基于遗传神经网络的高层框架结构损伤识别的研究
|
摘要
工程结构随着使用时间的延长,不可避免地发生老化,自然灾害的频繁发生也对其造成不同程度的损伤。结构损伤的检测及修复对于减少生命财产损失具有重要的作用。同时,尽早发现结构损伤,可以大大降低维修、维护的费用。因此,对工程结构的损伤识别、定位具有十分重要的意义。结构损伤检测技术已被广泛应用于航天、土木、机械和核工业中,是一门建立在损伤机理、传感器技术、信号分析技术、计算机技术及人工智能技术之上的多学科综合性技术。相对于传统的结构损伤检测方法,本论文主要对基于遗传神经网络的结构损伤检测技术理论与应用进行研究。
本文通过理论分析了适合结构损伤位置和损伤程度识别的组合参数法(此组合参数是由固有频率的变化信息和少数选定点的模态分量合成的向量),在此理论的基础上,分别对一个框架结构和一个悬臂梁结构进行了损伤数值模拟,同时采取合适的方法构造改进型BP—GA神经网络的输入参数,应用训练后的神经网络对结构进行损伤检测。
本论文的主要工作有下面几个内容:
首先,通过对神经网络的工作原理进行分析,得出在理论上它能够对结构的损伤进行识别。利用模态参数进行结构破损诊断是国内外研究的热点和难点。本文提出了基于改进型BP神经网络进行结构破损诊断的方法。BP网络由于具有强大的映射能力、容错性和鲁棒性等优点,非常适合解决破损诊断这类问题。但随着研究的深入,BP网络在应用中遇到了两个主要问题:(1)难以确定网络结构和初始值;(2)易陷入局部最小解。针对BP网络的不足,本文提出了一种基于遗传算法GA—BP网络的混合技术进行结构破损诊断的方法。该方法采用实数编码的遗传算法优化BP网络的结构及初始参数,从而提高了网络的精度。对比遗传BP网络与普通BP网络对三个仿真算例的识别结果,遗传BP网络的稳定性更好,精度更高,对噪声有很强的鲁棒性,是一种准确有效的结构破损诊断方法。
Along with the using time passing, the engineering structures inevitably get aged, and frequent natural disasters will also damage them in different degree. Detecting and repairing the damages of the structures plays a very important role in decreasing life and property loss. Meanwhile, early detection of the damages can reduce the expenses whether in repairing or maintaining. Therefore, the identity, location and estimation of the damages are of great importance. The structure damage detecting technology has been widely used in astronautics, civil engineering, mechanical engineering and nuclear industry, which is a multi-disciplinary and comprehensive technology based on damage mechanics, sensor technology, signal analysis technology, computer technology and artificial intelligence technology. Compared to traditional structure damage detecting methods, this article mainly focuses the theories and application of that based on genetic neural network.
This article analyzes the combination parameter method which is suitable for the detection of location and degree of the damages. (The combination parameter is a vector consisting of changing information of the natural frequency and the modal components of some selected points) On this basis, a frame structure and a projecting beam structure are employed to receive damage numerical modeling, while some appropriate methods are adapted to construct input parameters of the improved GA—BP neural network, and the trained neural network is applied to carry damage detection to the structure.
This article has the following main contents:
First of all, as a result of analysis of operating principle of neural network, it's clear that it can identify the damages of the structure.
It's a focus and difficult to identify the damages of the structure by modal parameters. This article put forward a method based on improved BP neural network on that topic. It's the powerful mapping capacity, fault-tolerance and the robust that make BP neural network fit for dealing with damage identification. But with the proceeding of the study, there appear two main problems in applications of the neural network: (1) it's hard to determine the initial value of the network structure; (2) it's easy to trap in local minimal solution. For dealing with the shortages, a method based on GA-BP neural network which adapt the mixed technologies to detect the damages is put forward. Thismethod employs genetic algorithm of real coding to optimize the structure and initialparameters of the neural network and it improves the accuracy of the network.Compared to general BP neural network, the detecting results of the three emulatorexamples gained by genetic BP neural network owns better stability, higher accuracyand is much more robust, it is an accurate and effective way to detect the damages ofthe structure.
本文通过理论分析了适合结构损伤位置和损伤程度识别的组合参数法(此组合参数是由固有频率的变化信息和少数选定点的模态分量合成的向量),在此理论的基础上,分别对一个框架结构和一个悬臂梁结构进行了损伤数值模拟,同时采取合适的方法构造改进型BP—GA神经网络的输入参数,应用训练后的神经网络对结构进行损伤检测。
本论文的主要工作有下面几个内容:
首先,通过对神经网络的工作原理进行分析,得出在理论上它能够对结构的损伤进行识别。利用模态参数进行结构破损诊断是国内外研究的热点和难点。本文提出了基于改进型BP神经网络进行结构破损诊断的方法。BP网络由于具有强大的映射能力、容错性和鲁棒性等优点,非常适合解决破损诊断这类问题。但随着研究的深入,BP网络在应用中遇到了两个主要问题:(1)难以确定网络结构和初始值;(2)易陷入局部最小解。针对BP网络的不足,本文提出了一种基于遗传算法GA—BP网络的混合技术进行结构破损诊断的方法。该方法采用实数编码的遗传算法优化BP网络的结构及初始参数,从而提高了网络的精度。对比遗传BP网络与普通BP网络对三个仿真算例的识别结果,遗传BP网络的稳定性更好,精度更高,对噪声有很强的鲁棒性,是一种准确有效的结构破损诊断方法。
Along with the using time passing, the engineering structures inevitably get aged, and frequent natural disasters will also damage them in different degree. Detecting and repairing the damages of the structures plays a very important role in decreasing life and property loss. Meanwhile, early detection of the damages can reduce the expenses whether in repairing or maintaining. Therefore, the identity, location and estimation of the damages are of great importance. The structure damage detecting technology has been widely used in astronautics, civil engineering, mechanical engineering and nuclear industry, which is a multi-disciplinary and comprehensive technology based on damage mechanics, sensor technology, signal analysis technology, computer technology and artificial intelligence technology. Compared to traditional structure damage detecting methods, this article mainly focuses the theories and application of that based on genetic neural network.
This article analyzes the combination parameter method which is suitable for the detection of location and degree of the damages. (The combination parameter is a vector consisting of changing information of the natural frequency and the modal components of some selected points) On this basis, a frame structure and a projecting beam structure are employed to receive damage numerical modeling, while some appropriate methods are adapted to construct input parameters of the improved GA—BP neural network, and the trained neural network is applied to carry damage detection to the structure.
This article has the following main contents:
First of all, as a result of analysis of operating principle of neural network, it's clear that it can identify the damages of the structure.
It's a focus and difficult to identify the damages of the structure by modal parameters. This article put forward a method based on improved BP neural network on that topic. It's the powerful mapping capacity, fault-tolerance and the robust that make BP neural network fit for dealing with damage identification. But with the proceeding of the study, there appear two main problems in applications of the neural network: (1) it's hard to determine the initial value of the network structure; (2) it's easy to trap in local minimal solution. For dealing with the shortages, a method based on GA-BP neural network which adapt the mixed technologies to detect the damages is put forward. Thismethod employs genetic algorithm of real coding to optimize the structure and initialparameters of the neural network and it improves the accuracy of the network.Compared to general BP neural network, the detecting results of the three emulatorexamples gained by genetic BP neural network owns better stability, higher accuracyand is much more robust, it is an accurate and effective way to detect the damages ofthe structure.
引文
[1]马宏伟,杨桂通.结构损伤探测的基本方法和进展.力学进展.1999,29(4):513-527
[2]Doebling S.W.,Farrar C.R.,Prime M.B.and Shevitz D.W.Damage Identification and Health Monitoring of Structural and Mechanical Systems from Changes in Their Vibration Characteristics:A Literature Review.LA- 13070-MS.1996
[3]Sidhu J.and Ewins D.J.Correlation of Finite Element and Modal Test Studies of a Practical Structure.Proceedings of 2~(td)International Modal Analysis Conference(IMAC).19 84:756-762
[4]Zhang Q.and Lallement G A Complete Procedure for the Adjustment of a Mathematical Modal from the Identified Complex Modes.Proceedings of 5th International Modal Analysis Conference(IMAC).1987:1183-1190
[5]Ojalvo I.U.and Pilon D.Diagnostics for Geometrically Locating Structural Math Model Errors from Modal Test Data.Proceedings of the 29th AIAA Structures,Structural Dynamics and Materials Conference.1988:1174-1186
[6]Zimmerman D.C.and Kaouk,M.Structural Damage Detection Using a Minimum Rank Update Theory.Journal of Vibration and Acoustics.1994,116(4):222-231
[7]Pandey A.K.and Biswas M.Damage Detection in Structures Using Changes in Flexibility.Journal of Sound and Vibration.1994,169(1):3-17
[8]Cawley P.and Adams R.D.The Location of Defects in Structures from Measurements of Natural Frequencies.Journal of Srain Analysis.1979,14(2):49-57
[9]Messina A.Williams E.J.and Contursi T.Structural Damage Detection by a Sensitivity and Statistical-based Method.Journal of Sound and Vibration.1998,216(5):791-808
[10]Lim T.W.And Kashangika T.A.L.Structural Damage Detection of Space Truss Structures Using Best Achievable Eigenvectors.AI AA Journal.1994,32(5):1049-1057
[11]Stubbs N.and Kim J.T Damage Localization in Strictures without Baseline Modal Parameters AIAA Journal.1996,34(8):1644-1649
[12]Shi Z.Y.Law S.S.and Zhang L.M.Structural Damage Localization from Modal Strain Energy Change.Journal of Sound and Vibration.1998,218(5):825-844
[13]董聪,范立础,陈肇元.结构智能健康诊断的理论和方法.中国铁道科学.2002,23(2):11-24
[14]张德文,[美]魏阜旋.模型修正与破损诊断.北京,科学出版社1999
[15]王其文等.人工神经网络与线性回归的比较.决策与决策支持系统,1993,3(3):43-49
[16]Lapedes Alan S.Farber Robert M.Nonlinear signal processing using neural networks:prediction and system modeling.Technical Report LA-UR-87-2662,Los Alamos National Laboratory,1987.
[17]J.J.Buckley and Y.Hayashi.Numerical relationships between neural networks,continuous functions.Fuzzy Sets and Systems,1993,60:1-8
[18]Rosenblatt F.Principles of Neurodynamics.NewYork,Spartan Book 1962
[19]袁曾任.人工神经网络及其应用北京.清华大学出版社 1999
[20]Hagan M.T.,Demuth H.B.and Beale M.Neural Network Design.Boston,PWS Publishing Co 1995
[21]Rosenblat F.A Perceiving and Recognizing Automation.Cornell Aeronautical Laboratory Report.86-406-1,1959
[22]Kolmogorov A.N.On the Representation of Continuous Functions of Several Variables by Superposition of Continuous Functions of One Variable and Addition.Doklady Akademiia Nauk SSSR.1957,114(5):953-956
[23]王文成.神经网络及其在汽车工程中的应用,北京,北京理工大学出版社 1998
[24]楼顺天,施阳.基于MATLAB的系统分析与设计一神经网络.西安,西安电子科技大学出版社 1998
[25]徐雷,迟惠生.静态神经网络的监督学习方法研究进展.电子学报.1992,20(10):106-113
[26]Peter J.A.,Gregory M.S.and Jordan B.P.An Evolutionary Algorithm that Constricts Recurrent Neural Networks.IEEE Transactions on Neural Network Works.1994,5:54-64
[27]李敏强、徐博,寇纪淞.遗传算法与神经网络的结合系统工程理论与实践1999,2:65-69
[28]王小平,曹立明.遗传算法:理论、应用与软件实现.西安,西安交通大学出版社 2002
[29]阎平凡,张长水.人工神经网络与模拟进化计算北京,清华大学出版社 2000
[30]VenkatasubramanianV.And Chan K.Neural Network Methodology for Process Fault Diagnosis.Journal of AlChE 1989,35(12):1993-2002
[31]Ghaboussi J.,Carrett J.H.and Wu X.J.Knowledge-based Modeling Behavior with Neural Network Journal of Engineer Meehanics.1991,117(1):132-153
[32]Wu X.J.,Ghaboussi J.and Garret J.H.Use of Neural Network in Detection of Structural Damage.Computers and structures.1992,42(4):649-659
[33]Baran,M.R.,Ghaboussi J.and Florom R.L.Neural Networks in Railway Engineering: Acoustic Wayside Fault Detection.Proceedings of the Artificial Neural Networks in Engineering Conference(ANNIE'94).1994,4:1147-1153
[34]Kudva J.N.,MunirN.and Tan P.W.Damage Detection in Smart Structures Using Neural Networks and Finite Element Analysis.Smart Material and Structure.1992,1:108-112
[35]Worden K.A.,Ball A.D.and Tomlinson GR.Neural Network for Fault Location.Proceedings of 11th International Modal Analysts Conference(IMAC).1993:47-54
[36]Elkordy M.F.,Chang,K.C.and Lee GC.A Structural Damage Neural Network Monitoring System Microcomputers in Civil Engineering.1994,9(2):83-96
[37]Stephens J.E.and Vanluchene R.D.Integrated Assessment of Seismic Damage in Structures.Microcomputers in Civil Engineering.1994,9(2):119-128
[38]Masri S.F.,Chassiakos A.G.Neural Network.Approach to Detection of Changes in Structural parameters.Journal of Engineer Mechanics.1996,122(4):350-360
[39]Nakamura M.and Maris S.F.A Method for Non-parametric Damage Detectionth through the Use of Neural Network.Earthquake Engineer and Structural Dynamics.1998,27(3):997-100
[40]Mc Culoch W.W.and Pitts W.A Logic Calculus of the Ideas Imment in Neurons Activity.Bulletin of Mathematical Biophysics.1943(5):115-133
[41]Hebb D.O.The Organization of Behavior.New York,Wiley 1949
[42]Hopfield J.J.Neural Network and Physical System swith Emergent Collective Computing Abilities.Proceeding of the National Academy of Science.1982,79:2554-2558
[43]Rumelhart and McCleland.Paralel Distributed Processing:Exploration in the Micro structure of cognition.Cambridge,MAMIT Press,1986
[44]王伟.人工神经网络原理一入门与应用.北京,北京肮空肮天大学出版社1995
[45]张明德.改进的BP神经网络收敛性的实验研究.计算机工程.1998,24(5):27-29
[46]王科俊,王克成.神经网络建模、预报与控制.哈尔滨,哈尔滨工业大学出版社1996
[47]张立明.人工神经网络的模型及其应用.上海,复旦大学出版社1993
[48]王凌.智能优化算法及其应用.北京,清华大学出版社,施普林格出版社2001
[49]陈国良,王煦法,庄镇泉.遗传算法及其应用.北京,人民邮电出版社1996
[50]Holland J.H Adaptation in Natural and Artificial Systems.Michigan,The University of Michigan Press 1995
[51]姜绍飞.基于神经网络的结构优化与损伤检测.北京,科学出版社 2002
[52]Kaminski P.C.The Approximation Location of Damage through the Analysis of Natural Frequencies with Artificial Neural Network.Journal of Process Mechanical Engineer.1995,209(E 2):117-124
[53]Lam H.F, Ko J.M, and Wong C.W. Localization of Damaged Structural Connections Based on Experimental Modal and Sensitivity Analysis. Journal of Sound and Vibration. 1998,21 0(1):91-115
[54]Ni Y.Q., Wang B.S. and Ko J.M. Selection of Input to Neural Network for Structural Damage identification. Smart Systems for Bridges, Structures and Highways, SPIE. 1999, 3671:270-280
[55] Johnson E.A., Lam H.F, Katafygiotis L. and Beck J. A Benchmark Problem for Structural Health Monitoring and Damage Detection. Proceedings of the 14th ASCE Engineering Mechanics Conference. 2000
[2]Doebling S.W.,Farrar C.R.,Prime M.B.and Shevitz D.W.Damage Identification and Health Monitoring of Structural and Mechanical Systems from Changes in Their Vibration Characteristics:A Literature Review.LA- 13070-MS.1996
[3]Sidhu J.and Ewins D.J.Correlation of Finite Element and Modal Test Studies of a Practical Structure.Proceedings of 2~(td)International Modal Analysis Conference(IMAC).19 84:756-762
[4]Zhang Q.and Lallement G A Complete Procedure for the Adjustment of a Mathematical Modal from the Identified Complex Modes.Proceedings of 5th International Modal Analysis Conference(IMAC).1987:1183-1190
[5]Ojalvo I.U.and Pilon D.Diagnostics for Geometrically Locating Structural Math Model Errors from Modal Test Data.Proceedings of the 29th AIAA Structures,Structural Dynamics and Materials Conference.1988:1174-1186
[6]Zimmerman D.C.and Kaouk,M.Structural Damage Detection Using a Minimum Rank Update Theory.Journal of Vibration and Acoustics.1994,116(4):222-231
[7]Pandey A.K.and Biswas M.Damage Detection in Structures Using Changes in Flexibility.Journal of Sound and Vibration.1994,169(1):3-17
[8]Cawley P.and Adams R.D.The Location of Defects in Structures from Measurements of Natural Frequencies.Journal of Srain Analysis.1979,14(2):49-57
[9]Messina A.Williams E.J.and Contursi T.Structural Damage Detection by a Sensitivity and Statistical-based Method.Journal of Sound and Vibration.1998,216(5):791-808
[10]Lim T.W.And Kashangika T.A.L.Structural Damage Detection of Space Truss Structures Using Best Achievable Eigenvectors.AI AA Journal.1994,32(5):1049-1057
[11]Stubbs N.and Kim J.T Damage Localization in Strictures without Baseline Modal Parameters AIAA Journal.1996,34(8):1644-1649
[12]Shi Z.Y.Law S.S.and Zhang L.M.Structural Damage Localization from Modal Strain Energy Change.Journal of Sound and Vibration.1998,218(5):825-844
[13]董聪,范立础,陈肇元.结构智能健康诊断的理论和方法.中国铁道科学.2002,23(2):11-24
[14]张德文,[美]魏阜旋.模型修正与破损诊断.北京,科学出版社1999
[15]王其文等.人工神经网络与线性回归的比较.决策与决策支持系统,1993,3(3):43-49
[16]Lapedes Alan S.Farber Robert M.Nonlinear signal processing using neural networks:prediction and system modeling.Technical Report LA-UR-87-2662,Los Alamos National Laboratory,1987.
[17]J.J.Buckley and Y.Hayashi.Numerical relationships between neural networks,continuous functions.Fuzzy Sets and Systems,1993,60:1-8
[18]Rosenblatt F.Principles of Neurodynamics.NewYork,Spartan Book 1962
[19]袁曾任.人工神经网络及其应用北京.清华大学出版社 1999
[20]Hagan M.T.,Demuth H.B.and Beale M.Neural Network Design.Boston,PWS Publishing Co 1995
[21]Rosenblat F.A Perceiving and Recognizing Automation.Cornell Aeronautical Laboratory Report.86-406-1,1959
[22]Kolmogorov A.N.On the Representation of Continuous Functions of Several Variables by Superposition of Continuous Functions of One Variable and Addition.Doklady Akademiia Nauk SSSR.1957,114(5):953-956
[23]王文成.神经网络及其在汽车工程中的应用,北京,北京理工大学出版社 1998
[24]楼顺天,施阳.基于MATLAB的系统分析与设计一神经网络.西安,西安电子科技大学出版社 1998
[25]徐雷,迟惠生.静态神经网络的监督学习方法研究进展.电子学报.1992,20(10):106-113
[26]Peter J.A.,Gregory M.S.and Jordan B.P.An Evolutionary Algorithm that Constricts Recurrent Neural Networks.IEEE Transactions on Neural Network Works.1994,5:54-64
[27]李敏强、徐博,寇纪淞.遗传算法与神经网络的结合系统工程理论与实践1999,2:65-69
[28]王小平,曹立明.遗传算法:理论、应用与软件实现.西安,西安交通大学出版社 2002
[29]阎平凡,张长水.人工神经网络与模拟进化计算北京,清华大学出版社 2000
[30]VenkatasubramanianV.And Chan K.Neural Network Methodology for Process Fault Diagnosis.Journal of AlChE 1989,35(12):1993-2002
[31]Ghaboussi J.,Carrett J.H.and Wu X.J.Knowledge-based Modeling Behavior with Neural Network Journal of Engineer Meehanics.1991,117(1):132-153
[32]Wu X.J.,Ghaboussi J.and Garret J.H.Use of Neural Network in Detection of Structural Damage.Computers and structures.1992,42(4):649-659
[33]Baran,M.R.,Ghaboussi J.and Florom R.L.Neural Networks in Railway Engineering: Acoustic Wayside Fault Detection.Proceedings of the Artificial Neural Networks in Engineering Conference(ANNIE'94).1994,4:1147-1153
[34]Kudva J.N.,MunirN.and Tan P.W.Damage Detection in Smart Structures Using Neural Networks and Finite Element Analysis.Smart Material and Structure.1992,1:108-112
[35]Worden K.A.,Ball A.D.and Tomlinson GR.Neural Network for Fault Location.Proceedings of 11th International Modal Analysts Conference(IMAC).1993:47-54
[36]Elkordy M.F.,Chang,K.C.and Lee GC.A Structural Damage Neural Network Monitoring System Microcomputers in Civil Engineering.1994,9(2):83-96
[37]Stephens J.E.and Vanluchene R.D.Integrated Assessment of Seismic Damage in Structures.Microcomputers in Civil Engineering.1994,9(2):119-128
[38]Masri S.F.,Chassiakos A.G.Neural Network.Approach to Detection of Changes in Structural parameters.Journal of Engineer Mechanics.1996,122(4):350-360
[39]Nakamura M.and Maris S.F.A Method for Non-parametric Damage Detectionth through the Use of Neural Network.Earthquake Engineer and Structural Dynamics.1998,27(3):997-100
[40]Mc Culoch W.W.and Pitts W.A Logic Calculus of the Ideas Imment in Neurons Activity.Bulletin of Mathematical Biophysics.1943(5):115-133
[41]Hebb D.O.The Organization of Behavior.New York,Wiley 1949
[42]Hopfield J.J.Neural Network and Physical System swith Emergent Collective Computing Abilities.Proceeding of the National Academy of Science.1982,79:2554-2558
[43]Rumelhart and McCleland.Paralel Distributed Processing:Exploration in the Micro structure of cognition.Cambridge,MAMIT Press,1986
[44]王伟.人工神经网络原理一入门与应用.北京,北京肮空肮天大学出版社1995
[45]张明德.改进的BP神经网络收敛性的实验研究.计算机工程.1998,24(5):27-29
[46]王科俊,王克成.神经网络建模、预报与控制.哈尔滨,哈尔滨工业大学出版社1996
[47]张立明.人工神经网络的模型及其应用.上海,复旦大学出版社1993
[48]王凌.智能优化算法及其应用.北京,清华大学出版社,施普林格出版社2001
[49]陈国良,王煦法,庄镇泉.遗传算法及其应用.北京,人民邮电出版社1996
[50]Holland J.H Adaptation in Natural and Artificial Systems.Michigan,The University of Michigan Press 1995
[51]姜绍飞.基于神经网络的结构优化与损伤检测.北京,科学出版社 2002
[52]Kaminski P.C.The Approximation Location of Damage through the Analysis of Natural Frequencies with Artificial Neural Network.Journal of Process Mechanical Engineer.1995,209(E 2):117-124
[53]Lam H.F, Ko J.M, and Wong C.W. Localization of Damaged Structural Connections Based on Experimental Modal and Sensitivity Analysis. Journal of Sound and Vibration. 1998,21 0(1):91-115
[54]Ni Y.Q., Wang B.S. and Ko J.M. Selection of Input to Neural Network for Structural Damage identification. Smart Systems for Bridges, Structures and Highways, SPIE. 1999, 3671:270-280
[55] Johnson E.A., Lam H.F, Katafygiotis L. and Beck J. A Benchmark Problem for Structural Health Monitoring and Damage Detection. Proceedings of the 14th ASCE Engineering Mechanics Conference. 2000