel, stability analysis and intelligent global optimization method for forked tunnel is proposed by integrating different theory and technology, such as 3D numerical simulation, bionic optimization, kernel machine learning and catastrophe theory. Specific steps are as follows:Bionic optimization algorithm firstly couples with FLAC for displacement back-analysis of mechanical parameters of surrounding rock. Moreover, PCA and catastrophe criterion are used to cope with weight distribution and stability evaluation respectively. Finally, the global optimum excavation sequence and support parameters are obtained by the new intelligent global optimization method. Thus, the problem mentioned above could be solved successfully based on the new method. Detailed research results include the followings:
1. Study on the kernel machine learning and bionic optimization algorithm
(1) Gaussian process (GP), the third generation kernel machine, has advantages of small samples, probabilistic reasoning and good generalization capability. The analysis results of displacement nonlinear time series of tunnel and slope indicate it notably improves on the accuracy and efficiency of prediction compared with ANN and SVM.
(2) Simulated annealing (SA) with characteristics of'uphill'and'downhill' simultaneously is introduced to improve the standard particle swarm optimization (PSO) for modifying the population diversity and then the new coupling algorithm PSO-SA is proposed. Its application results of function test state clearly that the algorithm is applicable to solve the highly nonlinear problems.
(3) For overcoming the shortcomings of conjugate gradient during the process of optimizing the kernel function of machine learning, the PSO-SA instead couples with GP for forming the new PSO-SA-GP algorithm. Compared with the GA-GP algorithm, the new algorithm demonstrates advantages in two areas, namely simplicity and efficiency of code, aiming at predicting the displacement of typical landslide.
2. Study on excavation and support optimization based on computation intelligence
(1) PSO is used to couple with FLAC2D in order to form the new evolutional finite difference method. Then it is adopted to cope with the back-analysis of mechanical parameters of surrounding rock with the advantages of computational efficiency and optimization accuracy.
(2) PCA and catastrophe criterion are used to handle the weight distribution and stability evaluation during the process of optimization on excavation and support scheme respectively. The former can achieve the goal of simplifying the evaluation system and dimension reduction and the latter can be served as a new evaluation index and constraints for multi-objective decision making.
(3) Aiming at the global optimization of excavation and support scheme, a new PSO-SA-GPR-FLAC3D method with global parallel search and black-box reasoning is put forward for reducing the cost of large-scale 3D numerical simulation. It can handle the multi-objective decision making well and used as a new way for similar engineering.
3. Study on line-shape optimization of transition section and contour design of cross-section
Firstly, the stepped layout is decided as optimum transition mode based on catastrophe criterion and traditional analysis indexes. Secondly, considering the different speed between main tunnel and ramp tunnel new modified formulas for the lengths of transition section and horizontal line-shape are proposed. Finally, the spatial layout and contour design method of stepped cross-section is got by mapping principle.
4. Study on the optimization of design and construction of forked section of kiaochow bay subsea tunnel
Mechanical parameters of surrounding rock in tunnel site are obtained by PSO-FLAC2D. Then the optimization of excavation and support scheme and stability of tunnels are done by the integrated global intelligent method including the AI, ANSYS and TECPLOT etc. Finally, reasonable supporting parameters, construction sequence, section scale and its spatial layout are provided for builders.
引文
[1]王汉鹏.分岔式隧道设计施工的关键技术研究[D].山东大学,2007.
[2]中铁隧道勘察设计院有限公司.青岛胶州湾海底隧道设计说明[R].中铁隧道勘察设计院,2009.
[3]重庆交通科研设计院.万石山隧道与既有钟鼓山隧道立体交叉设计说明[R].重庆交通科研设计院,2005.
[4]吴波,刘维宁,高波等.地铁分岔隧道施工性态的三维数值模拟与分析[J].岩石力学与工程学报,2004,23(15)：3081～3086.
[5]刘洪伟.三线“Y”字型喇叭口隧道施工方法及转换研究[J].西部探矿工程,2001,21：180～182.
[6]重庆交通科学研究院.公路隧道设计规范(JTG D70-2004)[S].北京：人民交通出版社,2004.
[7]中交第一公路勘察设计研究院.公路路线设计(JTG D20-2006)[S].北京：人民交通出版社,2006.
[8]Kavanagh K.T., Clough R.W. Finite element application in the characterization of elastic solids[J]. Int J Solids structure,1972,7:11-23.
[9]Kristen H.A.D. Deternination of rock mass elastic moduli by back anlysis of deformation measurement[A]. In Proc Symp on Expiration for Rock Eng[C]. Johannesburg,1976, 1154-1160.
[10]Wang Zhiyin The back estimation of equivalent release load and support force by BEM[A]. In Proc 3rd Int Conf on Underground Spaces and Earth Sheltered Buildings[C]. Shanghai:TongJi University Press,1988,789-792.
[11]Sotirios S. Vardakos.Marte S. Gutierrez, Nick R. Barton. Back-analysis of Shimizu Tunnel No.3 by distinct element modeling[J]. Tunnelling and Underground Space Technology, 2007,22:401-413.
[12]Kovari K. et al. Integrated measuring technique for rock pressure determination[A]. In Proc Int Conf on Field Measurements in Rock Mechanics[C]. Zurich,1977,1:533-538.
[13]Sakurai S. Takeuchi K., Back analysis of measured displacement of tunnel[J]. Rock Mech and Rock Eng,1983,16(3):173-180.
[14]Gioda G. Maier G. Direct search solution of an inverse problem in elasto-plasticity identification of cohesion friction angle and in-situ stress by pressure tunnel tests[J]. Int J Num Methods in Eng,1980,15:1823-1834.
[15]Gioda G. Pandolfi A., Cividini A. A comparative evaluation of some back analysis algorithms and their application to in-situ load tests[A]. In Proc 2nd Int Symp on Field Measurement in Geom,1987,1131-1144.
[16]Arai R. An inverse problem approach to the prediction of Multi-dimensional consolidation behaviorfJ]. Soil and Foundations.1984,24(1):95-108.
[17]杨志法,刘竹毕.位移反分析法在地下工程设计中的初步应用[J].地下工程,1981(2)：20～24.
[18]杨林德等.初始地应力位移反分析的有限单元法[J].同济大学学报,1985(4)：15～20.
[19]王芝银.地下工程围岩粘弹塑性参数反分析[J].水利学报,1990,(9)：11～16.
[20]Wang Zhiyin, Li Yunpeng. Back analysis of measured rheologic displacements of underground opening.[A] In Proc Int Symp on Underground Eng[C]. New Delhi,1988, 181-186.
[21]刘怀恒.地下工程位移反分析原理应用及其发展[J].西安矿业学院学报,1988,8(3)：1～10.
[22]李云鹏,王芝银.粘弹性位移反分析的边界元法[J].西安矿业学院学报,1989,9(1)：17～24.
[23]Hisatake M. Three dimensional back analysis for tunnels[A]. In Proc Int Symp on ECRF[C]. Beijing:Science Press,1986,791-797.
[24]杨林德,朱合华.地层三维粘弹性反演分析[J].岩土工程学报,1991(6)：18～26.
[25]王芝银.空间轴对称蠕变位移反分析[A].第二届全国岩石力学数值计算与模型实验学术研讨会论文集[c].上海：同济大学出版社,1990,751～756.
[26]Gens A. Back analysis using Prior information-application to the staged excavation of a cavern in Rock[J]. Num Meth in Geomech, Innsbruck,1988,2009-2016.
[27]袁勇.围岩弹塑性参数反算的极大似然法[J].工程勘察,1991(5)：31-34.
[28]冯夏庭,张志强,杨成祥等.位移反分析的进化神经元网络方法研究[J].岩石力学与工程学报,1999,18(5)：529～533.
[29]戴荣,李忠全.三维地应力场BP反分析的改进[J].岩石力学与工程学报,2005,24(1)：83～88.
[30]刘开云.隧道工程信息化设计与智能分析方法研究[D].北京交通大学,2005.
[31]Gnirk P. F., Fossum A. F. On the formulation of stability and design of design criteria for compressed air energy storage in hard rock caverns[A]. In Proceedings of thelntersociety Energy Conversion Engineering Conference[C]. Am Chem Soc:1979,429-440.
[32]Miller, Stephen A., Gardner et al. Long-term stability of bryan mound solution caerns for LPG storge, with worst-case scenario[A]. In Pro Symp Solution Mining of Salts and Brines[C]. New York:1985,71-80.
[33]俞裕泰,黄赛超.坚硬而不完整岩体中地下洞室的分期开挖[J].地下工程,1984,11：31～35.
[34]莫海鸿,杨林德,鲍德波.复杂地质条件下地下厂房围岩稳定性分析[A].第六次全国岩石力学与工程学术大会会议论文集[c].北京：中国科学技术出版社,2000.
[35]史红光.二滩水电站地下厂房围岩稳定性因素评价[J]_水电站设计,1999,15(2)：75～78.
[36]张玉祥,包四根.复杂地质体中地下洞室的施工优化与稳定性评价[J].岩石力学与工程学报,2000,19(6)：722～725.
[37]陈帅宇,周围垣,杨强等.三维快速拉格朗日法进行水布垭地下厂房的稳定性分析[J].岩石力学与工程学报,2003,22(7)：1047～1053.
[38]朱维中,孙爱花,王文涛等.大型洞室群高边墙位移预测和围岩稳定性判别方法[J].岩石力学与工程学报,2007,26(9)：1729～1736.
[39]李术才,王汉鹏,郑学芬.分岔隧道稳定性分析及施工优化研究[J].岩石力学与工程学报,2008,27(3)：447～457.
[40]付成华,陈胜宏.基于突变理论的地下工程洞室围岩失稳判据研究[J].岩土力学,2008,29(1)：167～172.
[41]朱维中,王平.动态规划原理在洞室群施工力学中的应用[J].岩石力学与工程学报,1992,11(4)：323～331.
[42]肖明.地下洞室施工开挖三维动态过程数值模拟分析[J].岩士工程学报,2000,22(4)：421-425.
[43]朱维中,李术才,程峰.能量耗散模型在大型地下洞群施工顺序优化分析中的应用[J].岩土工程学报,2001,23(3)：333～336.
[44]姜谙男.大型洞室群开挖与加固方案反馈优化分析集成智能方法研究[D].东北大学,2004.
[45]苏国韶.高地应力下大型地下洞室群稳定性分析与智能优化研究[D].中科研武汉岩土力学所,2006.
[46]朱维中,何满潮.复杂条件下围岩稳定性与岩体动态施工力学[M].北京：科学出版社,1995
[47]李术才,朱维中.小浪底地下洞室群施工顺序优化分析[J].煤炭学报,1996,21(4)：393～398.
[48]朱万成,唐春安.基于正交试验原理和锚喷参数设计系统及其应用[J].岩土力学,1999,20(2)：87～91.
[49]朱万成,李晓.地下工程中的正交有限元分析方法及其应用[J].工程地质学报,1999,7(4)：337～347.
[50]朱万成,李晓.锚喷参数的回归正交有限元试验分析及其应用实例[J].岩石力学与工程学报,1999,18(3)：283～286.
[51]邓健,古德生,李夕兵.无间柱连续采矿采场参数的多指标正交有限元设计[J].中南工业大学学报,1999,30(5)：445～448.
[52]肖专文,张其志,赵文等.遗传算法与神经网络协调求解采矿工程中的优化问题[J].中国矿业,1998,7(1)：78～82.
[53]安红刚,冯夏庭.大型洞室群稳定性与优化的进化有限元方法研究[J].岩土力学,2001,22(4)：373～377.
[54]高玮,郑颖人.蚁群算法及其在硐群施工优化中的应用[J].2002,21(4)：471～474.
[55]赵洪波.非线性岩土力学行为的支持向量机研究[D].中科院武汉岩土力学所,2003.
[56]李兴璜.西安-安康铁路的隧道建设和进步技术[J].中国铁路,1999,12：1-5
[57]何川.公路双连拱隧道[M].
[58]铁路部第二勘测设计院.铁路隧道设计规范(TB10003-2005)[S].北京：中国铁道出版社,2005.
[59]交通部第二公路勘察设计院.公路隧道勘测规程(JTJ063-85)[S].北京：人民交通出版社,1985.
[60]秦峰.吴存兴.小净距隧道开挖方法浅论[J].现代隧道技术,2003,40(6)：39～42.
[61]陈文辉,秦峰,陈贵华.小净距隧道连拱隧道普通式隧道造价对比分析[J].公路交通技术,2005,6：120～122.
[62]刘伟.小净距公路净距优化研究[D].同济大学,2004.
[63]赵秋林,张芬兰.西安安康铁路喇叭口隧道的设计与施工[J].铁道工程学报,2000,3：72～75.
[64]黄宣明.大型地下立交隧道施工技术探讨[J].地下空间与工程学报,2007,3(4)：765～769.
[65]易小明,陈卫忠,李术才等.BP神经网络在分岔隧道位移反分析中的应用[J].岩石力学与工程学报,2006,25(增2)：3927～3932.
[66]张晓燕.分岔隧道围岩支护设计研究[J].公路工程,2009,34(3)：83～85.
[67]冯夏庭.智能岩石力学导论[M].北京：科学出版社,2000.
[68]于学馥.岩石力学的科学主题是过程的研究[J].东北煤炭技术,1997,2(1)：10～13.
[69]李世辉.隧道围岩稳定系统分析[M].北京：中国铁道出版社,1991.
[70]冯夏庭.巷道支护优化设计的智能系统研究[D].东北大学,1991.
[71]周伟达.核机器学习方法研究[D].西安电子科技大学,2003.
[72]沈峰,陈建胜,唐新建.专家系统在岩土工程中的应用综述[J].岩土工程界,2007,11(4)：27～29.
[73]刘勇建,李子生.人工神经网络在岩土工程中的应用综述[J].广东工业大学学报,2004,21(4)：66～71.
[74]张清,田盛丰,莫元彬.铁路隧道围岩分类的专家系统[J].铁道学报,1989,11(4)：66～71.
[75]张清.对岩石力学与工程发展战略的几点看法[J].岩石力学与工程学报,1993,12(3)：284～285.
[76]冯夏庭,杨成祥.智能岩石力学(2)—参数与模型的智能辨识[J].岩石力学与工程学报,1999,18(3)：350～353.
[77]马文涛.支持向量机方法在膨胀土分类中的应用[J].岩士力学,2005,26(11)：1790～1792.
[78]姜谙男,梁冰.基于PSO-SVM的大坝渗流监测时间序列非线性预报模型[J].水利学报,2006,37(3)：331～335.
[79]姜谙男,梁冰.基于粒子群支持向量机的三维含水层渗流参数反馈识别[J].岩土力学,2009,30(5)：1527～1531.
[80]姜谙男,梁冰,张娇.基于粒子群最小二乘支持向量机的瓦斯含量预测[J].辽宁工程技术大学学报：自然科学版,2009,28(3)：363～366.
[81]董辉,傅鹤林,冷伍明.滑坡位移时序预测的核函数构造[J].岩土力学,2008,29(4)：1087-1092.
[82]Shi Y, Eberhart R. Empirical study of particle swarm optimization[A]. International Conference on Evolutionary Computation[C]. Washington USA:IEEE,1999,1945-1950.
[83]侯俊钦,杨一军,陈得宝等.基于蚁群方法的机器人滑模跟踪控制器设计[J].计算机仿真,2009,11：161-165.
[84]黄光球,姚玉霞,陆秋琴.用鱼群算法求解通风系统风机定位优化问题[J].计算机工程与应用,2008,44(1)：243～248.
[85]肖云华.双峰隧道围岩稳定性非线性系统分析[D].吉林大学,2009.
[86]魏莉萍.隧道工程喷锚支护的案例设计研究及其与专家系统、神经元网络综合的研究[D].北方交通大学,1999.
[87]熊志化,黄国宏,邵惠鹤.基于高斯过程和支持向量机的软测量建模比较及应用研究[J].信息与控制,2004,33(6)：754～757.
[88]熊志化,张继承,邵惠鹤.基于高斯过程的软测量建模[J].系统仿真学报,2005,17(4)：793～794.
[89]Mercer J. Functions of positive and negative type and their connection with the theory of integral equations[J]. Philos. Trans. Roy. Soc. London,1909, A 209:415-446.
[90]熊志化.高斯过程模型及其在工业过程软测量中的应用研究[D].上海交通大学,2006.
[91]Mika et al. Fisher discriminant analysis with kernels[C]. In Y.H. Hu, J, Larsen, E. Wilson and S. Douglas, editors, Neural Networks for Signal Processing IX, New York:IEEE Press,1999,41-48.
[92]Xu J., Zhang X., Ci Y. Kernel neuron and its training algorithm[C]. Proceedings of the 8th International Conference on Neural Information Processing,2001,2,861-866.
[93]许建华,张学工,李衍达.基于核函数的非线性口袋算法[J].电子学报,2003,31(4)：612～615.
[94]Yu K., Zhang X., Ji L. Kernel nearest-neighbor algorithm[J]. Neural Processing Letter, 2002,15(2):147-156.
[95]Saunder C., Gammernann A., Vovk V. Ridge regression learning algorithm in dual variabIes.[C] In J.Shavlik, editor, Proceedings of the 15th International Conference on Machine Learning,1998,515-521.
[96]Tipping M.E. The relevance vector machine[C] In S.A. Solla, T.K. Leen and K.R. Muller, eds., Advances in Neural Information Processing System,2000,12,652-658.
[97]Herbrich R., Graepel T., Campbell C. Bayes point machines:estimating the Bayes point in kernel space[C] Proceeding of IJCAI Workshop Support Vector Machine,1999,23-27.
[98]Lawrence N.D., Seeger M., Herbrich R. The informative vector machine:a practical probabilistic alternative to the support vector machine[R]. Technical Report No. CS-04-07, Department of Computer Science, University of Sheffield,2004.
[99]Vapnik V.N. Statistical learning theory[M]. New York:Wiley,1998.
[100]Vapnik V.N. The nature of statistical learning theory(2th edition)[M]. New York: Springer-Verlag,1999.
[101]Carl Edward Rasmussen, Christopher K.I. Williams. Gaussian Processes for Machine Learning[M]. Massachusetts:The MIT Press,2006.
[102]苏国韶,燕柳斌,张小飞等.基坑位移时间序列预测的高斯过程方法[J].广西大学学报(自科版),2007,32(2)：223～226.
[103]苏国韶,宋咏春,燕柳斌.岩体爆破效应预测的一种新方法[J].岩石力学与工程学报,2007,26(增1)：3509～3513.
[104]冯夏庭,周辉,李邵军等.岩石力学与工程综合集成智能反馈分析方法及应用[J].2007,26(9)：1737～1744.
[105]赵洪波,冯夏庭,尹顺德.支持向量机函数拟合的边坡稳定性估计[J].岩石力学与工程学报,2003,22(2)：241-245.
[106]苏国韶,冯夏庭,江权等.高地应力下大型地下洞室群开挖顺序与支护参数组合优化的智能方法[J].岩石力学与工程学报,2007,Z1：2800～2808.
[107]江权,冯夏庭,苏国韶.基于松动圈-位移增量监测信息的高地应力下洞室群岩体力学参数的智能反分析[J].岩石力学与工程学报,2007,Z1：2654～2622.
[108]张友良,冯夏庭,赵洪波等.基于数据智能可视化分析的滑坡信息化施工研究[J].岩土力学,2003,24(6)：935～939.
[109]张友良,冯夏庭.岩土工程百万以上自由度有限元并行计算[J].岩土力学,2007, 28(4)：684～688.
[110]Radford M. Neal. Bayesian Learning for Neural Networks[D]. The University of Toronto,1995.
[111]陈世敏.山区道路降雨量推估模式建立之研究—以阿里山公路为例[D].台湾国立科技大学,2005.
[112]田执祥,乔春生,滕文彦等.基于支持向量机的隧道变形预测方法[J].中国铁道科学2004,25(1)：86～90.
[113]刘开云,乔春生,滕文彦.边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究[J].岩土工程学报,2004,26(1)：57～61.
[114]刘开云,乔春生,田盛丰等.边坡角设计的支持向量机建模与精度影响因素研究[J].岩石力学与工程学报,2005,24(2)：328～335.
[115]Evgeniou T., Pontil M., Poggio T. Regularization networks and support vector machines[J]. Advances in Computational Mathematics,2000,13,1-50.
[116]封举富.模式识别[OL].北京大学,2004.
[117]阎平凡,张长水.人工神经网络与模拟进化计算(第二版)[M].北京：清华大学出版社,2005：51～60,140～175.
[118]Courant R. Hilbert D. Method of mathematical physics[M]. Interscience, London, 1962.
[119]王明元.数学物理方程与特殊函数[M].北京：高等教育出版社,2005,84～97.
[120]Rosasco L. Reproducing kernel Hilbert spaces[R]. MIT,2010.
[121]Wahba G.. Spline models for observational data[C]. CBMS-NSF Regional Confercence series in applied mathematics,1990.
[122]Seeger M. Relationships between Gaussian processes, support vector machines and smoothing spline[R]. Submitted to machine learning, Institute of Adaptive and Neural Computation, University of Edinburgh,2002.
[123]Scholkopf B. Herbrich R. Smola A.J. A generalized tepresenter theorem[R]. NeuroCOLT2 Technical Report Series(NC2-TR-2000-81), Department of Engineering, Australian National University.
[124]Smola A.J. Scholkopf B. Bayesian kernel methods[M]. In Mendelson S. and Smola A.J., editors, Advanced lectures on machine learning, Springer,2003,65-117.
[125]曾建潮,介婧,崔志华微粒群算法[M].北京：科学出版社,2004.
[126]白凤仙.面向工程的电磁场软件与电磁场逆问题研究[D].太原理工大学,2002.
[127]Shi.Y., Eberhart R. Empirical study of particle swarm optimization[A]. in Proceedings of the IEEE Congress on Evolutionary Computation (CEC 1999)[C], Piscataway, NJ,1999:1945-1950.
[128]Clerc M., Kennedy J. The particle swarm-explosion, stability, and convergence in a multidimensional complex space[J]. IEEE Transactions on Evolutionary Computation, 2002,6(1):58-73,2002.
[129]Shi.Y., Eberhart R. Fuzzy adaptive particle swarm optimization[A]. In IEEE Int. Conf. on Evolutionary Computation[C].2001:101-106.
[130]陈贵敏,贾建援,韩琪.粒子群优化算法的惯性权值递减策略研究[J].西安交通大学学报,2006,40(1)：53～56.
[131]Stefan Janson, Martin Middendorf. A hierarchical particle swarm optimizer and its adaptive variant[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2005,35(6):1272-1282.
[132]李爱国.多粒子群协同优化算法[J].复旦大学学报,2004,43(5)：923～925.
[133]Suganthan, P.N. Particle swarm optimiser with neighbourhood operator[A]. in Proceedings of the IEEE Congress on Evolutionary Computation (CEC)[C]. Piscataway, NJ,1999,1958-1962.
[134]Robinson J., Sinton S., Rahmat-Samii Y. Particle Swarm, Genetic Algorithm, and Their Hybrids:Optimization of a profiled corrugated horn antenna[A]. In Antennas and Propagation Society International Symposium [C]. IEEE Press, New York,2002, vol.1: 314-317.
[135]Juang C F. A hybrid of genetic algorithm and particle swarm optimization for recurrent network design[J]. IEEE Transactions on Systems, Man and Cybernetics (Part B-Cybernetics),2004,34(2):997-1006.
[136]Krink T., Lovbjerg M. The Lifecycle Model:Combining particle swarm optimization, genetic algorithms and hill climbers[A]. In Proc. of PPSN 2002 [C].2002,621-630.
[137]Naka S., Genji T., Yura T. et al. A hybrid particle swarm optimization for distribution state estimation [C]. IEEE Trans. Power Syst.,2003,60-68.
[138]Angeline P. J. Using selection to improve particle swarm optimization [A], in Proc of the IEEE Congress on Evolutionary Computation [C]. Anchorage, USA,1998,84-89.
[139]方开泰,马长兴.正交与均匀实验设计[M].北京：科学出版社,2001.
[140]栾军.现代实验设计优化方法[M].上海：上海交通大学出版社,1995.
[141]汪荣鑫.数理统计[M].西安：西安交通大学出版社,1986.
[142]汪晓程,王瑛.多目标决策分析中的目标关联分析法[J].系统工程理论与实践,2000,12,63～66.
[143]何瑶,王哲.主成分分析、法在优化纺织工艺中的应用[J].棉纺织技术,2001,29(1)：34～36.
[144]袁志发,周静芋.多元统计分析[M].北京：科学出版社,2002.
[145]秦四清.非线性岩土力学基础[M].北京：地质出版社,2008.
[146]付成华,陈胜宏.基于突变理论的地下工程洞室围岩失稳判据研究[J].岩土力学,2008,29(1)：167～162.
[147]赵志峰,徐卫亚.基于突变理论的边坡安全稳定性综合评价[J].岩石力学与工程学报,2007,S1(26)：2707～2712.
[148]潘岳,张志强,张勇.突变理论在岩体系统动力失稳中的应用[M].北京：科学出版社,2008.
[149]叶金汉.岩石力学手册[M].北京：水利电力出版社,1991.
[150]Vermeer P. A., R. de Borst. Non-associated plasticity for soils[J]. Concrete and Rock, 1984,29(3):1-64.
[2]中铁隧道勘察设计院有限公司.青岛胶州湾海底隧道设计说明[R].中铁隧道勘察设计院,2009.
[3]重庆交通科研设计院.万石山隧道与既有钟鼓山隧道立体交叉设计说明[R].重庆交通科研设计院,2005.
[4]吴波,刘维宁,高波等.地铁分岔隧道施工性态的三维数值模拟与分析[J].岩石力学与工程学报,2004,23(15)：3081～3086.
[5]刘洪伟.三线“Y”字型喇叭口隧道施工方法及转换研究[J].西部探矿工程,2001,21：180～182.
[6]重庆交通科学研究院.公路隧道设计规范(JTG D70-2004)[S].北京：人民交通出版社,2004.
[7]中交第一公路勘察设计研究院.公路路线设计(JTG D20-2006)[S].北京：人民交通出版社,2006.
[8]Kavanagh K.T., Clough R.W. Finite element application in the characterization of elastic solids[J]. Int J Solids structure,1972,7:11-23.
[9]Kristen H.A.D. Deternination of rock mass elastic moduli by back anlysis of deformation measurement[A]. In Proc Symp on Expiration for Rock Eng[C]. Johannesburg,1976, 1154-1160.
[10]Wang Zhiyin The back estimation of equivalent release load and support force by BEM[A]. In Proc 3rd Int Conf on Underground Spaces and Earth Sheltered Buildings[C]. Shanghai:TongJi University Press,1988,789-792.
[11]Sotirios S. Vardakos.Marte S. Gutierrez, Nick R. Barton. Back-analysis of Shimizu Tunnel No.3 by distinct element modeling[J]. Tunnelling and Underground Space Technology, 2007,22:401-413.
[12]Kovari K. et al. Integrated measuring technique for rock pressure determination[A]. In Proc Int Conf on Field Measurements in Rock Mechanics[C]. Zurich,1977,1:533-538.
[13]Sakurai S. Takeuchi K., Back analysis of measured displacement of tunnel[J]. Rock Mech and Rock Eng,1983,16(3):173-180.
[14]Gioda G. Maier G. Direct search solution of an inverse problem in elasto-plasticity identification of cohesion friction angle and in-situ stress by pressure tunnel tests[J]. Int J Num Methods in Eng,1980,15:1823-1834.
[15]Gioda G. Pandolfi A., Cividini A. A comparative evaluation of some back analysis algorithms and their application to in-situ load tests[A]. In Proc 2nd Int Symp on Field Measurement in Geom,1987,1131-1144.
[16]Arai R. An inverse problem approach to the prediction of Multi-dimensional consolidation behaviorfJ]. Soil and Foundations.1984,24(1):95-108.
[17]杨志法,刘竹毕.位移反分析法在地下工程设计中的初步应用[J].地下工程,1981(2)：20～24.
[18]杨林德等.初始地应力位移反分析的有限单元法[J].同济大学学报,1985(4)：15～20.
[19]王芝银.地下工程围岩粘弹塑性参数反分析[J].水利学报,1990,(9)：11～16.
[20]Wang Zhiyin, Li Yunpeng. Back analysis of measured rheologic displacements of underground opening.[A] In Proc Int Symp on Underground Eng[C]. New Delhi,1988, 181-186.
[21]刘怀恒.地下工程位移反分析原理应用及其发展[J].西安矿业学院学报,1988,8(3)：1～10.
[22]李云鹏,王芝银.粘弹性位移反分析的边界元法[J].西安矿业学院学报,1989,9(1)：17～24.
[23]Hisatake M. Three dimensional back analysis for tunnels[A]. In Proc Int Symp on ECRF[C]. Beijing:Science Press,1986,791-797.
[24]杨林德,朱合华.地层三维粘弹性反演分析[J].岩土工程学报,1991(6)：18～26.
[25]王芝银.空间轴对称蠕变位移反分析[A].第二届全国岩石力学数值计算与模型实验学术研讨会论文集[c].上海：同济大学出版社,1990,751～756.
[26]Gens A. Back analysis using Prior information-application to the staged excavation of a cavern in Rock[J]. Num Meth in Geomech, Innsbruck,1988,2009-2016.
[27]袁勇.围岩弹塑性参数反算的极大似然法[J].工程勘察,1991(5)：31-34.
[28]冯夏庭,张志强,杨成祥等.位移反分析的进化神经元网络方法研究[J].岩石力学与工程学报,1999,18(5)：529～533.
[29]戴荣,李忠全.三维地应力场BP反分析的改进[J].岩石力学与工程学报,2005,24(1)：83～88.
[30]刘开云.隧道工程信息化设计与智能分析方法研究[D].北京交通大学,2005.
[31]Gnirk P. F., Fossum A. F. On the formulation of stability and design of design criteria for compressed air energy storage in hard rock caverns[A]. In Proceedings of thelntersociety Energy Conversion Engineering Conference[C]. Am Chem Soc:1979,429-440.
[32]Miller, Stephen A., Gardner et al. Long-term stability of bryan mound solution caerns for LPG storge, with worst-case scenario[A]. In Pro Symp Solution Mining of Salts and Brines[C]. New York:1985,71-80.
[33]俞裕泰,黄赛超.坚硬而不完整岩体中地下洞室的分期开挖[J].地下工程,1984,11：31～35.
[34]莫海鸿,杨林德,鲍德波.复杂地质条件下地下厂房围岩稳定性分析[A].第六次全国岩石力学与工程学术大会会议论文集[c].北京：中国科学技术出版社,2000.
[35]史红光.二滩水电站地下厂房围岩稳定性因素评价[J]_水电站设计,1999,15(2)：75～78.
[36]张玉祥,包四根.复杂地质体中地下洞室的施工优化与稳定性评价[J].岩石力学与工程学报,2000,19(6)：722～725.
[37]陈帅宇,周围垣,杨强等.三维快速拉格朗日法进行水布垭地下厂房的稳定性分析[J].岩石力学与工程学报,2003,22(7)：1047～1053.
[38]朱维中,孙爱花,王文涛等.大型洞室群高边墙位移预测和围岩稳定性判别方法[J].岩石力学与工程学报,2007,26(9)：1729～1736.
[39]李术才,王汉鹏,郑学芬.分岔隧道稳定性分析及施工优化研究[J].岩石力学与工程学报,2008,27(3)：447～457.
[40]付成华,陈胜宏.基于突变理论的地下工程洞室围岩失稳判据研究[J].岩土力学,2008,29(1)：167～172.
[41]朱维中,王平.动态规划原理在洞室群施工力学中的应用[J].岩石力学与工程学报,1992,11(4)：323～331.
[42]肖明.地下洞室施工开挖三维动态过程数值模拟分析[J].岩士工程学报,2000,22(4)：421-425.
[43]朱维中,李术才,程峰.能量耗散模型在大型地下洞群施工顺序优化分析中的应用[J].岩土工程学报,2001,23(3)：333～336.
[44]姜谙男.大型洞室群开挖与加固方案反馈优化分析集成智能方法研究[D].东北大学,2004.
[45]苏国韶.高地应力下大型地下洞室群稳定性分析与智能优化研究[D].中科研武汉岩土力学所,2006.
[46]朱维中,何满潮.复杂条件下围岩稳定性与岩体动态施工力学[M].北京：科学出版社,1995
[47]李术才,朱维中.小浪底地下洞室群施工顺序优化分析[J].煤炭学报,1996,21(4)：393～398.
[48]朱万成,唐春安.基于正交试验原理和锚喷参数设计系统及其应用[J].岩土力学,1999,20(2)：87～91.
[49]朱万成,李晓.地下工程中的正交有限元分析方法及其应用[J].工程地质学报,1999,7(4)：337～347.
[50]朱万成,李晓.锚喷参数的回归正交有限元试验分析及其应用实例[J].岩石力学与工程学报,1999,18(3)：283～286.
[51]邓健,古德生,李夕兵.无间柱连续采矿采场参数的多指标正交有限元设计[J].中南工业大学学报,1999,30(5)：445～448.
[52]肖专文,张其志,赵文等.遗传算法与神经网络协调求解采矿工程中的优化问题[J].中国矿业,1998,7(1)：78～82.
[53]安红刚,冯夏庭.大型洞室群稳定性与优化的进化有限元方法研究[J].岩土力学,2001,22(4)：373～377.
[54]高玮,郑颖人.蚁群算法及其在硐群施工优化中的应用[J].2002,21(4)：471～474.
[55]赵洪波.非线性岩土力学行为的支持向量机研究[D].中科院武汉岩土力学所,2003.
[56]李兴璜.西安-安康铁路的隧道建设和进步技术[J].中国铁路,1999,12：1-5
[57]何川.公路双连拱隧道[M].
[58]铁路部第二勘测设计院.铁路隧道设计规范(TB10003-2005)[S].北京：中国铁道出版社,2005.
[59]交通部第二公路勘察设计院.公路隧道勘测规程(JTJ063-85)[S].北京：人民交通出版社,1985.
[60]秦峰.吴存兴.小净距隧道开挖方法浅论[J].现代隧道技术,2003,40(6)：39～42.
[61]陈文辉,秦峰,陈贵华.小净距隧道连拱隧道普通式隧道造价对比分析[J].公路交通技术,2005,6：120～122.
[62]刘伟.小净距公路净距优化研究[D].同济大学,2004.
[63]赵秋林,张芬兰.西安安康铁路喇叭口隧道的设计与施工[J].铁道工程学报,2000,3：72～75.
[64]黄宣明.大型地下立交隧道施工技术探讨[J].地下空间与工程学报,2007,3(4)：765～769.
[65]易小明,陈卫忠,李术才等.BP神经网络在分岔隧道位移反分析中的应用[J].岩石力学与工程学报,2006,25(增2)：3927～3932.
[66]张晓燕.分岔隧道围岩支护设计研究[J].公路工程,2009,34(3)：83～85.
[67]冯夏庭.智能岩石力学导论[M].北京：科学出版社,2000.
[68]于学馥.岩石力学的科学主题是过程的研究[J].东北煤炭技术,1997,2(1)：10～13.
[69]李世辉.隧道围岩稳定系统分析[M].北京：中国铁道出版社,1991.
[70]冯夏庭.巷道支护优化设计的智能系统研究[D].东北大学,1991.
[71]周伟达.核机器学习方法研究[D].西安电子科技大学,2003.
[72]沈峰,陈建胜,唐新建.专家系统在岩土工程中的应用综述[J].岩土工程界,2007,11(4)：27～29.
[73]刘勇建,李子生.人工神经网络在岩土工程中的应用综述[J].广东工业大学学报,2004,21(4)：66～71.
[74]张清,田盛丰,莫元彬.铁路隧道围岩分类的专家系统[J].铁道学报,1989,11(4)：66～71.
[75]张清.对岩石力学与工程发展战略的几点看法[J].岩石力学与工程学报,1993,12(3)：284～285.
[76]冯夏庭,杨成祥.智能岩石力学(2)—参数与模型的智能辨识[J].岩石力学与工程学报,1999,18(3)：350～353.
[77]马文涛.支持向量机方法在膨胀土分类中的应用[J].岩士力学,2005,26(11)：1790～1792.
[78]姜谙男,梁冰.基于PSO-SVM的大坝渗流监测时间序列非线性预报模型[J].水利学报,2006,37(3)：331～335.
[79]姜谙男,梁冰.基于粒子群支持向量机的三维含水层渗流参数反馈识别[J].岩土力学,2009,30(5)：1527～1531.
[80]姜谙男,梁冰,张娇.基于粒子群最小二乘支持向量机的瓦斯含量预测[J].辽宁工程技术大学学报：自然科学版,2009,28(3)：363～366.
[81]董辉,傅鹤林,冷伍明.滑坡位移时序预测的核函数构造[J].岩土力学,2008,29(4)：1087-1092.
[82]Shi Y, Eberhart R. Empirical study of particle swarm optimization[A]. International Conference on Evolutionary Computation[C]. Washington USA:IEEE,1999,1945-1950.
[83]侯俊钦,杨一军,陈得宝等.基于蚁群方法的机器人滑模跟踪控制器设计[J].计算机仿真,2009,11：161-165.
[84]黄光球,姚玉霞,陆秋琴.用鱼群算法求解通风系统风机定位优化问题[J].计算机工程与应用,2008,44(1)：243～248.
[85]肖云华.双峰隧道围岩稳定性非线性系统分析[D].吉林大学,2009.
[86]魏莉萍.隧道工程喷锚支护的案例设计研究及其与专家系统、神经元网络综合的研究[D].北方交通大学,1999.
[87]熊志化,黄国宏,邵惠鹤.基于高斯过程和支持向量机的软测量建模比较及应用研究[J].信息与控制,2004,33(6)：754～757.
[88]熊志化,张继承,邵惠鹤.基于高斯过程的软测量建模[J].系统仿真学报,2005,17(4)：793～794.
[89]Mercer J. Functions of positive and negative type and their connection with the theory of integral equations[J]. Philos. Trans. Roy. Soc. London,1909, A 209:415-446.
[90]熊志化.高斯过程模型及其在工业过程软测量中的应用研究[D].上海交通大学,2006.
[91]Mika et al. Fisher discriminant analysis with kernels[C]. In Y.H. Hu, J, Larsen, E. Wilson and S. Douglas, editors, Neural Networks for Signal Processing IX, New York:IEEE Press,1999,41-48.
[92]Xu J., Zhang X., Ci Y. Kernel neuron and its training algorithm[C]. Proceedings of the 8th International Conference on Neural Information Processing,2001,2,861-866.
[93]许建华,张学工,李衍达.基于核函数的非线性口袋算法[J].电子学报,2003,31(4)：612～615.
[94]Yu K., Zhang X., Ji L. Kernel nearest-neighbor algorithm[J]. Neural Processing Letter, 2002,15(2):147-156.
[95]Saunder C., Gammernann A., Vovk V. Ridge regression learning algorithm in dual variabIes.[C] In J.Shavlik, editor, Proceedings of the 15th International Conference on Machine Learning,1998,515-521.
[96]Tipping M.E. The relevance vector machine[C] In S.A. Solla, T.K. Leen and K.R. Muller, eds., Advances in Neural Information Processing System,2000,12,652-658.
[97]Herbrich R., Graepel T., Campbell C. Bayes point machines:estimating the Bayes point in kernel space[C] Proceeding of IJCAI Workshop Support Vector Machine,1999,23-27.
[98]Lawrence N.D., Seeger M., Herbrich R. The informative vector machine:a practical probabilistic alternative to the support vector machine[R]. Technical Report No. CS-04-07, Department of Computer Science, University of Sheffield,2004.
[99]Vapnik V.N. Statistical learning theory[M]. New York:Wiley,1998.
[100]Vapnik V.N. The nature of statistical learning theory(2th edition)[M]. New York: Springer-Verlag,1999.
[101]Carl Edward Rasmussen, Christopher K.I. Williams. Gaussian Processes for Machine Learning[M]. Massachusetts:The MIT Press,2006.
[102]苏国韶,燕柳斌,张小飞等.基坑位移时间序列预测的高斯过程方法[J].广西大学学报(自科版),2007,32(2)：223～226.
[103]苏国韶,宋咏春,燕柳斌.岩体爆破效应预测的一种新方法[J].岩石力学与工程学报,2007,26(增1)：3509～3513.
[104]冯夏庭,周辉,李邵军等.岩石力学与工程综合集成智能反馈分析方法及应用[J].2007,26(9)：1737～1744.
[105]赵洪波,冯夏庭,尹顺德.支持向量机函数拟合的边坡稳定性估计[J].岩石力学与工程学报,2003,22(2)：241-245.
[106]苏国韶,冯夏庭,江权等.高地应力下大型地下洞室群开挖顺序与支护参数组合优化的智能方法[J].岩石力学与工程学报,2007,Z1：2800～2808.
[107]江权,冯夏庭,苏国韶.基于松动圈-位移增量监测信息的高地应力下洞室群岩体力学参数的智能反分析[J].岩石力学与工程学报,2007,Z1：2654～2622.
[108]张友良,冯夏庭,赵洪波等.基于数据智能可视化分析的滑坡信息化施工研究[J].岩土力学,2003,24(6)：935～939.
[109]张友良,冯夏庭.岩土工程百万以上自由度有限元并行计算[J].岩土力学,2007, 28(4)：684～688.
[110]Radford M. Neal. Bayesian Learning for Neural Networks[D]. The University of Toronto,1995.
[111]陈世敏.山区道路降雨量推估模式建立之研究—以阿里山公路为例[D].台湾国立科技大学,2005.
[112]田执祥,乔春生,滕文彦等.基于支持向量机的隧道变形预测方法[J].中国铁道科学2004,25(1)：86～90.
[113]刘开云,乔春生,滕文彦.边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究[J].岩土工程学报,2004,26(1)：57～61.
[114]刘开云,乔春生,田盛丰等.边坡角设计的支持向量机建模与精度影响因素研究[J].岩石力学与工程学报,2005,24(2)：328～335.
[115]Evgeniou T., Pontil M., Poggio T. Regularization networks and support vector machines[J]. Advances in Computational Mathematics,2000,13,1-50.
[116]封举富.模式识别[OL].北京大学,2004.
[117]阎平凡,张长水.人工神经网络与模拟进化计算(第二版)[M].北京：清华大学出版社,2005：51～60,140～175.
[118]Courant R. Hilbert D. Method of mathematical physics[M]. Interscience, London, 1962.
[119]王明元.数学物理方程与特殊函数[M].北京：高等教育出版社,2005,84～97.
[120]Rosasco L. Reproducing kernel Hilbert spaces[R]. MIT,2010.
[121]Wahba G.. Spline models for observational data[C]. CBMS-NSF Regional Confercence series in applied mathematics,1990.
[122]Seeger M. Relationships between Gaussian processes, support vector machines and smoothing spline[R]. Submitted to machine learning, Institute of Adaptive and Neural Computation, University of Edinburgh,2002.
[123]Scholkopf B. Herbrich R. Smola A.J. A generalized tepresenter theorem[R]. NeuroCOLT2 Technical Report Series(NC2-TR-2000-81), Department of Engineering, Australian National University.
[124]Smola A.J. Scholkopf B. Bayesian kernel methods[M]. In Mendelson S. and Smola A.J., editors, Advanced lectures on machine learning, Springer,2003,65-117.
[125]曾建潮,介婧,崔志华微粒群算法[M].北京：科学出版社,2004.
[126]白凤仙.面向工程的电磁场软件与电磁场逆问题研究[D].太原理工大学,2002.
[127]Shi.Y., Eberhart R. Empirical study of particle swarm optimization[A]. in Proceedings of the IEEE Congress on Evolutionary Computation (CEC 1999)[C], Piscataway, NJ,1999:1945-1950.
[128]Clerc M., Kennedy J. The particle swarm-explosion, stability, and convergence in a multidimensional complex space[J]. IEEE Transactions on Evolutionary Computation, 2002,6(1):58-73,2002.
[129]Shi.Y., Eberhart R. Fuzzy adaptive particle swarm optimization[A]. In IEEE Int. Conf. on Evolutionary Computation[C].2001:101-106.
[130]陈贵敏,贾建援,韩琪.粒子群优化算法的惯性权值递减策略研究[J].西安交通大学学报,2006,40(1)：53～56.
[131]Stefan Janson, Martin Middendorf. A hierarchical particle swarm optimizer and its adaptive variant[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2005,35(6):1272-1282.
[132]李爱国.多粒子群协同优化算法[J].复旦大学学报,2004,43(5)：923～925.
[133]Suganthan, P.N. Particle swarm optimiser with neighbourhood operator[A]. in Proceedings of the IEEE Congress on Evolutionary Computation (CEC)[C]. Piscataway, NJ,1999,1958-1962.
[134]Robinson J., Sinton S., Rahmat-Samii Y. Particle Swarm, Genetic Algorithm, and Their Hybrids:Optimization of a profiled corrugated horn antenna[A]. In Antennas and Propagation Society International Symposium [C]. IEEE Press, New York,2002, vol.1: 314-317.
[135]Juang C F. A hybrid of genetic algorithm and particle swarm optimization for recurrent network design[J]. IEEE Transactions on Systems, Man and Cybernetics (Part B-Cybernetics),2004,34(2):997-1006.
[136]Krink T., Lovbjerg M. The Lifecycle Model:Combining particle swarm optimization, genetic algorithms and hill climbers[A]. In Proc. of PPSN 2002 [C].2002,621-630.
[137]Naka S., Genji T., Yura T. et al. A hybrid particle swarm optimization for distribution state estimation [C]. IEEE Trans. Power Syst.,2003,60-68.
[138]Angeline P. J. Using selection to improve particle swarm optimization [A], in Proc of the IEEE Congress on Evolutionary Computation [C]. Anchorage, USA,1998,84-89.
[139]方开泰,马长兴.正交与均匀实验设计[M].北京：科学出版社,2001.
[140]栾军.现代实验设计优化方法[M].上海：上海交通大学出版社,1995.
[141]汪荣鑫.数理统计[M].西安：西安交通大学出版社,1986.
[142]汪晓程,王瑛.多目标决策分析中的目标关联分析法[J].系统工程理论与实践,2000,12,63～66.
[143]何瑶,王哲.主成分分析、法在优化纺织工艺中的应用[J].棉纺织技术,2001,29(1)：34～36.
[144]袁志发,周静芋.多元统计分析[M].北京：科学出版社,2002.
[145]秦四清.非线性岩土力学基础[M].北京：地质出版社,2008.
[146]付成华,陈胜宏.基于突变理论的地下工程洞室围岩失稳判据研究[J].岩土力学,2008,29(1)：167～162.
[147]赵志峰,徐卫亚.基于突变理论的边坡安全稳定性综合评价[J].岩石力学与工程学报,2007,S1(26)：2707～2712.
[148]潘岳,张志强,张勇.突变理论在岩体系统动力失稳中的应用[M].北京：科学出版社,2008.
[149]叶金汉.岩石力学手册[M].北京：水利电力出版社,1991.
[150]Vermeer P. A., R. de Borst. Non-associated plasticity for soils[J]. Concrete and Rock, 1984,29(3):1-64.