基于机器学习和模态参数识别理论的水工结构损伤诊断方法研究
|
摘要
基于结构模态参数识别理论的损伤诊断技术是现阶段水利水电工程研究中的热点问题之一。水工结构在实际运营中,由于设计、施工等先天缺陷或者使用载荷超出设计以及遭受强大的突加外在荷载(如地震作用等)的作用会使结构物出现不同程度的损伤,结构发生损伤以后将严重影响结构的承载力及耐久性,甚至会发生严重的工程事故,不仅造成重大的人员伤亡和经济损失,而且还会产生极坏的社会影响。因此,为了保证结构的安全性、完整性和耐久性,需采用有效的手段对结构的健康状态进行诊断。常规的一些结构损伤诊断方法,由于其本身的缺陷而不适用于水利水电工程。鉴于水工结构流激振动响应的获取较为容易,且不会对结构产生不良影响,利用结构在流激振动下的实测响应对结构进行模态参数识别,进而借助于机器学习理论强大的学习功能对结构的损伤进行诊断无疑是一种很好的方法。本文针对流激振动下基于机器学习和模态参数识别理论的水工结构损伤诊断方法进行了研究,主要得到以下创新性的研究成果:
(1)提出了泄流振动下基于带通滤波的水工结构模态参数识别方法。即通过分析结构的特点和结构自振频率的范围,首先应用带通滤波的方法对信号进行预处理,提取出信号中感兴趣的部分,然后应用时域方法进行识别。工程实例表明:该种方法能够很好的对流激振动下水工结构的自振频率进行识别。
(2)提出了水工结构模态参数的遗传识别方法。借助于遗传算法强大的全局寻优能力,将遗传算法应用到水工结构模态参数识别中来。由于该方法以结构的噪声为研究对象,所以其在提高结构自振频率识别精度的同时,在一定程度上也提高了阻尼比的识别精度。最后,通过工程实例表明了这种算法的有效性。
(3)提出了基于机器学习理论和模态分析的水工结构损伤诊断方法。在结构模态参数识别的基础上,通过有限元计算各种损伤状态下的耦合动力特性,以构造支持向量机(SVM)学习的样本库,建立基于支持向量机(SVM)的结构损伤定位及损伤程度诊断方法。即通过支持向量机的二次优化问题求解,以保证小样本情况下机器学习得到的解是全局最优解,避免了人工神经网络等方法的网络结构难于确定、过学习、欠学习以及局部最小化等问题。以最小二乘线性系统作为损失函数,代替传统的支持向量机采用的二次规划方法。较成功地解决了泄流结构(特别是水下部位)损伤定位和损伤定量难的问题。
(4)流激振动下基于水工结构模态参数识别的损伤诊断方法能够有效地节约资源,且识别结果可靠。本文首次提出将其应用到水利水电工程中来。以青铜峡坝体结构三大条贯穿性裂缝为研究对象,通过对现场采集信号的分析、模态参数识别和有限元计算,得出在裂缝深度为自基础向上22m左右,最后,就结构损伤发生后的安全性进行了分析。
The structural damage diagnosis based on the modal parameter identification is one of issues nowadays in hydraulic structure. The hydraulic structure in the actual operations will be to some extent damaged caused by the design, construction, and the other defects or the load in excess of the design and the sudden powerful external load (such as earthquake, etc.). After happening in a certain degree, the structure damage will have a bad effect on the load capacity and durability greatly or even cause the serious accidents. Thus, it caused not only the significant casualties and economic losses but also a very bad social influence. Therefore, in order to ensure the structural safety, integrity and durability of the structure, some effective measures should be taken to fulfill the health diagnosis. Some conventional structural damage diagnostic methods, due to its own shortcomings, are not fit for the hydropower project. Whereas the response of the structure is easy to be gained under flow-induced vibration and has no negative impacts on the structure, it is no doubt that the modal parameter identification in the use of flow-induced vibration is a good method with the help of the machine learning theory. With the theory of the machine learning and the modal parameter identification and diagnostic methods under flow-induced vibration hydropower structure taken into research, the paper involves the following major research results of innovations:
(1) It puts forward the modal parameter identification methods based on band-pass filter and discharge vibration, i.e., according to the analysis of the structural characteristics and the natural frequency, the signals are preprocessed by the band-pass filter. After extracted the interesting signals, the time domain method is used to identify the modal parameter. The results show that the methods can efficiently identify the structure natural frequency in the vibration on the discharge.
(2) The genetic algorithm is applied in the modal parameters identification of the hydraulic structure, considering its global optimization. The genetic identification method used in hydraulic structure modal parameters is come up with. Because the measurement noise is taken into the research, not only is the identification accuracy of natural frequencies improved, but also the damping ratio’s identification accuracy does to a certain extent. Finally, the result shows that the efficiency of the structure’s natural frequency and damping ration is tested.
(3) The damage identification method is proposed based on the machine learning theory and modal analysis of the guide wall structural. On the basis of the modal parameters identification, the coupling dynamic characteristics of the structure are calculated by the finite element method so as to construct the sample of the Support Vector Machine (SVM). The damage diagnoses method including the damage position and based on the establishment of Support Vector Machine (SVM) and the damage ration. That is to say, the Support Vector Machine can ensure the global optimal solution in the small sample of events through its quadratic optimization problem solved. It overcomes such the shortcomings caused by the artificial neural network methods as the difficulties in defining the network structure, the over fitting, under fitting and local minimum. Instead of the traditional support vector machines which use quadratic programming method, least-squares linear system is used as the loss function. Thus the problems such as damage positioning and damage degrees are solved successfully in the discharge structure (especially the underwater part).
(4) Some of the main advantages of the damage diagnoses method, based on the discharge vibration and parameter identification, over other ones is that it is effectively helpful to save resources and get reliable recognition results. The paper first proposes damage diagnosis method based on the dynamic parameters identification and applies it to the hydraulic structure. Taking the three cross crack in Qing Tongxia as the research object and making the comprehensive analysis of signal collecting, modal identification and the finite element calculation, it concludes that the cross crack is 22m. Finally, the analysis of the safety is performed after the structure damages occur.
(1)提出了泄流振动下基于带通滤波的水工结构模态参数识别方法。即通过分析结构的特点和结构自振频率的范围,首先应用带通滤波的方法对信号进行预处理,提取出信号中感兴趣的部分,然后应用时域方法进行识别。工程实例表明:该种方法能够很好的对流激振动下水工结构的自振频率进行识别。
(2)提出了水工结构模态参数的遗传识别方法。借助于遗传算法强大的全局寻优能力,将遗传算法应用到水工结构模态参数识别中来。由于该方法以结构的噪声为研究对象,所以其在提高结构自振频率识别精度的同时,在一定程度上也提高了阻尼比的识别精度。最后,通过工程实例表明了这种算法的有效性。
(3)提出了基于机器学习理论和模态分析的水工结构损伤诊断方法。在结构模态参数识别的基础上,通过有限元计算各种损伤状态下的耦合动力特性,以构造支持向量机(SVM)学习的样本库,建立基于支持向量机(SVM)的结构损伤定位及损伤程度诊断方法。即通过支持向量机的二次优化问题求解,以保证小样本情况下机器学习得到的解是全局最优解,避免了人工神经网络等方法的网络结构难于确定、过学习、欠学习以及局部最小化等问题。以最小二乘线性系统作为损失函数,代替传统的支持向量机采用的二次规划方法。较成功地解决了泄流结构(特别是水下部位)损伤定位和损伤定量难的问题。
(4)流激振动下基于水工结构模态参数识别的损伤诊断方法能够有效地节约资源,且识别结果可靠。本文首次提出将其应用到水利水电工程中来。以青铜峡坝体结构三大条贯穿性裂缝为研究对象,通过对现场采集信号的分析、模态参数识别和有限元计算,得出在裂缝深度为自基础向上22m左右,最后,就结构损伤发生后的安全性进行了分析。
The structural damage diagnosis based on the modal parameter identification is one of issues nowadays in hydraulic structure. The hydraulic structure in the actual operations will be to some extent damaged caused by the design, construction, and the other defects or the load in excess of the design and the sudden powerful external load (such as earthquake, etc.). After happening in a certain degree, the structure damage will have a bad effect on the load capacity and durability greatly or even cause the serious accidents. Thus, it caused not only the significant casualties and economic losses but also a very bad social influence. Therefore, in order to ensure the structural safety, integrity and durability of the structure, some effective measures should be taken to fulfill the health diagnosis. Some conventional structural damage diagnostic methods, due to its own shortcomings, are not fit for the hydropower project. Whereas the response of the structure is easy to be gained under flow-induced vibration and has no negative impacts on the structure, it is no doubt that the modal parameter identification in the use of flow-induced vibration is a good method with the help of the machine learning theory. With the theory of the machine learning and the modal parameter identification and diagnostic methods under flow-induced vibration hydropower structure taken into research, the paper involves the following major research results of innovations:
(1) It puts forward the modal parameter identification methods based on band-pass filter and discharge vibration, i.e., according to the analysis of the structural characteristics and the natural frequency, the signals are preprocessed by the band-pass filter. After extracted the interesting signals, the time domain method is used to identify the modal parameter. The results show that the methods can efficiently identify the structure natural frequency in the vibration on the discharge.
(2) The genetic algorithm is applied in the modal parameters identification of the hydraulic structure, considering its global optimization. The genetic identification method used in hydraulic structure modal parameters is come up with. Because the measurement noise is taken into the research, not only is the identification accuracy of natural frequencies improved, but also the damping ratio’s identification accuracy does to a certain extent. Finally, the result shows that the efficiency of the structure’s natural frequency and damping ration is tested.
(3) The damage identification method is proposed based on the machine learning theory and modal analysis of the guide wall structural. On the basis of the modal parameters identification, the coupling dynamic characteristics of the structure are calculated by the finite element method so as to construct the sample of the Support Vector Machine (SVM). The damage diagnoses method including the damage position and based on the establishment of Support Vector Machine (SVM) and the damage ration. That is to say, the Support Vector Machine can ensure the global optimal solution in the small sample of events through its quadratic optimization problem solved. It overcomes such the shortcomings caused by the artificial neural network methods as the difficulties in defining the network structure, the over fitting, under fitting and local minimum. Instead of the traditional support vector machines which use quadratic programming method, least-squares linear system is used as the loss function. Thus the problems such as damage positioning and damage degrees are solved successfully in the discharge structure (especially the underwater part).
(4) Some of the main advantages of the damage diagnoses method, based on the discharge vibration and parameter identification, over other ones is that it is effectively helpful to save resources and get reliable recognition results. The paper first proposes damage diagnosis method based on the dynamic parameters identification and applies it to the hydraulic structure. Taking the three cross crack in Qing Tongxia as the research object and making the comprehensive analysis of signal collecting, modal identification and the finite element calculation, it concludes that the cross crack is 22m. Finally, the analysis of the safety is performed after the structure damages occur.
引文
[1]陈德亮,水工建筑物[M].北京:中国水利水电出版社,2001.
[2]吴中如,重大水工混凝土结构病害检测与健康诊断[M].北京:高等教育出版社.2005.
[3]陈德亮,结构损伤检测与诊断的方法研究进展[J].沈阳工业大学学报,2004,26(4):457-460.
[4]王茂龙,结构损伤识别与模型更新方法研究.东南大学博士论文.2003.
[5]陈凯,朱钰机器学习及其相关算法综述[J].统计与信息论坛. 2007(5):105-112.
[6]洪家荣.机器学习—回顾与展望[J].计算机科学.1991.(2):1-8.
[7]董本清.机器学习与支持向量机[J].软件工程师. 2007:41-42
[8]辛宪会,叶秋果,等.小样本机器学习算法的特性分析与应用[J].海洋测绘.2007(3):16-19.
[9]闫友彪,陈元琰.机器学习的主要策略综述[J].计算机应用研究[J].2004.(7):4-13.
[10]李惠彬,大型工程结构模态参数识别技术[M].北京:北京理工大学出版社,2007.
[11]林循泓,振动模态参数识别及其应用[M].南京:东南大学出版社,1990
[12]曹树谦等,振动结构模态分析理论、实验与应用.天津:天津大学出版社,2001.
[13]王柏生,结构损伤检测与识别技术[M].杭州:浙江大学出版社,2000.
[14] Taehyoun Kim ,Frequency-domain Karhunen-loeve method and its application to linear dynamic systems [J].AIAA Journal, 1998, 36(11):2117-2123.
[15] Sirovich, L.and others. An eigenfunction approach to large scale transitional structures in jet flow[J].Physics of Fluids A,1990,2(2):127-136.
[16] Breuer,K.S.,Sirovich,L.The use of the karhunen-loeve procedure for the calculation of linear eigenfunctions [J] .Journal of Computational Physics,1991,96(2):277-296.
[17] Winter, M, and others .Eigenfunction analysis of turbulent mixing phenomena [J].AIAA Journal, 1992, 30(7):1681-1688.
[18] Romanowski ,M.C. Reduced-order unsteady aerodynamic and aero elastic modelusing karhunen-loeve eigenmodes[A].Proceedings of the AIAA Symposium on Multidisciplinary Analysis and Optimization(Bellevue,WA),AIAA, Reston, VA, 1996 , 7-13.
[19] Park,H.M., Lee,M.W.An efficient method of solving the navier-stokes equations for flow control[J].International Journal for Numerical Methods in Engineering,1998,41(6):1133-1151.
[20]李德葆,陆秋海,实验模态分析及其应用[M].北京:科学出版社,2001
[21]刘齐茂.用随机减量法及ITD法识别工作模态参数[J].广西工学院学报,2002,13(4):23-26.
[22] Box G E P, Jenkins G M.Times Series Analysis, Forecasting and Control[M].2nd Editor,1976.
[23] Mergeary M. Least Squares Complex Exponential Method and Global System Parameter Estimations used by Modal Analysis[C].Proc. of the 5nd IMAC,1983,3.
[24]宝志雯.建筑物的脉冲信号分析[J].地震工程与工程振动.1981,1(2):71-87.
[25]宝志雯,陈志鹏.从建筑物的脉冲响应确定其动力特性[J].深圳大学学报(理工版),1986,1:36-49.
[26]曾庆华,张令弥,等.飞行颤振试验数据处理方法及软件研制[J].航空学报,1994,15(2):76-79.
[27]于开平,邹经湘,等.模态参数识别的小波变换方法[J].航空学报,1999,20(4):72-76.
[28]于开平,邹经湘,等.结构系统的时变参数识别方法[J].力学进展,2000,30(3):370-377.
[29]陈隽,徐幼麟.HHT模态参数识别方法在结构模态参数识别中的应用[J].振动工程学报,2003,16(3):383-388.
[30]庞世伟,于开平,邹经湘.识别时变结构模态参数的改进子空间方法[J].应用力学学报,2005,22(2):184-188.
[31]董聪,范立础,等.结构智能健康诊断的理论与方法[J].中国铁道科学.2002,23(1):11-24.
[32]董聪.基于动力特性的结构损伤定位方法[J ] .力学与实践, 1999,20 (4) :62- 63.
[33]张丽卿,韩兵康,等.基于振动的土木工程结构损伤研究进展[J ] .力学与实践, 1999,20 (4) :62- 63.
[34]崔飞,袁万城,史家钧.基于静态应变及位移测量的结构损伤识别法[J].同济大学学报,2000,28(1):5-8.
[35]宗周红,任伟新,等.土木工程结构损伤诊断研究进展[J].土木工程学报,2003,36(5)105-110.
[36]马祥森.基于神经网络的结构破损诊断[D].南京航空航天大学硕士论文.2004.
[37]沈东强.基于神经网络的土木工程结构损伤识别方法研究[D].武汉大学硕士论文.2004.
[38]王军强.基于振动模态分析技术和神经网络的结构损伤监测[D].西北工业大学硕士论文.1999.
[39]王军强.土木工程中结构识别方法的研究[D].大连理工大学博士论文.2002.
[40]易伟建.基于遗传算法的结构损伤诊断研究[J].工程力学.2001.18(2):64-71.
[41] Koh B H,Ray L R.Feedback controller design for sensitivity-based damage localization[J].Journal of Sound and Vibration,2004,273:317—335.
[42] Abdo,M A B,Hori M.A. A Numerical Study of Structural Damage Detection Using Changing in the rotation of mode shape [J].Journal of Sound and Vibration, March, 2002, 251(2):227-239.
[43] A.K.Pandey. Damage Detection from Changes of Curvature Mode Shape. Sound and Vibration[J].1991.145(2):321-332.
[44]郑明刚.曲率模态在桥梁状态监测中的应用[J].振动与冲击,2000(2):81-83.
[45]胡宁.利用测试数据得到的柔度矩阵进行损伤识别[J].现代振动与噪声技术.航空工业出版社.2000.
[46] K.E.Alvin. Extraction of Sub structural Flexibility from Global Frequencies and Mode Shapes. AIAA J.1999, 37(11):1444-1501.
[47]周先雁,沈蒲生.用振动参数识别技术对混凝土框架进行破损评估[J].土木工程学报,1998,31(2):39-45.
[48]王济,胡晓. MATLAB在振动信号处理中的应用[M].北京:中国水利水电出版社,2006.
[49]刘纪文,徐金梧.IIR数字滤波器的计算机设计方法[J].北京科技大学学报.1999,21(1):79-82.
[50]郑忠龙,于飞,等.应用小波分析研究信号消噪[J].青岛化工学院学报,2002,23(4):71-74.
[51]周伟. MATLAB小波分析高级技术[M].西安电子科技大学出版社,2006.
[52]李智录,胡静.卡尔曼滤波回归统计模型及工程应用分析[J].水电自动化与大坝监测,2007,31(1):82-84.
[53]胡建华,徐健健.一种基于遗传算法和卡尔曼滤波的运动目标跟踪方法[J].计算机应用,2007,27(2):916-918.
[54]邓自立.最优滤波理论及其应用[M].哈尔滨:哈尔滨工业大学出版社,2000.
[55]邓自立.卡尔曼滤波与维纳滤波[M].哈尔滨:哈尔滨工业大学出版社,2001.
[56] Simon Haykin.自适应滤波器原理[M].北京:电子工业出版社,2006.
[57]姜常真.信息分析与处理[M].天津:天津大虚出版社,2000
[58]傅志方,华宏星,模态分析理论与应用[M].上海:上海交通出版社,2000
[59]谭冬梅,姚兰,等,振动模态的参数识别综述[J].华中科技大学学报. 2002,19(3):73-78.
[60]曹树谦等,振动结构模态分析理论、实验与应用[M].天津:天津大学出版社,2001.
[61] J.E.Mottershead, M.I.Friswell. Model updating in structural dynamics [J].Joural of Sound and Vibration, 1993, 167(2):343-375.
[62]李国强,李杰.工程结构动力检测理论与应用[M].北京:科学出版社,2002.
[63]李涛.几种基于环境激励的结构损伤识别方法的比较[D].大庆:大庆石油学院硕士学位论文,2007.
[64]李中付,宋汉文,等.基于环境激励的模态参数识别方法综述[J].振动工程学报增刊,2000,13(5):578-585.
[65]郭健.基于小波分析的结构损伤识别方法研究[D].浙江大学博士学位论文.2004.
[66]陈换过.小波变换和神经网络方法在复合材料结构损伤振动检测中的应用[D].合肥:合肥工业大学硕士论文.
[67]王长军.基于小波分析的结构模态参数识别与破损诊断方法研究[D].浙江大学博士学位论文.2004.
[68].Z.Hou, M.Noori, R.St.Amand. Wavelet-based Approach for Structural Damage Detection[J].Journal of engineering mechanics.2000,7:677-683.
[69]周伟. MATLAB小波分析高级技术[M].西安:西安电子科技大学出版社,2006.
[70]李建平,唐远炎.小波分析方法的应用[M].重庆:重庆大学出版社,1999.
[71]李爱萍,段利国,小波分析在信号降噪处理中的应用[J],太原理工大学学报,2001,32(1):69-71
[72]钟佑明.希尔伯特-黄变换局瞬信号分析理论的研究[D].重庆大学博士论文,2002.
[73] Huang .N. and others. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-station time series analysis [J] .Proc.R.Soc.1998, 4:903-995.
[74]邓拥军等,EMD方法及Hilbert变换中边界问题的处理,科学通报,2001,46(3):257-263.
[75]罗奇峰,石春香,Hilbert—Huang变换理论及其计算中的问题,同济大学学报,2003,31(6):637-640
[76]石春香,HHT变换及其在结构分析中的应用[D].上海:同济大学博士学位论文,2004.
[77]常鸣,基于HHT技术的结构损伤定位研究[D].南京:南京航空航天大学硕士学位论文,2005.
[78]任春,HHT在结构动力分析中应用的探讨[D].上海:同济大学硕士学位论文,2005.
[79]张郁山,希尔伯特—黄变换(HHT)与地震动时程的希尔伯特谱——方法与应用研究,中国地震局地球物理研究所博士学位论文,2003.
[80] Helong Lia, Xiaoyan Deng, Hongliang Dai. Structural damage detection using the combination method of EMD and wavelet analysis [J]. Mechanical Systems and Signal Processing.2007, 21: 298-306.
[81]贾民平等,基于时序分析的经验模式分解法及其应用,2004,40(9):54-57.
[82]张辉东.水电站厂房结构的非线性和藕联振动分析与模态参数识别[D].天津大学博士学位论文,2006.
[83]刘波,文忠,曾涯.MATLAB信号处理[M].北京:电子工业出版社.2006.
[84] ArnoJ. van Leest, Martin J. Bastiaans. Gabor’s signal expansion and the Gabor transform on a non-separable time-frequency lattices. Journal of the Franklin Institute [J] .2000,337:291-301.
[85]Liang Tao, H.K.kwan. Parallel Lattice structure of block time-recursive discrete Gabor transform and its inverse transform.Signal Processing [J] .2007, 337:1-8.
[86] Taehyoun Kim ,Frequency-domain Karhunen-loeve method and its application to linear dynamic systems [J].AIAA Journal, 1998, 36(11):2117-2123
[87]张志谊,续秀忠,等.基于信号时频分解的模态参数识别[J].振动工程学报,2002,15(4):389-394.
[88]李敏强,寇纪松,等.遗传算法的基本理论与应用[M].北京:科学出版社,2002.
[89]王小平,曹立明.遗传算法理论、应用与软件实现[M].西安:西安交通大学出版社, 2002.
[90]玄光南,程润伟.遗传算法与工程实现[M].北京:科学出版社,2002.
[91]马斌.遗传算法在初始地应力场分析中的应用[D].天津:天津大学硕士论文.2003.
[91]王春华,邹少军,青铜峡大坝电站坝段三大条贯穿性裂缝及3#胸墙裂缝处理.大坝与安全,1998(14):61-65.
[92]吴子平,吴中如,等,青铜峡大坝电站坝段变形性态及裂缝物理成因分析.大坝观测与土工测试,2001,25(1):25-27,45.
[93]练继建,黄河李家峡水电站双排机组真机试验研究[R].天津:天津大学水利水电工程系,2004.
[94]练继建,田会静,秦亮等,停机过程中水电站厂房支承结构动力特性识别方法[J].中国工程科学, 2006,8(4):72-75.
[95]练继建,秦亮,双排机水电站厂房结构动力特性研究[J].水力发电学报2004.23(2):55-60.
[96]郭巍,基于应变及应变模态变化率的薄板损伤数值分析,大庆石油学院硕士学位论文,2006.
[97]顾培英,陈厚群,等.用应变模态技术诊断梁结构的损伤[J].地震工程与工程振动,2005,25(4):50-53.
[98]刘娟,黄维平.二重结构编码遗传算法在传感器配置中的应用[J].振动、测试与诊断.2004,24(4):281-284.
[99]邹晓军,梁桥结构损伤识别的曲率模态技术[D].武汉:武汉理工大学硕士学位论文,2003.
[100]杨华.基于柔度矩阵法的结构损伤识别[J].长春理工大学学报.2005,28(4):22-23.
[101]陈孝珍.基于结构动力响应的结构损伤诊断[J].科学技术与工程.2004,4(3):176-180.
[102]胡少伟,苗同臣编,结构振动理论及其应用,北京:中国建筑工业出版社,2005.
[103]刘龙.基于曲率模态和支持向量机的结构损伤位置的两步识别方法[J].工程力学增刊.2006,23:35-45.
[104]谭东宁.小样本机器学习理论:统计学习理论[J].南京理工大学学报.2001,25(1):108-112.
[105] Vapnik V N,Levin E,Le C Y. Measuring the VC-dimension of a learning machine[J]. Neural Computation,1994,(6):851～876.
[106] Everett J G,Thompson W S. Experience Modification Rating For Workers’Compensation Insurance[J]. Journal of Construction Engineering and Management,1995,121(1):66～78.
[107] Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Disco-very,1998,2 (2):57～60.
[108] Cortes C,Vapnik V. Support-vector networks[J]. Machine Learning,1995,20:273～297.
[109] Scholkopf B,Burges C,Vapnik V N. Extracting support data for a given task. In:Fayyad U MUthurusamy R(eds.). Proc. Of First Intl. Conf. On Knowledge Discovery & Data Mining,AAA I Press,1995:262～267.
[110] Vapnik V N,Golowich S,Smola A. Support vector method for function approximation,regression estimation,and signal processing. In:Mozer M,Jordan M,Petsche T (eds)[C]. Neural Information,2003.
[111] Muller K-R,Smola A J,Ratsch G,et al. Predicting time series with support vector machines.In:Proc. of ICANN'97[C],Springer Lecture Notes in Computer Science,1997,999～1005.
[112] Zhang H B,Zhong P, Zhang C H. The Newton-PCG Algorithm via Automatic Differentiation. OR Transaction,2003,7(1):28～38.
[113] Bartlett P L. The sample complexity of pattern classification with neural network: the size of the weights is more important than the size of network[J]. IEEE Transactions on Information Theory,1998,44(2):525～536.
[114] Scholkopf B,Smola A,MllerK-R. Nonlinear componen tanalysis as kernel eigenvalue problem[J].
[115] Scholkopf B,Sung K-K,Burges C,et al. Comparing support vector machines with Gaussian kernels to radial basis function classifiers[C]. IEEE Trans. On Signal Processing,1997,45(11):2758～2765.
[116] Zhang XG. Using class-center vectors to build support vector machines[C].Madison:Proc. Of NNSP'99,1999.
[117]郭琳,孙伟,魏建军.基于BP神经网络算法的土木结构损伤检测研究[J].华东交通大学学报.2007,24(4):39-42.
[118]杨杰,李爱群,缪长青.BP神经网络在大跨斜拉桥的斜拉索损伤识别中的应用[J].土木工程学报.2006,39(5):72-95.
[119]郄志红.大坝安全监测资料正反分析的智能软计算方法及其应用[J],天津:天津大学博士学位论文,2005.
[120] Cherkassky V,Mulier F. Learning from Data: Concepts,Theory and Methods[M]. NY: John Viley& Sons,1997.
[121]张恒喜,郭基联,朱家元,等.小样本多元数据分析方法及应用[M].西安:西安工业大学出版,2002.
[122] Zhu J Y,Ren B,Zhang H X,et al. Time Series Prediction via New Support Vector Machines[C].Beijing:IEEE In proceedings of ICMLC2002,2002.
[123] Zhu J Y,Shang B L,Zhang H X. An Improve Fast Classification Algorithm Based on Learning Vector Quantization[C]. Chengdu:In proceedings of international conference on modeling and simulating of complex system, 2002.
[124]张学工.统计学习理论的本质[M].北京:清华大学出版社,2000.
[125]刘江华,程君实,陈佳品.支持向量机训练算法综述[J].信息与控制,2002,31(1),45～50.
[126]朱国强,刘士荣,俞金寿.支持向量机及其在函数逼近中的应用[J].华东理工大学学报,2002 28(2),555～559.
[127]肖健华,吴今培.样本数目不对称时的SVM模型[J].计算科学,2003,30(2):165～167.
[128]Ren-Jeng Lin, Fu-Ping Cheng. Multiple crack identification of a free-free beam with uniform material property variation and varied noised frequency [J]. Engineering Structure, 2007, 1-21
[129]余昆,倪海波,唐小兵.基于神经网络和遗传算法结合的桥梁结构损伤诊断[J].武汉理工大学学报(交通科学与工程版).2006,30(2):279-281.
[130]崔光涛,练继建等.水流动力荷载与流固相互作用[M].北京:中国水利水电出版社.1999.
[131]李建中,宁利中.高速水力学[M].北京:清华大学出版社,2000.
[132]顾冲时,马福衡,吴中如等.青铜峡大坝电站坝段变形“疑点”的物理成因分析,大坝与安全,1998,4:38-43.
[133]马福恒,吴中如,顾冲时等.综合分析法研究特殊坝体结构的变形规律,河海大学学报,1999,27(1):103-108.
[134]黄正道,唐平.青铜峡水电站大坝安全定期检查与补强消缺,水力发电,1999,8:48-50.
[135]刘广林,陶来顺等,青铜峡大坝变形监测系统,大坝观测与变形监测系统,1996,20(1):16-19.
[136]单宇翥,胡连军,贾恩红,陈雪峰,邹少军等,青铜峡水工泄水建筑物混凝土缺陷水下补强加固,大坝与安全,2002(1):39-43.
[137]潘毅群,夏峰等,青铜峡大坝安全运行管理,大坝与安全,1998(4):16-20
[138]孔繁全,宁夏的“龙头”工程、塞上江南的一颗明珠,中国电力,1995(7):66-67.
[139]马福恒,王仁钟,吴中如,顾冲时,等.模糊控制的预测模型及其应用,大坝观测与土工测试,2001,25(2):17-20.
[140]孙小鹏.脉动压力的随机数学模拟[J].水利学报,1991(5):52-56.
[141]孙小鹏,薛盘珍,吕家才.泄流压力脉动及其概化设计[J].水动力学研究与进展,1997,12(1):102-112.
[2]吴中如,重大水工混凝土结构病害检测与健康诊断[M].北京:高等教育出版社.2005.
[3]陈德亮,结构损伤检测与诊断的方法研究进展[J].沈阳工业大学学报,2004,26(4):457-460.
[4]王茂龙,结构损伤识别与模型更新方法研究.东南大学博士论文.2003.
[5]陈凯,朱钰机器学习及其相关算法综述[J].统计与信息论坛. 2007(5):105-112.
[6]洪家荣.机器学习—回顾与展望[J].计算机科学.1991.(2):1-8.
[7]董本清.机器学习与支持向量机[J].软件工程师. 2007:41-42
[8]辛宪会,叶秋果,等.小样本机器学习算法的特性分析与应用[J].海洋测绘.2007(3):16-19.
[9]闫友彪,陈元琰.机器学习的主要策略综述[J].计算机应用研究[J].2004.(7):4-13.
[10]李惠彬,大型工程结构模态参数识别技术[M].北京:北京理工大学出版社,2007.
[11]林循泓,振动模态参数识别及其应用[M].南京:东南大学出版社,1990
[12]曹树谦等,振动结构模态分析理论、实验与应用.天津:天津大学出版社,2001.
[13]王柏生,结构损伤检测与识别技术[M].杭州:浙江大学出版社,2000.
[14] Taehyoun Kim ,Frequency-domain Karhunen-loeve method and its application to linear dynamic systems [J].AIAA Journal, 1998, 36(11):2117-2123.
[15] Sirovich, L.and others. An eigenfunction approach to large scale transitional structures in jet flow[J].Physics of Fluids A,1990,2(2):127-136.
[16] Breuer,K.S.,Sirovich,L.The use of the karhunen-loeve procedure for the calculation of linear eigenfunctions [J] .Journal of Computational Physics,1991,96(2):277-296.
[17] Winter, M, and others .Eigenfunction analysis of turbulent mixing phenomena [J].AIAA Journal, 1992, 30(7):1681-1688.
[18] Romanowski ,M.C. Reduced-order unsteady aerodynamic and aero elastic modelusing karhunen-loeve eigenmodes[A].Proceedings of the AIAA Symposium on Multidisciplinary Analysis and Optimization(Bellevue,WA),AIAA, Reston, VA, 1996 , 7-13.
[19] Park,H.M., Lee,M.W.An efficient method of solving the navier-stokes equations for flow control[J].International Journal for Numerical Methods in Engineering,1998,41(6):1133-1151.
[20]李德葆,陆秋海,实验模态分析及其应用[M].北京:科学出版社,2001
[21]刘齐茂.用随机减量法及ITD法识别工作模态参数[J].广西工学院学报,2002,13(4):23-26.
[22] Box G E P, Jenkins G M.Times Series Analysis, Forecasting and Control[M].2nd Editor,1976.
[23] Mergeary M. Least Squares Complex Exponential Method and Global System Parameter Estimations used by Modal Analysis[C].Proc. of the 5nd IMAC,1983,3.
[24]宝志雯.建筑物的脉冲信号分析[J].地震工程与工程振动.1981,1(2):71-87.
[25]宝志雯,陈志鹏.从建筑物的脉冲响应确定其动力特性[J].深圳大学学报(理工版),1986,1:36-49.
[26]曾庆华,张令弥,等.飞行颤振试验数据处理方法及软件研制[J].航空学报,1994,15(2):76-79.
[27]于开平,邹经湘,等.模态参数识别的小波变换方法[J].航空学报,1999,20(4):72-76.
[28]于开平,邹经湘,等.结构系统的时变参数识别方法[J].力学进展,2000,30(3):370-377.
[29]陈隽,徐幼麟.HHT模态参数识别方法在结构模态参数识别中的应用[J].振动工程学报,2003,16(3):383-388.
[30]庞世伟,于开平,邹经湘.识别时变结构模态参数的改进子空间方法[J].应用力学学报,2005,22(2):184-188.
[31]董聪,范立础,等.结构智能健康诊断的理论与方法[J].中国铁道科学.2002,23(1):11-24.
[32]董聪.基于动力特性的结构损伤定位方法[J ] .力学与实践, 1999,20 (4) :62- 63.
[33]张丽卿,韩兵康,等.基于振动的土木工程结构损伤研究进展[J ] .力学与实践, 1999,20 (4) :62- 63.
[34]崔飞,袁万城,史家钧.基于静态应变及位移测量的结构损伤识别法[J].同济大学学报,2000,28(1):5-8.
[35]宗周红,任伟新,等.土木工程结构损伤诊断研究进展[J].土木工程学报,2003,36(5)105-110.
[36]马祥森.基于神经网络的结构破损诊断[D].南京航空航天大学硕士论文.2004.
[37]沈东强.基于神经网络的土木工程结构损伤识别方法研究[D].武汉大学硕士论文.2004.
[38]王军强.基于振动模态分析技术和神经网络的结构损伤监测[D].西北工业大学硕士论文.1999.
[39]王军强.土木工程中结构识别方法的研究[D].大连理工大学博士论文.2002.
[40]易伟建.基于遗传算法的结构损伤诊断研究[J].工程力学.2001.18(2):64-71.
[41] Koh B H,Ray L R.Feedback controller design for sensitivity-based damage localization[J].Journal of Sound and Vibration,2004,273:317—335.
[42] Abdo,M A B,Hori M.A. A Numerical Study of Structural Damage Detection Using Changing in the rotation of mode shape [J].Journal of Sound and Vibration, March, 2002, 251(2):227-239.
[43] A.K.Pandey. Damage Detection from Changes of Curvature Mode Shape. Sound and Vibration[J].1991.145(2):321-332.
[44]郑明刚.曲率模态在桥梁状态监测中的应用[J].振动与冲击,2000(2):81-83.
[45]胡宁.利用测试数据得到的柔度矩阵进行损伤识别[J].现代振动与噪声技术.航空工业出版社.2000.
[46] K.E.Alvin. Extraction of Sub structural Flexibility from Global Frequencies and Mode Shapes. AIAA J.1999, 37(11):1444-1501.
[47]周先雁,沈蒲生.用振动参数识别技术对混凝土框架进行破损评估[J].土木工程学报,1998,31(2):39-45.
[48]王济,胡晓. MATLAB在振动信号处理中的应用[M].北京:中国水利水电出版社,2006.
[49]刘纪文,徐金梧.IIR数字滤波器的计算机设计方法[J].北京科技大学学报.1999,21(1):79-82.
[50]郑忠龙,于飞,等.应用小波分析研究信号消噪[J].青岛化工学院学报,2002,23(4):71-74.
[51]周伟. MATLAB小波分析高级技术[M].西安电子科技大学出版社,2006.
[52]李智录,胡静.卡尔曼滤波回归统计模型及工程应用分析[J].水电自动化与大坝监测,2007,31(1):82-84.
[53]胡建华,徐健健.一种基于遗传算法和卡尔曼滤波的运动目标跟踪方法[J].计算机应用,2007,27(2):916-918.
[54]邓自立.最优滤波理论及其应用[M].哈尔滨:哈尔滨工业大学出版社,2000.
[55]邓自立.卡尔曼滤波与维纳滤波[M].哈尔滨:哈尔滨工业大学出版社,2001.
[56] Simon Haykin.自适应滤波器原理[M].北京:电子工业出版社,2006.
[57]姜常真.信息分析与处理[M].天津:天津大虚出版社,2000
[58]傅志方,华宏星,模态分析理论与应用[M].上海:上海交通出版社,2000
[59]谭冬梅,姚兰,等,振动模态的参数识别综述[J].华中科技大学学报. 2002,19(3):73-78.
[60]曹树谦等,振动结构模态分析理论、实验与应用[M].天津:天津大学出版社,2001.
[61] J.E.Mottershead, M.I.Friswell. Model updating in structural dynamics [J].Joural of Sound and Vibration, 1993, 167(2):343-375.
[62]李国强,李杰.工程结构动力检测理论与应用[M].北京:科学出版社,2002.
[63]李涛.几种基于环境激励的结构损伤识别方法的比较[D].大庆:大庆石油学院硕士学位论文,2007.
[64]李中付,宋汉文,等.基于环境激励的模态参数识别方法综述[J].振动工程学报增刊,2000,13(5):578-585.
[65]郭健.基于小波分析的结构损伤识别方法研究[D].浙江大学博士学位论文.2004.
[66]陈换过.小波变换和神经网络方法在复合材料结构损伤振动检测中的应用[D].合肥:合肥工业大学硕士论文.
[67]王长军.基于小波分析的结构模态参数识别与破损诊断方法研究[D].浙江大学博士学位论文.2004.
[68].Z.Hou, M.Noori, R.St.Amand. Wavelet-based Approach for Structural Damage Detection[J].Journal of engineering mechanics.2000,7:677-683.
[69]周伟. MATLAB小波分析高级技术[M].西安:西安电子科技大学出版社,2006.
[70]李建平,唐远炎.小波分析方法的应用[M].重庆:重庆大学出版社,1999.
[71]李爱萍,段利国,小波分析在信号降噪处理中的应用[J],太原理工大学学报,2001,32(1):69-71
[72]钟佑明.希尔伯特-黄变换局瞬信号分析理论的研究[D].重庆大学博士论文,2002.
[73] Huang .N. and others. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-station time series analysis [J] .Proc.R.Soc.1998, 4:903-995.
[74]邓拥军等,EMD方法及Hilbert变换中边界问题的处理,科学通报,2001,46(3):257-263.
[75]罗奇峰,石春香,Hilbert—Huang变换理论及其计算中的问题,同济大学学报,2003,31(6):637-640
[76]石春香,HHT变换及其在结构分析中的应用[D].上海:同济大学博士学位论文,2004.
[77]常鸣,基于HHT技术的结构损伤定位研究[D].南京:南京航空航天大学硕士学位论文,2005.
[78]任春,HHT在结构动力分析中应用的探讨[D].上海:同济大学硕士学位论文,2005.
[79]张郁山,希尔伯特—黄变换(HHT)与地震动时程的希尔伯特谱——方法与应用研究,中国地震局地球物理研究所博士学位论文,2003.
[80] Helong Lia, Xiaoyan Deng, Hongliang Dai. Structural damage detection using the combination method of EMD and wavelet analysis [J]. Mechanical Systems and Signal Processing.2007, 21: 298-306.
[81]贾民平等,基于时序分析的经验模式分解法及其应用,2004,40(9):54-57.
[82]张辉东.水电站厂房结构的非线性和藕联振动分析与模态参数识别[D].天津大学博士学位论文,2006.
[83]刘波,文忠,曾涯.MATLAB信号处理[M].北京:电子工业出版社.2006.
[84] ArnoJ. van Leest, Martin J. Bastiaans. Gabor’s signal expansion and the Gabor transform on a non-separable time-frequency lattices. Journal of the Franklin Institute [J] .2000,337:291-301.
[85]Liang Tao, H.K.kwan. Parallel Lattice structure of block time-recursive discrete Gabor transform and its inverse transform.Signal Processing [J] .2007, 337:1-8.
[86] Taehyoun Kim ,Frequency-domain Karhunen-loeve method and its application to linear dynamic systems [J].AIAA Journal, 1998, 36(11):2117-2123
[87]张志谊,续秀忠,等.基于信号时频分解的模态参数识别[J].振动工程学报,2002,15(4):389-394.
[88]李敏强,寇纪松,等.遗传算法的基本理论与应用[M].北京:科学出版社,2002.
[89]王小平,曹立明.遗传算法理论、应用与软件实现[M].西安:西安交通大学出版社, 2002.
[90]玄光南,程润伟.遗传算法与工程实现[M].北京:科学出版社,2002.
[91]马斌.遗传算法在初始地应力场分析中的应用[D].天津:天津大学硕士论文.2003.
[91]王春华,邹少军,青铜峡大坝电站坝段三大条贯穿性裂缝及3#胸墙裂缝处理.大坝与安全,1998(14):61-65.
[92]吴子平,吴中如,等,青铜峡大坝电站坝段变形性态及裂缝物理成因分析.大坝观测与土工测试,2001,25(1):25-27,45.
[93]练继建,黄河李家峡水电站双排机组真机试验研究[R].天津:天津大学水利水电工程系,2004.
[94]练继建,田会静,秦亮等,停机过程中水电站厂房支承结构动力特性识别方法[J].中国工程科学, 2006,8(4):72-75.
[95]练继建,秦亮,双排机水电站厂房结构动力特性研究[J].水力发电学报2004.23(2):55-60.
[96]郭巍,基于应变及应变模态变化率的薄板损伤数值分析,大庆石油学院硕士学位论文,2006.
[97]顾培英,陈厚群,等.用应变模态技术诊断梁结构的损伤[J].地震工程与工程振动,2005,25(4):50-53.
[98]刘娟,黄维平.二重结构编码遗传算法在传感器配置中的应用[J].振动、测试与诊断.2004,24(4):281-284.
[99]邹晓军,梁桥结构损伤识别的曲率模态技术[D].武汉:武汉理工大学硕士学位论文,2003.
[100]杨华.基于柔度矩阵法的结构损伤识别[J].长春理工大学学报.2005,28(4):22-23.
[101]陈孝珍.基于结构动力响应的结构损伤诊断[J].科学技术与工程.2004,4(3):176-180.
[102]胡少伟,苗同臣编,结构振动理论及其应用,北京:中国建筑工业出版社,2005.
[103]刘龙.基于曲率模态和支持向量机的结构损伤位置的两步识别方法[J].工程力学增刊.2006,23:35-45.
[104]谭东宁.小样本机器学习理论:统计学习理论[J].南京理工大学学报.2001,25(1):108-112.
[105] Vapnik V N,Levin E,Le C Y. Measuring the VC-dimension of a learning machine[J]. Neural Computation,1994,(6):851～876.
[106] Everett J G,Thompson W S. Experience Modification Rating For Workers’Compensation Insurance[J]. Journal of Construction Engineering and Management,1995,121(1):66～78.
[107] Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Disco-very,1998,2 (2):57～60.
[108] Cortes C,Vapnik V. Support-vector networks[J]. Machine Learning,1995,20:273～297.
[109] Scholkopf B,Burges C,Vapnik V N. Extracting support data for a given task. In:Fayyad U MUthurusamy R(eds.). Proc. Of First Intl. Conf. On Knowledge Discovery & Data Mining,AAA I Press,1995:262～267.
[110] Vapnik V N,Golowich S,Smola A. Support vector method for function approximation,regression estimation,and signal processing. In:Mozer M,Jordan M,Petsche T (eds)[C]. Neural Information,2003.
[111] Muller K-R,Smola A J,Ratsch G,et al. Predicting time series with support vector machines.In:Proc. of ICANN'97[C],Springer Lecture Notes in Computer Science,1997,999～1005.
[112] Zhang H B,Zhong P, Zhang C H. The Newton-PCG Algorithm via Automatic Differentiation. OR Transaction,2003,7(1):28～38.
[113] Bartlett P L. The sample complexity of pattern classification with neural network: the size of the weights is more important than the size of network[J]. IEEE Transactions on Information Theory,1998,44(2):525～536.
[114] Scholkopf B,Smola A,MllerK-R. Nonlinear componen tanalysis as kernel eigenvalue problem[J].
[115] Scholkopf B,Sung K-K,Burges C,et al. Comparing support vector machines with Gaussian kernels to radial basis function classifiers[C]. IEEE Trans. On Signal Processing,1997,45(11):2758～2765.
[116] Zhang XG. Using class-center vectors to build support vector machines[C].Madison:Proc. Of NNSP'99,1999.
[117]郭琳,孙伟,魏建军.基于BP神经网络算法的土木结构损伤检测研究[J].华东交通大学学报.2007,24(4):39-42.
[118]杨杰,李爱群,缪长青.BP神经网络在大跨斜拉桥的斜拉索损伤识别中的应用[J].土木工程学报.2006,39(5):72-95.
[119]郄志红.大坝安全监测资料正反分析的智能软计算方法及其应用[J],天津:天津大学博士学位论文,2005.
[120] Cherkassky V,Mulier F. Learning from Data: Concepts,Theory and Methods[M]. NY: John Viley& Sons,1997.
[121]张恒喜,郭基联,朱家元,等.小样本多元数据分析方法及应用[M].西安:西安工业大学出版,2002.
[122] Zhu J Y,Ren B,Zhang H X,et al. Time Series Prediction via New Support Vector Machines[C].Beijing:IEEE In proceedings of ICMLC2002,2002.
[123] Zhu J Y,Shang B L,Zhang H X. An Improve Fast Classification Algorithm Based on Learning Vector Quantization[C]. Chengdu:In proceedings of international conference on modeling and simulating of complex system, 2002.
[124]张学工.统计学习理论的本质[M].北京:清华大学出版社,2000.
[125]刘江华,程君实,陈佳品.支持向量机训练算法综述[J].信息与控制,2002,31(1),45～50.
[126]朱国强,刘士荣,俞金寿.支持向量机及其在函数逼近中的应用[J].华东理工大学学报,2002 28(2),555～559.
[127]肖健华,吴今培.样本数目不对称时的SVM模型[J].计算科学,2003,30(2):165～167.
[128]Ren-Jeng Lin, Fu-Ping Cheng. Multiple crack identification of a free-free beam with uniform material property variation and varied noised frequency [J]. Engineering Structure, 2007, 1-21
[129]余昆,倪海波,唐小兵.基于神经网络和遗传算法结合的桥梁结构损伤诊断[J].武汉理工大学学报(交通科学与工程版).2006,30(2):279-281.
[130]崔光涛,练继建等.水流动力荷载与流固相互作用[M].北京:中国水利水电出版社.1999.
[131]李建中,宁利中.高速水力学[M].北京:清华大学出版社,2000.
[132]顾冲时,马福衡,吴中如等.青铜峡大坝电站坝段变形“疑点”的物理成因分析,大坝与安全,1998,4:38-43.
[133]马福恒,吴中如,顾冲时等.综合分析法研究特殊坝体结构的变形规律,河海大学学报,1999,27(1):103-108.
[134]黄正道,唐平.青铜峡水电站大坝安全定期检查与补强消缺,水力发电,1999,8:48-50.
[135]刘广林,陶来顺等,青铜峡大坝变形监测系统,大坝观测与变形监测系统,1996,20(1):16-19.
[136]单宇翥,胡连军,贾恩红,陈雪峰,邹少军等,青铜峡水工泄水建筑物混凝土缺陷水下补强加固,大坝与安全,2002(1):39-43.
[137]潘毅群,夏峰等,青铜峡大坝安全运行管理,大坝与安全,1998(4):16-20
[138]孔繁全,宁夏的“龙头”工程、塞上江南的一颗明珠,中国电力,1995(7):66-67.
[139]马福恒,王仁钟,吴中如,顾冲时,等.模糊控制的预测模型及其应用,大坝观测与土工测试,2001,25(2):17-20.
[140]孙小鹏.脉动压力的随机数学模拟[J].水利学报,1991(5):52-56.
[141]孙小鹏,薛盘珍,吕家才.泄流压力脉动及其概化设计[J].水动力学研究与进展,1997,12(1):102-112.
© 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 |