模式识别在工程结构振动损伤识别中的应用
|
摘要
工程结构与人类的生活息息相关，工程结构的质量问题不仅关系到人民的生命财产
安全，而且还会带来社会财富的巨大损失。但事实上，工程结构往往存在各种各样的缺
陷和损伤。进行结构损伤诊断，可以提高结构的可靠性与安全性，避免重大事故的发生，
减少事故危害性，可以获得潜在的巨大的经济效益和社会效益。
结构损伤检测的方法很多，振动测试技术由于易于实现诊断系统的自动化、小型化，
且理论基础雄厚、分析测试设备完善、诊断结果准确可靠，加上振动诊断具有实时性、
在线性、遥测性、可控性和提取信号的方便性等诸多优点而在工程诊断技术中占主导地
位，在结构损伤诊断中具有广阔的应用前景。
振动诊断的方法很多，常用的有三种：直接分析法,时序分析法和参数识别法。其
中参数识别法直接从测量的输入输出信号识别模态参数或物理参数的变化情况，具有很
大的方便性。基于模态分析的振动诊断技术自 20 世纪 60 年代兴起至今，已在工程领域
得到了广泛的应用。从目前来看，单一模态参数的诊断方法比较常见。而基于模态参数
识别的振动诊断属于动力学的反问题，从数学上看，反问题往往不唯一和不确定，从而
使识别结果可能不唯一，出现误判。所以目前多参量的综合诊断技术已经兴起，模式识
别，人工智能，专家系统等的研究成果为损伤诊断注入了新的活力。其中模式识别是人
工智能的一个重要分支，将模式识别或人工智能的理论和方法应用于结构损伤诊断，发
展智能化的损伤诊断技术已成为当今故障诊断技术的发展的主流。
本文选取悬臂梁作为典型构件，将模式识别理论和方法应用到基于模态分析的振动
诊断技术中，利用由模态参数构造的损伤信息特征量建立损伤模式，对结构损伤的位置
和程度进行分步识别，从而提高了损伤诊断的精度。
Engineering structure is closely linked with human Beings’ life; its
quality problem not only connects to the safety of the people’s life and wealth,
but also causes great loss of social wealth. But engineering structure sometimes
exists many types defects and damage in fact. The reliability and security of
structure can be improved by structural damage detection, the occurrence of
momentous accident can be avoided, the harm degree of accident can be minished,
and the great potential economy benefit and social benefit can be obtained.
There are many kinds of structural damage detection method, but dynamic
damage detection technology is prone to realize automatization and
miniaturization of system, the foundation of its theory is abundant, the
equipment to analyze and test is perfect, the detection result is nicety and
credibility, and dynamic damage detection technology have many abilities, for
example, real time, on line, remote test, controllability and convenience of
picking up signal, so it is in dominant in engineering structural damage
detection technology, it has wide use foreground in structural damage
identification.
There are many kinds of dynamic damage detection methods, there are three
types of methods in common use: direct analytic method, time order analytic
method and parameter recognition method. In these three methods, parameter
recognition method recognizes the changes of modal parameter or physical
parameter from metrical input and output signal directly, so it is convenient.
From 1960s to this day, the dynamic damage detection technology based on modal
analysis has been used widely. Detection method based on single modal parameter
is relative common at present. But the dynamic damage detection based on
recognition of modal parameter belongs to “inverse problem” in dynamics,
“inverse problem” sometimes is not single and certain, so the detection result
is likely to be not single, and the wrong detection occurs. So the synthetically
detection technology based on multi-parameter rises, the research production
of pattern recognition, artificial intelligence and expert system etc. infuses
damage detection with fresh energy. In these methods, pattern recognition is
an important embranchment of artificial intelligence, it is a leading direction
in today’s development of damage detection technology to develop
intelligentized technology by appliance of theory and technique of pattern
recognition or artificial intelligence to structural damage detection.
In this paper, cantilever is chosen as typical component, the theory and
technique of pattern recognition is used to the dynamic detection technology
based on modal analysis, damage pattern is established by damage information
eigenvector from modal parameter, the structural damage position and extension
are recognized respectively, consequently precision of detection is improved.
安全，而且还会带来社会财富的巨大损失。但事实上，工程结构往往存在各种各样的缺
陷和损伤。进行结构损伤诊断，可以提高结构的可靠性与安全性，避免重大事故的发生，
减少事故危害性，可以获得潜在的巨大的经济效益和社会效益。
结构损伤检测的方法很多，振动测试技术由于易于实现诊断系统的自动化、小型化，
且理论基础雄厚、分析测试设备完善、诊断结果准确可靠，加上振动诊断具有实时性、
在线性、遥测性、可控性和提取信号的方便性等诸多优点而在工程诊断技术中占主导地
位，在结构损伤诊断中具有广阔的应用前景。
振动诊断的方法很多，常用的有三种：直接分析法,时序分析法和参数识别法。其
中参数识别法直接从测量的输入输出信号识别模态参数或物理参数的变化情况，具有很
大的方便性。基于模态分析的振动诊断技术自 20 世纪 60 年代兴起至今，已在工程领域
得到了广泛的应用。从目前来看，单一模态参数的诊断方法比较常见。而基于模态参数
识别的振动诊断属于动力学的反问题，从数学上看，反问题往往不唯一和不确定，从而
使识别结果可能不唯一，出现误判。所以目前多参量的综合诊断技术已经兴起，模式识
别，人工智能，专家系统等的研究成果为损伤诊断注入了新的活力。其中模式识别是人
工智能的一个重要分支，将模式识别或人工智能的理论和方法应用于结构损伤诊断，发
展智能化的损伤诊断技术已成为当今故障诊断技术的发展的主流。
本文选取悬臂梁作为典型构件，将模式识别理论和方法应用到基于模态分析的振动
诊断技术中，利用由模态参数构造的损伤信息特征量建立损伤模式，对结构损伤的位置
和程度进行分步识别，从而提高了损伤诊断的精度。
Engineering structure is closely linked with human Beings’ life; its
quality problem not only connects to the safety of the people’s life and wealth,
but also causes great loss of social wealth. But engineering structure sometimes
exists many types defects and damage in fact. The reliability and security of
structure can be improved by structural damage detection, the occurrence of
momentous accident can be avoided, the harm degree of accident can be minished,
and the great potential economy benefit and social benefit can be obtained.
There are many kinds of structural damage detection method, but dynamic
damage detection technology is prone to realize automatization and
miniaturization of system, the foundation of its theory is abundant, the
equipment to analyze and test is perfect, the detection result is nicety and
credibility, and dynamic damage detection technology have many abilities, for
example, real time, on line, remote test, controllability and convenience of
picking up signal, so it is in dominant in engineering structural damage
detection technology, it has wide use foreground in structural damage
identification.
There are many kinds of dynamic damage detection methods, there are three
types of methods in common use: direct analytic method, time order analytic
method and parameter recognition method. In these three methods, parameter
recognition method recognizes the changes of modal parameter or physical
parameter from metrical input and output signal directly, so it is convenient.
From 1960s to this day, the dynamic damage detection technology based on modal
analysis has been used widely. Detection method based on single modal parameter
is relative common at present. But the dynamic damage detection based on
recognition of modal parameter belongs to “inverse problem” in dynamics,
“inverse problem” sometimes is not single and certain, so the detection result
is likely to be not single, and the wrong detection occurs. So the synthetically
detection technology based on multi-parameter rises, the research production
of pattern recognition, artificial intelligence and expert system etc. infuses
damage detection with fresh energy. In these methods, pattern recognition is
an important embranchment of artificial intelligence, it is a leading direction
in today’s development of damage detection technology to develop
intelligentized technology by appliance of theory and technique of pattern
recognition or artificial intelligence to structural damage detection.
In this paper, cantilever is chosen as typical component, the theory and
technique of pattern recognition is used to the dynamic detection technology
based on modal analysis, damage pattern is established by damage information
eigenvector from modal parameter, the structural damage position and extension
are recognized respectively, consequently precision of detection is improved.
引文
[1] 周先雁，沈蒲生，程翔云，用振动参数识别技术对混凝土框架进行破损评估，土木
工程学报，1998,4,39～45
[2] 程庆国，我国桥梁工程的成就与展望，中国土木工程学会第八届年会论文集，北京，
机械工业出版社，1998
[3] Bapat A V, Venkatraman N.， New approach for the representation of a point
support in the analysis of plates, Journal of Sound and Vibration, 1988,
120(1), 107～125
[4] Yao C C, Chang K C, Lee C C, Damage diagnosis of steel frames using vibrational
signature anallysis ,Engineering Mechanics, ASCF, 1992, 118(9), 1949～1960
[5] 丁玉兰，石来德，机械设备故障诊断技术，上海科学技术文献出版设，1994
[6] 李佳升，湖南大学硕士学位论文，用振动参数识别技术诊断工程结构损伤的研究，
湖南长沙，湖南大学， 1995 年
[7] Ratcliffe C P, Bagaria W J.， Vibration technique for locating delamination
in a composite beam, AIAA JOURNAL,1998, 36(6), 1074～1077
[8] Kerstems J G M, Vibration of complex structures: the modal constraint method,
Journal of Sound and Vibration, 1981, 76(4), 467～480
[9] 钱管良，顾松年，姜节胜，含裂纹梁的动力特性，航空学报，1989,10(9),448～454
[10] 汪风泉，郑万泔，试验振动分析，南京，江苏科学技术出版社，1987
[11] 屈梁生，何正嘉，机械故障诊断学，上海，上海科学技术出版社，1986
[12] 钱管良，顾松年，姜节胜，含裂纹梁的动力响应,振动工程学报，1989,2(3),78～
85
[13] 虞和济，振动诊断的工程应用，北京，冶金工业出版社，1992
[14] 钱管良，顾松年，姜节胜，在线振动监测与故障诊断的一种新途径，固体力学学
报，1990，11(3),217～228
[15] O.S.Salswtl, Detection of structural damage through changes in frequency,
Engineering Structures, 1997,19(9), 718～723
57
华北工学院学位论文
[16] P.Cawley, R.D.Adams. The location of defects in structure from measurements
of natural frequencies, Journal of Strain Analysis, 1979,14(2), 49～57
[17] 陈素文，李国强。人工神经网络在结构损伤识别中的应用，振动、测试与诊断，
2001,21(2),116～123
[18] Y.Narkis, Identification of crack location in vibrating simply supported
beams, Journal of Sound and Vibration, 1994,172(4), 549～558
[19] Fox, C.H.J., The location of defects in structures: a comparison of the
use of natural frequency and mode shape data, Proceedings of the 10th MAC,
Saan Dieg, California, 1992, 1, 522～528
[20] Allemang,R.J., Brown, D.L., Correlation Coefficient for Modal Vector
Analysis,Proc.,1st Int.Modal Anal. Conf., Kissimmee, Fla.,110～116
[21] Ewins, D.I., Modal Testing: theory and practice, John Wiley and Sons.Inc.,
1984
[22] 靳晓雄，结构裂纹故障实用振动诊断法初探，振动、测试与诊断，1993,13(2),45～
51
[23] 黄方林，顾松年，结构故障诊断的高阶谱诊断的一种方法，振动工程学报，
1991,3,33～40
[24] 杨叔子，史铁林，丁宏，机械设备诊断的理论技术与方法，振动工程学报，
1992,5(3),193～201
[25] 沈清，汤霖，模式识别导论[M]，国防科技大学出版社，1991 年，1～23
[26] 张开银，余利华，潘传富，板结构裂纹故障的模式识别，武汉汽车工业大学学报，
1997,19(3),80～84
[27] 高宝成，史铁林，杨叔子，一种混凝土简支梁的裂缝识别方法研究，华中理工大
学学报，1997,25(增刊 1)，15～17
[28] 冯辅周，褚福磊，丁汉哲，KL-Bayes 方法在故障模式识别中的应用，振动工程学
报，1999,12(4),499～504
[29] 李艳军，左洪福，吴振锋，基于磨粒分析方法的发动机磨损故障智能诊断技术，
南京航空航天大学学报，2001，33(3),221～226
58
华北工学院学位论文
[30] 张启伟，桥梁健康监测中的损伤特征提取与异常诊断，同济大学学报，
2003,31(3),258～262
[31] Trendafilove I et al. Two statistical pattern recognition methods for damage
localization, Proceedings of 17th IMAC,1999,1380～1386
[32] S.Hoon and K.H.Law, A bayesinan probabilistic approach for structure damage
detection, Earthquake Engre. and Structural Dyn,1997,26(12),1259～1281
[33] 张云波，等，基于神经网络近似结构分析的最佳样板集的研究。华侨大学学报，
2001(4),397～400
[34] 王代华，熊炼，周德高，黄尚廉，基于神经网络的柔性结构损伤模式识别方法,
振动、测试与诊断，2000,20(4),240～297
[35] 翟伟廉，陈超，魏文辉，基于应变模态的刚结构构件焊缝损伤定位方法的研究,世
界地震工程，2002,18(2),1～8
[36] Kirkegaard P H, Rytter A., The use of neural networks for damage detection
and location in a steelmember, Neural Networks and Combinatorial
Optimization in Civil and Structural Engineering, Edinburgh, UK, 1993,1～
9
[37] Wu X, Ghaboussi J, Garrett J H, Use of neural networks in detection of
structural damage,Computers&Structures,1992,42(4),649～659
[38] Elkordy M F, Chang K C, Lee G C, Application of neural networks in vibrational
signature analysis, Journal of Engineering Mechanics,1994,120(2),251～264
[39] Rhim J, Lee S W, A neural network approach for damage detection and
identification of structures, Computational Mechanics, 1995, 16(6), 437～
443
[40] Pandy P C, Barai S V, Multilayer perception in damage detection of bridge
structures, Computers & Structures, 1995, 54(4), 597～608
[41] Mitsuru Nakamura, Masri Sami F, Anatassios G, et al, A method for
nonparametric damage detection through the use of neural networks,
Earthquake Engineering and Structural Dynamics, 1998, 27, 997～1010
59
华北工学院学位论文
[42] Chen S S, Kim S, Neural network based signal monitoring in a smart structural
system, Smart Structures and Materials, 1994:Smart sensing, Processing and
Instrumentation, J.S.Sirkis(ed.), SPIE, 1994, 2191, 176～186
[43] 郭国会，湖南大学硕士学位论文，钢筋混凝土结构破损评估的神经网络方法研究，
湖南，1998
[44] Ceravolo R, Stefano A De, Sabia D, Hierarchical use of neural techniques
in structural damage recognition, Smart Mateials and Structures, 1995, 4,
270～280
[45] Ferregut C, Osegueda R A, Ortiz J, Artificial neural networks for structural
damage detection and classification, Smart Structures and Materials 1995,
Smart Systems for Bridges, Structures, and Highways, L.K.Matthews(ed.),
SPIE, 1995, 2446, 68～80
[46] 于德介，雷慧，用 BP 神经网络诊断结构破损，工程力学，2001,18(1),56～61
[47] 孙宗光，倪一清，高赞明，丁江浩，基于斜拉索振动测量与神经网络技术的斜拉
桥损伤位置识别方法，工程力学，2003,20(3),26～30
[48] 黄苏南，邵惠鹤，基于信息的专家系统理论及应用，控制与决策，1995,10(2),119～
126
[49] 叶文，吕勇哉，沈平，时态覆盖集诊断模型 TGSC，计算机学报，1994,17(5),347～
353
[50] 刘贵立，张国英，薄板裂纹诊断的专家系统，机械强度，2001,23(2),141～143
[51] Edward S.Sazonov, Powsiri Klinkhachorn, Hota V.S.Gangarao and Udaya
B.Halabe, Fuzzy logic expert system for automated damage detection from
changes in strain energy mode shapes, Nondestructive Testing and
Evaluation, 2002 Vol, 18(1), 1～20
[52]J.M.Ko, Z.G.Sun, Y.Q.Ni, Multi-stage identifiacation scheme for detecting
damange in cable-stayed Kap Shui Mun Bridge, Engineering Structures, 2002,
24, 857～868
[53] 吴今培，智能故障诊断与专家系统，北京，科学出版社，1999
60
华北工学院学位论文
[54] 朱大奇，于盛林，基于知识的故障诊断方法综述，安徽工业大学学报，
2002,19(3),197～204
[55] 纪常伟，基于故障树和神经网络的故障诊断技术研究，哈尔滨，哈尔滨工业大学，
1995
[56] 何友，多传感器信息融合及应用，北京，电子工业出版社，2000
[57] 李宏男，李东升，土木工程结构安全性评估、健康监测及诊断述评，地震工程与
工程振动，2002,22(3),82～90
[58] 易伟建，刘霞，结构损伤诊断的遗传算法研究，系统工程理论与实践，2001,5,114～
118
[59] 朱宏平，李斌，利用动态特性测量值的结构损伤检测方法的比较研究，华中科技
大学学报，2002,19(1),48～53
[60] Friswell M L, Penny J E T, Garvey S D,A combined genetic and eigensensitivity
algorithm for the location of damage in structures, Computers &
Structures,1998,69(5),547～556
[61] C.Mares, C.Surace, An application of genetic algorithms to identify damage
in elastic structures, Journal of Sound and Vibration, 1996, 195(2), 195～
215
[62] F.T.K.Au, Y.S.Cheng, L.G.Tham and Z.Z.Bai, Structural damage detection
based on a micro-genetic algorithm using incomplete and noisy modal test
data, Journal of Sound and Vibration, 2003, 259(5), 1081～1094
[63] Wu, M., Tang, Z.H., Gui, W.H., Expert control strategy using neural networks
for electrolytic zinc process, Transaction on Nonferrous Metals Society of
China,2000,10(4),555～560
[64] 刘晓颖，桂卫华，朱爽，等，基于神经网络的动力锅炉故障诊断专家系统，基础
自动化，2001,8(S),55～57
[65] 桂卫华，基于人工智能方法的复杂过程故障诊断技术，控制工程，2002,9(4),1～
6
[66] Anantha Ramn S, Johnson V T, Damage assessment of composite structures—a
61
华北工学院学位论文
fuzzy logic integrated neural network approach, Computer & Structures, 1995,
57(3), 491～502
[67] 韩小云，刘瑞言，基于神经网络和模糊综合评判的梁故障诊断研究，国防科技大
学学报，1996, 18(1), 17～22
[68] 陈文颉，窦丽华，陈杰，杜丽辉，融合多特征信息的模式识别方法，北京理工大
学学报，2002,22(2),173～176
[69] Specht D F, Probabilistic neural networks, Neural Networks, 1990, 3, 109～
118
[70] 王柏生，倪一清，高赞明，用概率神经网络进行结构损伤位置识别，振动工程学
报，2001,14(1),60～64
[71] 杨晓楠，姜绍飞，倪一清，马传政，基于特征向量简化的复杂土木结构损伤检测，
沈阳建筑工程学院学报（自然科学版），2003,19(2),81～84
[72] 姜绍飞，周广师，刘红兢，刘明，考虑不确定性因素的结构损伤检测方法，沈阳
建筑工程学院学报（自然科学版）2002,18(2),85～87
[73] 胡雄，陈兆能，佟德纯，朱继梅，史家钧，多参数监测与模式识别技术在斜拉桥
模型中的应用，上海交通大学学报，2000,34(3),354～359
[74] 李得葆，陆秋海，实验模态分析及其应用，科技出版社，2001 年
[75] 傅志方，振动模态分析与参数辨识[M]，机械工业出版设，1990 年 9 月
[76] 张东利，华北工学院硕士学位论文，建筑结构损伤的振动诊断研究，山西太原，
华北工学院，2002 年
[77] George Hearn, Rene.B, Modal analysis for damage detection in structures,
Journal of Structural Engineering, Vol.117, No.10, October, 1991.
[78] 黄德双，神经网络模式识别系统理论，电子工业出版社，1996 年，1～10
[79] 傅京孙，模式识别应用，北京大学出版社，1990，2～3
[80] Yuen, M.M.F., A numerical study of the eigenparameters of a damaged
cantilever, Journal of Sound and Vibration, 1985,103,301～310
[81] 秦权，张卫国，悬索桥的损伤识别，清华大学学报（自然科学版），
Vol.38,No.12,1998,44～47
62
华北工学院学位论文
[82] Pandy A K,etal.Damage Detection from Changes in Curature Mode Shape,
Journal of Sound and Vibration,1991,145(2),321～332
[83] 董聪，结构损伤识别和定位的基本原理与方法，中国铁道科学，1999,20(3),89～
94
[84] Lieven, N.A.J.,Ewins, D.J.,Spatial Correlation of Mode Shapes, the
Coordinate Modal Assurance Criterion(COMAC), Proc.,6th Int.Modal
Anal.Conf.,Soc.For Experimental Mech.,Bethel,Conn.,690～695
[85] 邓焱，严普强，梁及桥梁应变模态与损伤测量的新方法，清华大学学报（自然科
学版），2000,40(11),123～127
[86] 胡列，姜节胜，顾松年，复合材料层合板故障诊断的一种新方法，振动工程学报，
1991,4(4),54～58
[87] 胡宇宏，结构损伤的动柔度方法，湖南大学学报（自然科学版），2002,29(3),72～
76
[88] Sampaio, Maia, Silva, Damage detection using the frequency response
function curvature method, Journal of Sound and Vibration, 1999, 226(5),
1029～1042
工程学报，1998,4,39～45
[2] 程庆国，我国桥梁工程的成就与展望，中国土木工程学会第八届年会论文集，北京，
机械工业出版社，1998
[3] Bapat A V, Venkatraman N.， New approach for the representation of a point
support in the analysis of plates, Journal of Sound and Vibration, 1988,
120(1), 107～125
[4] Yao C C, Chang K C, Lee C C, Damage diagnosis of steel frames using vibrational
signature anallysis ,Engineering Mechanics, ASCF, 1992, 118(9), 1949～1960
[5] 丁玉兰，石来德，机械设备故障诊断技术，上海科学技术文献出版设，1994
[6] 李佳升，湖南大学硕士学位论文，用振动参数识别技术诊断工程结构损伤的研究，
湖南长沙，湖南大学， 1995 年
[7] Ratcliffe C P, Bagaria W J.， Vibration technique for locating delamination
in a composite beam, AIAA JOURNAL,1998, 36(6), 1074～1077
[8] Kerstems J G M, Vibration of complex structures: the modal constraint method,
Journal of Sound and Vibration, 1981, 76(4), 467～480
[9] 钱管良，顾松年，姜节胜，含裂纹梁的动力特性，航空学报，1989,10(9),448～454
[10] 汪风泉，郑万泔，试验振动分析，南京，江苏科学技术出版社，1987
[11] 屈梁生，何正嘉，机械故障诊断学，上海，上海科学技术出版社，1986
[12] 钱管良，顾松年，姜节胜，含裂纹梁的动力响应,振动工程学报，1989,2(3),78～
85
[13] 虞和济，振动诊断的工程应用，北京，冶金工业出版社，1992
[14] 钱管良，顾松年，姜节胜，在线振动监测与故障诊断的一种新途径，固体力学学
报，1990，11(3),217～228
[15] O.S.Salswtl, Detection of structural damage through changes in frequency,
Engineering Structures, 1997,19(9), 718～723
57
华北工学院学位论文
[16] P.Cawley, R.D.Adams. The location of defects in structure from measurements
of natural frequencies, Journal of Strain Analysis, 1979,14(2), 49～57
[17] 陈素文，李国强。人工神经网络在结构损伤识别中的应用，振动、测试与诊断，
2001,21(2),116～123
[18] Y.Narkis, Identification of crack location in vibrating simply supported
beams, Journal of Sound and Vibration, 1994,172(4), 549～558
[19] Fox, C.H.J., The location of defects in structures: a comparison of the
use of natural frequency and mode shape data, Proceedings of the 10th MAC,
Saan Dieg, California, 1992, 1, 522～528
[20] Allemang,R.J., Brown, D.L., Correlation Coefficient for Modal Vector
Analysis,Proc.,1st Int.Modal Anal. Conf., Kissimmee, Fla.,110～116
[21] Ewins, D.I., Modal Testing: theory and practice, John Wiley and Sons.Inc.,
1984
[22] 靳晓雄，结构裂纹故障实用振动诊断法初探，振动、测试与诊断，1993,13(2),45～
51
[23] 黄方林，顾松年，结构故障诊断的高阶谱诊断的一种方法，振动工程学报，
1991,3,33～40
[24] 杨叔子，史铁林，丁宏，机械设备诊断的理论技术与方法，振动工程学报，
1992,5(3),193～201
[25] 沈清，汤霖，模式识别导论[M]，国防科技大学出版社，1991 年，1～23
[26] 张开银，余利华，潘传富，板结构裂纹故障的模式识别，武汉汽车工业大学学报，
1997,19(3),80～84
[27] 高宝成，史铁林，杨叔子，一种混凝土简支梁的裂缝识别方法研究，华中理工大
学学报，1997,25(增刊 1)，15～17
[28] 冯辅周，褚福磊，丁汉哲，KL-Bayes 方法在故障模式识别中的应用，振动工程学
报，1999,12(4),499～504
[29] 李艳军，左洪福，吴振锋，基于磨粒分析方法的发动机磨损故障智能诊断技术，
南京航空航天大学学报，2001，33(3),221～226
58
华北工学院学位论文
[30] 张启伟，桥梁健康监测中的损伤特征提取与异常诊断，同济大学学报，
2003,31(3),258～262
[31] Trendafilove I et al. Two statistical pattern recognition methods for damage
localization, Proceedings of 17th IMAC,1999,1380～1386
[32] S.Hoon and K.H.Law, A bayesinan probabilistic approach for structure damage
detection, Earthquake Engre. and Structural Dyn,1997,26(12),1259～1281
[33] 张云波，等，基于神经网络近似结构分析的最佳样板集的研究。华侨大学学报，
2001(4),397～400
[34] 王代华，熊炼，周德高，黄尚廉，基于神经网络的柔性结构损伤模式识别方法,
振动、测试与诊断，2000,20(4),240～297
[35] 翟伟廉，陈超，魏文辉，基于应变模态的刚结构构件焊缝损伤定位方法的研究,世
界地震工程，2002,18(2),1～8
[36] Kirkegaard P H, Rytter A., The use of neural networks for damage detection
and location in a steelmember, Neural Networks and Combinatorial
Optimization in Civil and Structural Engineering, Edinburgh, UK, 1993,1～
9
[37] Wu X, Ghaboussi J, Garrett J H, Use of neural networks in detection of
structural damage,Computers&Structures,1992,42(4),649～659
[38] Elkordy M F, Chang K C, Lee G C, Application of neural networks in vibrational
signature analysis, Journal of Engineering Mechanics,1994,120(2),251～264
[39] Rhim J, Lee S W, A neural network approach for damage detection and
identification of structures, Computational Mechanics, 1995, 16(6), 437～
443
[40] Pandy P C, Barai S V, Multilayer perception in damage detection of bridge
structures, Computers & Structures, 1995, 54(4), 597～608
[41] Mitsuru Nakamura, Masri Sami F, Anatassios G, et al, A method for
nonparametric damage detection through the use of neural networks,
Earthquake Engineering and Structural Dynamics, 1998, 27, 997～1010
59
华北工学院学位论文
[42] Chen S S, Kim S, Neural network based signal monitoring in a smart structural
system, Smart Structures and Materials, 1994:Smart sensing, Processing and
Instrumentation, J.S.Sirkis(ed.), SPIE, 1994, 2191, 176～186
[43] 郭国会，湖南大学硕士学位论文，钢筋混凝土结构破损评估的神经网络方法研究，
湖南，1998
[44] Ceravolo R, Stefano A De, Sabia D, Hierarchical use of neural techniques
in structural damage recognition, Smart Mateials and Structures, 1995, 4,
270～280
[45] Ferregut C, Osegueda R A, Ortiz J, Artificial neural networks for structural
damage detection and classification, Smart Structures and Materials 1995,
Smart Systems for Bridges, Structures, and Highways, L.K.Matthews(ed.),
SPIE, 1995, 2446, 68～80
[46] 于德介，雷慧，用 BP 神经网络诊断结构破损，工程力学，2001,18(1),56～61
[47] 孙宗光，倪一清，高赞明，丁江浩，基于斜拉索振动测量与神经网络技术的斜拉
桥损伤位置识别方法，工程力学，2003,20(3),26～30
[48] 黄苏南，邵惠鹤，基于信息的专家系统理论及应用，控制与决策，1995,10(2),119～
126
[49] 叶文，吕勇哉，沈平，时态覆盖集诊断模型 TGSC，计算机学报，1994,17(5),347～
353
[50] 刘贵立，张国英，薄板裂纹诊断的专家系统，机械强度，2001,23(2),141～143
[51] Edward S.Sazonov, Powsiri Klinkhachorn, Hota V.S.Gangarao and Udaya
B.Halabe, Fuzzy logic expert system for automated damage detection from
changes in strain energy mode shapes, Nondestructive Testing and
Evaluation, 2002 Vol, 18(1), 1～20
[52]J.M.Ko, Z.G.Sun, Y.Q.Ni, Multi-stage identifiacation scheme for detecting
damange in cable-stayed Kap Shui Mun Bridge, Engineering Structures, 2002,
24, 857～868
[53] 吴今培，智能故障诊断与专家系统，北京，科学出版社，1999
60
华北工学院学位论文
[54] 朱大奇，于盛林，基于知识的故障诊断方法综述，安徽工业大学学报，
2002,19(3),197～204
[55] 纪常伟，基于故障树和神经网络的故障诊断技术研究，哈尔滨，哈尔滨工业大学，
1995
[56] 何友，多传感器信息融合及应用，北京，电子工业出版社，2000
[57] 李宏男，李东升，土木工程结构安全性评估、健康监测及诊断述评，地震工程与
工程振动，2002,22(3),82～90
[58] 易伟建，刘霞，结构损伤诊断的遗传算法研究，系统工程理论与实践，2001,5,114～
118
[59] 朱宏平，李斌，利用动态特性测量值的结构损伤检测方法的比较研究，华中科技
大学学报，2002,19(1),48～53
[60] Friswell M L, Penny J E T, Garvey S D,A combined genetic and eigensensitivity
algorithm for the location of damage in structures, Computers &
Structures,1998,69(5),547～556
[61] C.Mares, C.Surace, An application of genetic algorithms to identify damage
in elastic structures, Journal of Sound and Vibration, 1996, 195(2), 195～
215
[62] F.T.K.Au, Y.S.Cheng, L.G.Tham and Z.Z.Bai, Structural damage detection
based on a micro-genetic algorithm using incomplete and noisy modal test
data, Journal of Sound and Vibration, 2003, 259(5), 1081～1094
[63] Wu, M., Tang, Z.H., Gui, W.H., Expert control strategy using neural networks
for electrolytic zinc process, Transaction on Nonferrous Metals Society of
China,2000,10(4),555～560
[64] 刘晓颖，桂卫华，朱爽，等，基于神经网络的动力锅炉故障诊断专家系统，基础
自动化，2001,8(S),55～57
[65] 桂卫华，基于人工智能方法的复杂过程故障诊断技术，控制工程，2002,9(4),1～
6
[66] Anantha Ramn S, Johnson V T, Damage assessment of composite structures—a
61
华北工学院学位论文
fuzzy logic integrated neural network approach, Computer & Structures, 1995,
57(3), 491～502
[67] 韩小云，刘瑞言，基于神经网络和模糊综合评判的梁故障诊断研究，国防科技大
学学报，1996, 18(1), 17～22
[68] 陈文颉，窦丽华，陈杰，杜丽辉，融合多特征信息的模式识别方法，北京理工大
学学报，2002,22(2),173～176
[69] Specht D F, Probabilistic neural networks, Neural Networks, 1990, 3, 109～
118
[70] 王柏生，倪一清，高赞明，用概率神经网络进行结构损伤位置识别，振动工程学
报，2001,14(1),60～64
[71] 杨晓楠，姜绍飞，倪一清，马传政，基于特征向量简化的复杂土木结构损伤检测，
沈阳建筑工程学院学报（自然科学版），2003,19(2),81～84
[72] 姜绍飞，周广师，刘红兢，刘明，考虑不确定性因素的结构损伤检测方法，沈阳
建筑工程学院学报（自然科学版）2002,18(2),85～87
[73] 胡雄，陈兆能，佟德纯，朱继梅，史家钧，多参数监测与模式识别技术在斜拉桥
模型中的应用，上海交通大学学报，2000,34(3),354～359
[74] 李得葆，陆秋海，实验模态分析及其应用，科技出版社，2001 年
[75] 傅志方，振动模态分析与参数辨识[M]，机械工业出版设，1990 年 9 月
[76] 张东利，华北工学院硕士学位论文，建筑结构损伤的振动诊断研究，山西太原，
华北工学院，2002 年
[77] George Hearn, Rene.B, Modal analysis for damage detection in structures,
Journal of Structural Engineering, Vol.117, No.10, October, 1991.
[78] 黄德双，神经网络模式识别系统理论，电子工业出版社，1996 年，1～10
[79] 傅京孙，模式识别应用，北京大学出版社，1990，2～3
[80] Yuen, M.M.F., A numerical study of the eigenparameters of a damaged
cantilever, Journal of Sound and Vibration, 1985,103,301～310
[81] 秦权，张卫国，悬索桥的损伤识别，清华大学学报（自然科学版），
Vol.38,No.12,1998,44～47
62
华北工学院学位论文
[82] Pandy A K,etal.Damage Detection from Changes in Curature Mode Shape,
Journal of Sound and Vibration,1991,145(2),321～332
[83] 董聪，结构损伤识别和定位的基本原理与方法，中国铁道科学，1999,20(3),89～
94
[84] Lieven, N.A.J.,Ewins, D.J.,Spatial Correlation of Mode Shapes, the
Coordinate Modal Assurance Criterion(COMAC), Proc.,6th Int.Modal
Anal.Conf.,Soc.For Experimental Mech.,Bethel,Conn.,690～695
[85] 邓焱，严普强，梁及桥梁应变模态与损伤测量的新方法，清华大学学报（自然科
学版），2000,40(11),123～127
[86] 胡列，姜节胜，顾松年，复合材料层合板故障诊断的一种新方法，振动工程学报，
1991,4(4),54～58
[87] 胡宇宏，结构损伤的动柔度方法，湖南大学学报（自然科学版），2002,29(3),72～
76
[88] Sampaio, Maia, Silva, Damage detection using the frequency response
function curvature method, Journal of Sound and Vibration, 1999, 226(5),
1029～1042