摘要
随着国民经济持续、快速的发展，我国不断加大对基础建设的投资。相应地出现了大量的岩土工程问题。地下工程多修建于性状复杂的岩土体中，岩土材料具有高度的随机性、模糊性和不确定性。由于其赋存的特殊性，天然岩体被各种地质构造（如节理、断层等）切割成半连续的状态，通常是一个从松散体到弱面体再到连续体的序列，其所涉及的问题更是一个多场（温度场、渗流场、应力场等）、多相（固相、液相、气相）的复杂耦合问题，再加上施工和复杂的外部环境影响，更难以得到准确的力学参数和本构模型。
岩土体与支护体系是一个复杂的非线性动力系统，在对其缺乏了解的情况下很难去建立一个能够反映其演化规律的数学或物理模型。一种有效的方法是对该系统产生的时间序列进行分析，因其反映了这个系统的状态。对时间序列进行分析方法就是数据挖掘，也就是从大量不完全的、有噪声的、随机的数据中，提取出潜在的包含系统特征的有用信息和知识的过程。这些信息和知识可以反馈到应用领域，指导相应的工作。
本文应用经验模态分解技术和希尔伯特——黄变换理论对监测数据进行处理和分析，应用EMD对监测数据进行降噪和分离，并对其进行了有限元分析和回归分析，使含有特征信息的时间序列被分离出来，比较符合岩土体卸荷变形的内在规律和施工扰动的实际情况，可以较好地满足工程需要。
本文将数据挖掘技术引入监测数据的分析中。为了全面、系统地分析问题，通常要考虑众多的相关变量，若采用多变量时间序列分析方法就可以只用数量较少、互不相关的新变量来反映原变量所包含的大部分信息，达到解决问题的目的。本文在分析多变量时间序列数据特点和实际应用需求的基础上，提出一种基于主成分分析的多变量时间序列模式表示方法，针对多变量时间序列聚类、相似性查找、距离度量、序列分类和异常检验等关键技术进行了深入的分析研究，说明了多变量时间序列的预处理和聚类方法。在对大量监测数据进行统计分析和数值分析的基础上，结合有限元理论的动态位移分析方法，建立围岩位移的智能反分析模型。
为了提高对监测数据、专家经验和其他相关技术的利用率，以及针对围岩应力和位移的发展情况及时地做出决策，本文在传统专家系统的基础上引入神经网络技术，利用神经网络知识库表示知识的分布式连接机制，构建了神经网络专家系统。该系统可以利用已有或已观测到的数据进行推理，为工程实践中的分析、预测和决策等问题提供科学依据。
As the national economy sustained and rapid development, the government continually increaseinvestment in infrastructure in China, and at the same time many problems in geotechnical projectswill also come forth. As we know, tunnels are usually built in the highly complex geologicalmaterials，which shows great randomness, vagueness and uncertainty. Due to the particularity ofnatural rock, it was cut into half continuous by various kinds of geological structure such as joints,fault, etc. Usually rock has an order from granular to continuum. It is a complicated problem whichwas coupled by multiphysics and heterogeneous, and also was influenced by the complex externalenvironment. For those reasons, it was more difficult to acquire the exact mechanics parameters andconstitutive model.
Considering the complex dynamic system which was composed by the rock, soil and lining isnonlinear. It is difficult for us to find out the evolution rules by component a mathematical model ora physical model, if we are lacking in understanding about the system. But we can do it by analyzingthe monitoring time series which reflect the system’s state. Data mining is an appropriate tool inanalyzing time series. By using it we can pick up the potential useful information and knowledgewhich contain characteristics of the system from lots of incomplete, noisy, random data. Theinformation and knowledge we picked up could be feedback to the fields of application to guidancethe corresponding jobs.
In this thesis the experience mode decomposition technique and Hilbert-Huang transformtheory were used to analyze the monitoring data. In order to separate the time series containingfeature information, the monitoring data is noise reduced and decomposed, and also carried finiteelement analysis and regression analysis. The inherent law of the rock-mass and soil-body’sdeformation and response of construction are due to the actual situation. The needs of the projectcould be better met.
In this thesis the data mining technology is introduced to the monitoring data analysis. In orderto comprehensively and systematically analyzing problems, it was necessary to take large amountsof variables. By using multivariable time series analysis, we can pick up most of information fromonly a small number, irrelevant new variables. The thesis provides a representation method of thepattern of multivariate time series based on the analysis of the principal component on the basis ofthe analysis of the features of multivariate time series and its application. We studied the data miningtasks in time series, such as clustering, similarity search, distance measures, classification, discordsdetect, etc. and we also illustrated that the pretreatment and clustering of the multivariate time series.According to the statistical and numerical analysis of lots of monitoring data, the intelligent back analysis model was built combined with dynamic displacement analysis method in finite elementtheory.
In order to improve the utilization of the monitoring data, expert experience and other relatedtechnical, and make timely decisions based on the development of the surrounding rock’s stress anddisplacement, we combined neural network technology with traditional expert system. By using thedistributed connecting mechanism of neural network technology in knowledge representing, weconstructed the neural network expert system. Existing data or observations are used in reasoningapplication and provided as a scientific basis for the practical analysis, forecasting anddecision-making.
引文
[1] Karanagh K and Clough R W. Finite element Applicationin the characterization of elasticsolida[J]. lnt. J. solids structures，1971，7:11-13.
[2] Gioda G，JurinaL. Numerical identification of soil-strueture interaction pressures[J]. Int. J. forNumerical and Analytical Methods in Geomeehanics,1981,(5):33-56.
[3]杨志法，刘竹华.位移反分析在地下工程设计中的初步应用[J].地下工程，1981(2):20-24.
[4] Sakurai S，Abe S. A design approach to dimensioning underground opening[C]. In：Proc3rd IntConf Numerical Methods in Geomechanics．Aachen，1979:649-661.
[5] Sakurai S，Takeuchi K. Back analysis of measured displacement of tunnel[J]、Rock Mech andRock Eng，1983，16(3):173-180.
[6] Gioda G, Sakurai S. Back analysis procedures for the interpretation of field measurements ingeomechanics[J]. Intemational Journal for Numerical and Analytical methods in Geomechanics,1987,11(6):555-583.
[7]郭怀志，马启超，薛玺成等.初始应力场的分析方法[J].岩土工程学报，1983，5(3):64-75.
[8]朱伯芳.岩体初始地应力场反分析[J].水利学报,1994，10(10):30-35.
[9]张有天等.地应力场的趋势分析[J].水利学报,1984,4(4)：31-38
[10]肖明.三维初始应力场反演与应力函数拟合[J].1989,8(4):337-345
[11]白世伟,李光煌.某水电站坝区岩体应力场研究[J].岩石力学与工程学报,1982, l(l):255-285.
[12]冯紫良，杨林德.初始地应力的反推原理[J].同济大学学报，1983，(3):18-25.
[13]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.
[14]王芝银，刘怀恒.粘弹塑性有限元分析及其在岩石力学与工程中的应用[J].西安矿业学院学报,1985,5(1):86-101.
[15]郑颖人，张德微，高效伟.弹塑性问题反演计算的边界元法[C].中国土木学会第三届年会论文集.上海:同济大学出版社，1986:377-385.
[16]郑颖人，张德微，高效伟.应变空间弹塑性反演计算的边界元法[C].第一届全国计算岩土力学研讨会论文集(一).峨眉:西南交通大学出版杜，1987:209-216.
[17]王芝银，李云鹏.地下工程位移反分析法及程序[M].西安:陕西科学技术出版社.1993.
[18] WangZhiyin，LiuHuaiheng. Back analysis of measured rheologic displacements ofundergroundopenings[C]. In: Proc6th Conf On Num Meth in6eom. Austria，1988:2291-2297.
[19]刘怀恒.地下工程位移反分析原理、应用及发展[J].西安矿业学院学报，1988，8(3):1-11.
[20]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.
[21]朱维申等.考虑时空效应的地下洞室变形观测及反分析[J].岩石力学与工程学报,1989,8:346-353.
[22]王芝银.地下巷道考虑空间效应的增量反分析[J].西安矿业学院学报,1987,7(4):13-21.
[23]孙钧，黄伟.岩石力学参数弹塑性反演问题的优化方法[J].岩石力学与工程学报,1992,11:221—229.
[24]徐日庆，龚晓南，王明洋，等.粘弹性本构模型的识别与变形预报[J].水利学报，1998(4):75-80.
[25]吉小明,赵中旺.隧道监测和信息反馈中的计算模型优化问题[J].地下空间，1997.17(2):104-108.
[26]徐卫亚,刘世君.岩石力学参数的非线性随机反分析[J].岩土力学,2001,22(4):432-435.
[27]刘世君，蒋中明，徐卫噩，等.岩体非线性随机反分析优化算法的研究[J].三峡大学学报(自然科学版)，2002，24(3):202-205.
[28]李宁，尹森菁.边坡安全监测的仿真反分析[J].岩石力学与工程学报，1996，15(1):9-18.
[29]李宁，辛有良，韩火亘，G．Swoboda.华盛顿地铁福特一图特站的仿真反分析[J].西安理工大学学报，1996，12(4):324-329．
[30]李宁，李永刚，等.碎裂块体围岩安全监测与仿真反分析[J].岩土工程学报，2000，22(2):0-173.
[31]朱合华,杨林德等.坑工程动态施工反演分析与变形预报[J].工程学报，1998，20(4):30-35.
[32]朱合华,等.软土深基坑粘弹性动态增量反演分析与变形预测[J].岩土力学，2000，21(4):381-384.
[33]杨志法，熊顺成，王存玉，等.关于位移反分析的某些考虑[J].岩石力学与工程学报，1995，14(1):11-16.
[34]李仲奎，莫兴华，王爱民，等.地下洞室松动区模型及其在反馈分析中的应用[J].水利水电技术，1999，(5):49-51.
[35]邓建辉，李焯芬，葛修润.岩石边坡松动区与位移反分析[J].岩石力学与工程学报，2001,20(2):171-174.
[36]吕爱钟，蒋斌松.岩石力学反问题[M].北京:煤炭工业出版社，1998.
[37]张路青，贾正雪.弹性位移反分析对地应力、弹模的反演唯一性[J].岩土工程学报，2001，23(2):172-177.
[38]杨林德，吴蔺，等.反演分析中量测误差的传递与仪表选择的研究[J].土木工程学报，2000，33(1):77-82.
[39]张路青，杨志法，吕爱钟．两平行的任意形状洞室围岩位移场解析法研究及其在位移反分析中的应用[J].岩石力学与工程学报,2000,19(5):584-589．
[40]冯夏庭，张治强，等．位移反分析的进化神经网络方法研究[J]．岩石力学与工程学报,1999,18(5)：529—533．
[41]高强，等．遗传算法求解粘弹性反问题[J]．大连理工大学学报，2000，40(6)：664—668．
[42]王思敬，杨志法.地下工程岩体稳定性分析[M].北京：科学出版社，1984
[43]刘寒箫.地下工程围岩稳定性分析与预测[J].山西建筑，2008.34（16）：110-111.
[44]薛琳.圆形隧道粘弹性围岩地应力解析法反分析[P].青岛建工学院学报，1994,15(2):69-76
[45]薛琳.具有水平表面岩土斜坡粘弹性位移解析解[J].岩石力学与工程学报，2005,24(6):950-954.
[46]朱大勇，钱七虎.复杂形状硐室围岩应力弹性解析分析[J].岩石力学与工程学报，1999,18(4):402-404.
[47]许传华，任青文.地下工程围岩稳定性分析方法研究进展[J]金属矿山，2003,(2):34-39.
[48]刘军,李仲奎.非连续变形分析(DDA)方法研究现状及发展趋势[J].岩石力学与工程学报,2004,23(5):839-845.
[49]朱文彬,伍法权,任爱武.关键块体概率分析在复杂构造条件下大型地下工程开挖中的应用[J].工程地质学报.2010.18(2):261-266
[50]马钺,方祖烈,马强.岩石力学离散介质数值方法及应用程序研究综述[J].东北煤炭技术.1999.6(3):17-22
[51]任青文,余天堂.边坡稳定的块体单元法分析[J].岩石力学与工程学报.2001.20(1):20-24.
[52]陈文胜,冯夏庭,葛修润.静态松弛快速拉格朗日分析方法原理[J].岩石力学与工程学报.1999.18(6)：680-684.
[53]张明,姚振汉,杜庆华.双材料基本解弹塑性边界元法[J].力学学报.1999.31(5)：563-573
[54] G. Li and J. Vance. A3D Block-Spring Model of simulating the behavior of jointed rocks. RockMechanics for Industry, Proceeding of37th U. S. Rock Mechanics Symposium, Vail, Colorado,1999,6(1):144-149.
[55] Barton N. Rock mass classification and tunnel reinforcement selection using the Q-system [A].In: Proc. Symp. Rock Class. Eng. Purp. ASTM Special Technical Publication1984[C]. Philadelphia.1988.s1:59-88.
[56]许传华,任青文.围岩稳定分析的熵突变准则研究[J].岩土力学,2004,25(3):437－440.
[57]田宝国等译.复杂系统理论基础[M].上海科技教育出版社.2002:180-186.
[58]高为炳.变结构控制的理论及设计方法[M].科学出版社,1996.
[59] Cam pion G, d’Andrea Novel B, Bastin G. Controllability and state feedback stabilization ofnonholonomic mechanical systems [J]. Advanced Robot Control, Lect Notes control Inf. Sc.162,1991.106-124.
[60] Isidori, A. Nonlinear Control Systems[M]. Springer-Verlag. Berlin.1995.
[61] Artstein. Z. Stabilization with relaxed controls[J]. Nonlinear Analysis.1983.
[62] Byrnes C I, Hu X. The zero dynamics algorithm for general nonlinear systems and itsapplication in exact output tracking. J of Math System Estimation and Control,1993,3(1):51-72.
[63] Biling S A, Tsang K M. Spectral analysis for nonlinear systerms Part Interpretation of nonlinearfrequency response functon[J]. Mechanical Systems and Signal Processing,1989,3(4):341-359.
[64] Zames G, El-Sakkary A K. Unstable systems and feedback: The gap metric[C]. Proc of AllertonConf on Communication, Control, and Computing. Urbana: University of Illinois atUrbana-Champaign,1980:380-385.
[65] Holms J K, Chen C C. Acquisition Time Performance of PN Spread Spectrum System[J].Communications,1977(25):770-783.
[66] Wiggins S. Introduction to applied nonlinear dynamical systems and chaos[M]. New york:Spring-Verlag,1990.
[67] Guido Koch, Gerwald Lichtenberg, Alexander Brandt, et al. Moderling and identification of afree electron laser RF system[C]. Proceeding of the2006IEEE International Conference on ControlApplications. Munich, Germany:IEEE,2006:2921-2926.
[68] Keogh E, Chakrabarti K, Pazzani M, et al. Dimensionality Reduction for Fast Similarity Searchin Large Time Series Databases.Journal of Knowledge and Information Systems. Vol.3(3),2001:263-286.
[69]周大镯,李敏强.基于序列重要点的时间序列分割[J].计算机工程.2008,34(23):14-16.
[70] Agrawal R,Faloutsos C,Swami A,Efficient Similarity Search in Sequence Databases,Proc.4thInt.l Conf Foundations of Data Organizationand Algorithms,Chicago,IL,Oct,1993:69-84.
[71] Chan K,Fu A W. Efficient Time Series Matching by Wavelets. Proc of the15th IEEE Int'lConference on Data Engineering. Sydney,Australia,1999:126-133.
[72] B.Ripley. Pattern recognition and neural networks [M]. London: Cambridge University Press.1996.
[73] Agrawal R,Psaila G,Wimmers E L,Zait M,Querying shapes of histories,In Proc. of the21st Int'lConference on Very Large Databases. San Francisco: Morgan Kaufmann Publishers Inc.1995:502-514.
[74] André-Jnsson H,Badal. D,Using signature files for querying time-series data,In proceedings ofPrinciples of Data Mining and Knowledge Discovery,1st European Symposium.Trondheim,Norway,Jun24-27,1997:11-220.
[75]蒋嵘,李德毅,基于形态表示的时间序列相似性搜索,计算机研究与发展,2000,37(5):601-608.
[76]曾海泉,时间序列挖掘与相似性查找技术研究[博士学位论文],复旦大学,2003.
[77] Keogh E, Chakrabarti K, Pazzani M, et al. Dimensionality Reduction for Fast Similarity Searchin Large Time Series Databases.Journal of Knowledge and Information Systems. Vol.3(3),2001:263-286.
[78] Park Sanghyun,Wesley W,Yoon Jeehee,Won Jungim,Similarity search of time-warpedsubsequences via a suffix tree,Information Systems,2003,Volume:28. Issue:7:867-883.
[79] Perng C.-S.,Wang H.,Zhang S. R.,Parker D. S,Landmarks: A New Model for Similarity-BasedPattern Querying in Time Series Databases,Feb:Proc16th IEEE Int.l Conf on Data Engineering,2000:675-693.
[80] Prat K.B.,Fink E. Search for Patterns in Compressed Time Series. International Journal ofImage and Graphics,2002,2(1) pp.89-106.
[81] Sidiropoulos N. D.,Bros R.,Mathematical Programming Algorithms for Regression-basedNon-linear Filtering in N-dimensional real space,IEEE Transactions on Signal Processing,1999,47:771-782.
[82] Aggarwal C. C.,Hinneburg A,Keim D. A.,On the Surprising Behavior of Distance Metrics inHigh Dimensional Space,International Conference on Database Theory,(ICDT Conference),2001.
[83] H.J.L.M.Vullings,M.H.G.Verhaegen,H.B.Verbruggen. ECG segmentation using time warping.In:Proc. Of2nd Int'1Symposium on Advances in Intelligent Data Analysis.1997:275-285.
[84] Berndt D J,Clifford J,Using dynamic time warping to find patterns in time series,Proc.Knowledge Discovery in Databases Workshop,1994:359-370.
[85] Jain AK,Dubes RC.Algorithms for Clustering Data. Prentice-Hall Advanced ReferenceSeries,1988:1-334.
[86] Hjaltason G. R.,Samet H,Index-driven similarity search in metric spaces. ACM Transactions onDatabase Systems (TODS),2003,28(4):517-580.
[87]李建中,张兆功,超平面树.度量空间中相似性搜索的索引结构[J].计算机研究与发展,2003,40(8)：209-1215.
[88] Kailing K.,Kriegel H.-P.,Schonauer S.,Seidl T,Efficient Similarity Search for Hierarchical Datain Large Databases, Proc.9th Int. Conf. on Extending Database Technology (EDBT2004),Heraklion, Greece,2004:676-693.
[89] Braunmüller B, Ester M, Kriegel H.-P.,Sander J, Efficiently Supporting Multiple SimilarityQueries for Mining in Metric Databases, Proc.16th Int. Conf. on Data Engineering (ICDE2000),SanDiego,CA,2000:256-267.
[90] Kriegel H.-P.,Schonauer S,Similarity Search in Structured Data,Proc.5th Int. Conf. on DataWarehousing and Knowledge Discovery (DaWaK'03),Prague,Czech Republic,2003, in: LectureNotes in Computer Science (LNCS), Vol.2737,2003:309-319.
[91] Bohm C.,Krebs F,The k-Nearest Neighbor Join: Turbo Charging the KDD Process,in:Knowledge and Information Systems (KAIS),2004.1(6).
[92] Li Ming, Chen Xin, Li Xin, Ma Bin, Vitanyi M. B. The similarity Metric, IEEE Transactions onInformation Theory,2004,50(12):3250-3264.
[93] Christian B hm,Powerful Database Support for High Performance Data Mining [PhD thesis],2001. University of Munich,2001.
[94] Grade V, Gunther O.Multidimensional access methods.ACM Computing Surveys,1998,30(2):170-231.
[95] Sellis T. K., Roussopoulos N.,Multidimensional access methods: Trees have grown everywhere,In: Proceedings of the23rd VLDB, Athens, Greens,1997:13-14.
[96] Salzberg B,Access Methods, ACM Computing Surveys,1996,28(1):117-120.
[97] Bohm C,Berchtold S,Keim D A, Seraching in high-dimensional spaces: Index structure forimproving the performance of multimedia dadbases. ACM Computing Servey,2001,33(3):322-373.
[98]张明波,陆锋,申排伟,程昌秀.R树家族的演变和发展,计算机学报,2005,28(3):289-300.
[99] Agrawal R,Faloutsos C,Swami A,Efficient Similarity Search in Sequence Databases,Proc.4thInt.l Conf Foundations of Data Organizationand Algorithms, Chicago, IL, Oct,1993:69-84.
[100] Salzberg B, Tsotras V J, A Comparison of Access Methods for Temporal Data, ACMComputing Survey,1999,31(2):158-221.
[101] Chen M S, Han Jiawet. Yu P S. Data mining: An overview from a database perspective. IEEETrans on Knowledge and Data Engineering,1996,8(6):866-883.
[102]李爱国.时间序列数据分割与时态模式挖掘研究[博士学位论文],西安交通大学,2003.
[103]甘仞初.动态数据的统计分析[M].北京:北京工业大学出版社,1991.
[104] Navone H D,Ceccatto H A. Forecasting Chaos from Small Data Sets: A Comparison DifferentNonlinear Algorithms. Phys A: Math Gen,1995,28:3381-3388.
[105] Kugiumtzis D,and Ling O C,Christophersen N. Regularized Local Linear Prediction ofChaotic Time Series. Physica D.1998,112:344-360.
[106] Kugiumtzis D. State Space Reconstruction Parameters in the Analysis of Chaotic TimeSeries-the Role of the Time Window Length. Physica D.1996,95:13-28
[107] Kantz H,Schreiber T. Nonlinear Time Series Analysis. Cambridge University Press,1997(北京:清华大学出版社,2000,影印本)
[108]张志华,郑南宁,郑海兵.径向基函数神经网络（RBF）的一种极大熵学习算法.计算机学报,2001,24(5):474-479.
[109]陈哲,冯天瑾,张海燕.基于小波神经网络的混沌时间序列分析与相空间重构.计算机研究与发展,2001,38(5):591-596.
[110] Maguire L P,Roche B,McGinnity T M,L J McDaid. Predicting A Chaotic Time Series Using AFuzzy Neural Network. Information Sciences,1998,112:125–136.
[111]李爱国,覃征.积单元网络预测噪声混沌时间序列.西安科技大学学报,2003,23(3):295-297.
[112]石纯一.人工智能原理[M].北京:清华大学出版社,1993:126-148.
[113]吴泉源，刘江宁.人工智能与专家系统[M].长沙:国防科技大学出版社，1995:143-15.
[114]王克宏.知识工程与知识处理系统[M].北京:清华大学出版社，1994:119-145.
[115]陆汝铃.人工智能[M].北京:科学出版社，1989:24-40.
[116]何新贵.知识处理与专家系统[M].北京:国防工业出版社，1990:67-93,112-144.
[117]邹祖讳等著.复合材料的结构与性能[M].吴人杰等译.北京:科学出版社，1999:1-22
[118]武波，马玉祥.专家系统[M].北京:北京理工大学出版社，2001
[119]顾沈明，刘全良.一种基于web的专家系统的设计及实现[J].计算机工程,2001(11):100-110.
[120] Agarwal B D, Broutman L J. Analysis and Performance of Fiber Composites[R]. John Wiley&Sons, Inc,1980.
[121] Huang N. E, Shen Z, Wu M. C. The empiricial mode decomposition and the Hibert spectrumfor nonlinear and non-stationarty time series analysis. Proc. R. Soc. Lond, A,1998,454:903-955.
[122] Terradas J, Oliver R,Ballester J.I. Application of sratisrical techniques to the analysis ofsolarcoronal oscillation[J]. The Astrophysical Journal,2004,614:435-447.
[123] Zhang Ray Ruichong, Ma Shuo, Safak Erdal, et al. Hilbert-Huang Transform analysis ofdynamic and earthquake motion recordings [J]. ASCE: Journal of Engineering Mechanics,2003,129(8):861-875.
[124]何习佳.基于支持向量机的电力短期负荷预测研究[J].电子设计工程.2009.17(12):90-92
[125]刘慧婷,张旻,程家兴.基于多项式拟合算法的EMD端点问题的处理[J].计算机工程与应用.2004,40(16):84-86
[126]胡爱军，安连锁，唐贵基. Hilbert-Huang变换端点效应处理新方法[J].机械工程学报.2008,44(4):154-158.
[127]魏纲，魏新江，龚慈等.软土中盾构法隧道引起的土体移动计算研究[J].岩土力学，2006，27(6):995-999.
[128] PECK R B. Deep excavations and tunneling in soft ground[C]. Proceedings of the7thInternational Conference on Soil Mechanics and Foundation Engineering. Mexico City:[s. n.],1969:225-290.
[129]魏纲.盾构法隧道统一土体移动模型的建立[J].岩土工程学报,2007,29(4):554-559.
[130] LOGANATHAN N. POULOS H G. Analytical prediction for tunneling-induced groundmovement in clays[J]. Journal of Geotechnical and Geoenvironmental Engineering,1998,124(9):846-856.
[131] VERRUIJT A, BOOKER H G. Surface settlements due to deformation of a tunnel in an elastichalf plane[J]. Gcotechnique,1996,46(4):753—756.
[132]魏纲.盾构法隧道施工引起的土体变形预测[J].岩石力学与工程学报.2009,28(2):418-424.
[133] Palus M, Albrecht V, Dvorak I. Information-theoretic test for nonlinearity in time series[J].Physics Letters A,1993,175:203-209.
[134] Palus M. Testing for nonlinearity using redundancies quantitative and aspects[J]. Physica D,1995,80:186-205.
[135] Palus M. Detedting nonlinearity in multivariate time series[J]. Physics Letters A,1996,213:138-147.
[136] Theiler J, Galdrikan B, Longtin A et al. Using surrogate data to detect nonlinearity in timeseries, in Nonlinear Modeling and Forecasting[J]. Studies in the Sciences of Complexity, Proc. Vol.XII, eds. Casdaglis and S.Eubank (Addision-Wesley, Resding, MA),1992,163-188.
[137] Prichard D, Theiler J. Generating surrogate data for time series analysis[J]. Physica D,1995,84:476-493.
[138] Takens F. On the numerical determination of the dimension of an attractor [J]. DynamicalSystems and Turbulence. Warwick,1980, Lecture Notes in Mathematics, Springer-Verlag,1981,898:366-381.
[139] Mane R. On the dimension of compact invariant sets of certain nonlinear maps [J]. DynamicalSystems and Turbulence. Warwick,1980, Lecture Notes in Mathematics, Springer-Verlag,1981,898:230-237
[140] Fraser A M, Swiney H. Independent coordinates for strange attractors from mutualinformation[J]. Physical Review A,1986,33(2):1134-1140
[141] Grassberger P and Procaccia I. Characterization of strange attracttors. Phys. Rev. Lett.1983,50:346-350
[142] Rosenstein M T, Collins J. and C. J. De Luca.A practical method for calculating largestLyapunov exponents from small data sets[J]. Physica D,1993,65:117-134
[143] Moon T K, Stifling W C．Mathematical Methods and Algorithms for Signal Processing[M].Prentice Hall,2000.
[144] Yang K, Shahabi C. A PCA-based Similiarity Measure for Multivariate Time Series[J].Proceedings of the2nd ACM intemational workshop on Multimedia databases，2004:65-74．
[145] Keogh E. Exact Indexing of Dynamic Time Warping[C]. Proceedings of the28th VLDBConference, Hong Kong, China,2002:406-417.
[146] Krzanowski W J. Between-Group Comparison of Principal Components[J]. AmeR. Stat．Assoc,1979,74(3):703-707.
[147] Singhal A, Seborg D E. Pattem Matching in Multivariate Time Series Databases Using aMoving-Window Approach[J]. Chem, Res,2002,41(5):3822-3838.
[148] Jain AK, Dubes RC. Algorithms for Clustering Data. Prentice-Hall Advanced Reference Series,1988:1-334.
[149]贺玲,吴玲达,蔡益朝.数据挖掘中的聚类算法综述[J].计算机应用研究,2007:10-14.
[150] Ma WM, Chow E, Tommy WS. A new shifting grid clustering algorithm[J]. PatternRecognition,2004,37(3):503514.
[151] Nanni M,Pedreschi D. Time-Focused clustering of trajectories of moving objects. Journal ofIntelligent Information Systems,2006,27(3):267289
[152] Pilevar AH,Sukumar M. GCHL: A grid-clustering algorithm for high-dimensional very largespatial data bases. Pattern Recognition Letters,2005,26(7):9991010.
[153]梅长林,周家良.实用统计方法[M].科学出版社,2003:53-65.
[154]曲吉林.时间序列挖掘中索引与查询技术的研究[博士学位论文],天津大学,2006.
[155]韩力群等.人工神经网络理论、设计及其应用[M].北京:化学工业出版社,2002.
[156]丛爽等.面向MATLAB工具箱的神经网络理论与应用(第2版)[M].合肥:中国科学技术大学出版社,2003.
[157]张代远.神经网络新理论与方法[M].北京:清华大学出版社,2005.
[158] J M Duncan. Applieation of Numerical analysis for Tunnelling Intemational Jkunral forNumerical&Analytical[J]. Methods in Geoteenies, Vol.15,1991,223-239.
[159]郑余朝,仇文革.重叠隧道结构内力演变的三维弹塑性数值模拟[J].西南交通大学学报,2006,41(3):376-380.
[160]徐波,吴智敏.混凝土中锚杆荷载传递机理的理论分析[J].哈尔滨工业大学学报,2006,(03)
[161]郑卫锋,邵龙潭,贾金青.深基坑预应力锚杆锚固段应力分布规律与应用[J].辽宁工程技术大学学报(自然科学版),2008,(06)
[162]刘汉东,高磊,李国维. GFRP锚杆锚固机理试验研究[J].华北水利水电学院学报,2007(3)
[163]刘洪洲,黄伦海.连拱隧道设计与施工技术研究现状[J].西部探矿工程,2001.13:54-55.
[164]李强,曾德清.盾构施工中垂直交叉隧道变形的三维有限元分析[J].岩土力学.2001.22(3):334-338.
[165]张玉军,朱维申,杨家岭.近距离双隧道开挖与支护稳定性的黏弹塑性有限元计算[J].岩石力学与工程学报.1999，18(增刊):855-859.
[166]王明年，李志业，刘智成，等.软弱围岩3孔小间距平行浅埋隧道施工力学研究[J].铁道建筑技术,2002,(4):11-14.
[167]靳晓光，刘伟，郑学贵，等.小净距偏压公路隧道开挖顺序优化[J].公路交通科技，2005，22(8)：61-64.
[168]林刚,何川.连拱隧道施工全过程地层沉降三维数值模拟[J]．公路，2004,(3)：136-140.
[169]邓少军,阳军生,张学民等.浅埋偏压连拱隧道施工数值模拟及方案比选[J].地下空间与工程学报，2002,1(6)：944-947.
[170] Soliman E, Duddeck H, Ahens H. Two and three dimensional analysis of closely spaceddouble-tube tunnels[J]. Tunnelling and Underground Space Technology,1993,8(1):13－18.
[171] Galli G, Grimaldi A, Leonardi A. Three-dimensional modeling of tunnel excavation andlining[J]. Computers and Geotechnics,2004,31:171－183.
[172]王戍平.隧道施工方法有限元分析[D].杭州:浙江大学,2004.
[173]徐干成,白洪才,郑颖人.地下工程支护结构[M].北京:中国水利水电出版社,2002
[174]于远祥,谷拴成,韩荣刚.隧道开挖对临近墩基础承载力影响的数值模拟分析[J].西安科技大学学报,2009,29(4):427-431.
[175]赖金星.软岩双连拱公路隧道力学性状测试与施工过程仿真分析[D].西安:长安大学,2003.
[176]刘彤.双连拱隧道施工过程有限元分析[D].西安:西安建筑科技大学,2003.
[177]郑雨天.岩石力学的弹塑粘性理论基础[M].北京:煤炭工业出版社,1988.
[178]袁文伯,陈进.软化岩层中巷道的塑性区与破碎区分析[J].煤炭学报,1986,3:77-86.
[179]刘夕才,林韵梅.软岩巷道弹塑性变形的理论分析[J].岩土力学,1994,15(2):27-36.
[180]马念杰,张益东.圆形巷道围岩变形压力新解法[J].岩石力学与工程学报,1996,15(1):84-89.
[181] SHARAN S K. Elastic-brittle-plastic analysis of circular openings in Hoek-Brown media[J].International Journal of Rock Mechanics and Mining Sciences,2003,40(6):817-824.
[182] BROWN E T, BRAY J W, LADANYI B, et al. Ground response curves for rock tunnels[J].Journal of Geotechnical Engineering,1983,109(1):15-39.
[183] WANG Y. Ground response of circular tunnel in poorly consolidated rock[J]. Journal ofGeotechnical Engineering,1996,122(9):703-708.
[184] CARRANZA-TORRES C, FAIRHURST C. General formulation of the elastic-plasticresponse of openings in rock using the Hoek-Brown failure criterion[J]. International Journal ofRock Mechanics and Mining Sciences,1999,36(6):777-809.
[185] SHARAN S K. Exact and approximate solutions for displacements around circular openings inelastic-brittle-plastic Hoek-Brown rock[J]. International Journal of Rock Mechanics and MiningSciences,2005,42(4):542-549.
[186] SHARAN S K. Analytical solutions for stresses and displacements around a circular openingsin a generalized Hoek-Brown rock[J]. International Journal of Rock Mechanics and Mining Sciences,2008,45(1):78-85.
[187]武波,马玉祥.专家系统[M].北京：北京理工大学出版社，2000.
[188]吴今培,肖健华.智能故障诊断与专家系统[M].北京:科学出版社,1997:1-5.
[189]王建华,黄河清.面向PLC控制系统的故障诊断专家系统[J].微特电机,2004,(1):34-36.
[190]余世林,朱国宝,邓军,等.基于规则推理的船艇柴油机故障诊断专家系统[J].船海工程,2005(2):240-242.
[191]王俊国,尹泉,万淑芸.基于规则的机车柴油机故障诊断专家系统[J].武汉理工大学学报,2003(6):2785-2787.
[192]张代胜,王月,陈朝阳.融合实例与规则推理的车辆故障诊断专家系统[J].机械工程学报,2002(7):291-295.
[193]陈祥光,裴旭东.人工神经网络技术及应用[M].北京:中国电力出版社,2003
[194]虞和济,陈长征,张省等.基于神经网络的智能诊断[M].北京:冶金工业出版社,2000.
[195]丁明军,宋丹.基于神经网络的数控机床故障诊断专家系统[J].机电工程,2007,24(5):92-94
[196]张建民,王涛,王忠礼.智能控制原理及应用[M].北京:冶金工业出版社,2003:123-124.