智能结构及其健康检测与监测
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
近年来,由于新材料技术、信息技术及计算机技术的快速发展及其与其他传统行业的逐步结合,高科技正迅速渗透到包括土木工程在内的各个行业之中,具有仿人智能功能和生命特征的土木工程结构正在一步一步变为现实。
     对在役结构进行状态监测、损伤检测、健康诊断、安全评估和灾难预警,将有利于从根本上消除隐患,并避免灾难性事故的发生。智能结构及其健康诊断成为近年来业内人士的研究热点,而且已经成为各国政府、科研机构和专家学者的投资热点和研究热点。
     本文对智能结构的理论框架及其健康状态的检测与监测进行了一些探索和研究。
     首先针对智能结构的理论和应用研究现状,明确地阐明了智能结构的定义和概念,全面论述了智能结构构成要素;论述了智能结构健康诊断的实现方式——人工神经网络的模式识别法;论述了智能结构的研究内容,指出了智能结构的设计特点及流程。
     其次,论述了基于振动的结构健康(损伤)检测的原理,从力学反问题的角度出发,论述了智能结构的智能计算的两种思路——无几何模型的计算智能法和有几何模型的有限元法。通过对这两种计算路线的比较,提出了一种优化的智能结构计算方案,即充分利用各自的优点,将有限元和神经网络结合起来应用于智能结构中。还介绍了应用于工程中的人工神经网络的原理和网络结构设计及其改进方法。
     最后,提出了具体的智能化算法,基于BP网络的结构健康状态的诊断方法——分层逐步识别法。结合数值算例,对一个两跨三层框架结构,建立BP网络模型,对结构的损伤位置和损伤程度进行了模拟试验及识别。模拟试验表明恰当的神经网络模型具有较好损伤识别能力,然而对于损伤程度识别的精度问题,还需要进一步深入的研究。
In recent years ,as the technologies of new materials ,IT and computer rapidly develop and combine with the traditional productive mode ,the Hi -tech has been rapidly penetrating almost all of industries including civil engineering .The civil engineering structures which has the intelligent functions like the human being are becoming realities .
    It will be advantageous to remove dangerous things and prevent potential catastrophic events through respecting condition, detecting damage, diagnosing health, and evaluating safety of the building structures in service. The thought of intelligent structure and health diagnosis of it was brought forward frequently by the research in the field of civil engineering, and the research of this field has become hit of invest and research.
    In this paper, the author has done some research works on the theory frame of the intelligent structure, the detection and health condition inspection of it.
    Firstly, aiming at the state of intelligent structure the art on the theoretic and applied research work ,clearly define the conception of the intelligent structure ;discuss the components of the intelligent structure; introduce the characteristic of artificial neural net (ANN) which is used on the civil engineering structure ;discuss the method that is suit to the intelligent structure-mode identification based on ANN ; discuss the research content of the intelligent structure; and both the characteristic of the intelligent structure design and its flow chart are discussed.
    Secondly ,the structural health (damage) detection method based dynamics is discussed ;from the point of view of inverse problems in mechanics ,two trains of thought for solving the intelligent structure commutative problems are proposed ,i.e. :by means of intelligence computation method with geometrical modeling and by the aid of finite element method with geometrical modeling . By comparing the two methods, a feasible and optimum seeking method is presented to the intelligent structure commutative problems, which combine
    
    
    the finite element method and ANN method.
    Finally, a detailed and intelligent solution is proposed for diagnosing the health condition of the structure, which based on BP neural net-the method identified step by step, combine with a numerical example .The frame structure is a two bays and three stories .Through establishing ANN model, simulating verification has been processed, which is to predict the damage location and severity .It has been shown that a proper ANN model has a comparatively strong ability on damage identification .However, numerical results also show that further research should be done to improve the precision of the damage identification.
引文
[1] 智能建筑技术1 中国工业出版社 1999:10~11
    [2] 淡丹辉 智能桥梁结构 西南交通大学博士研究生学位论文:1~3
    [3] 陶宝祺 智能材料结构 北京:国防工业出版社,1997
    [4] 李宏男 阎石 智能结构控制发展综述地震工程与工程振动 1999,19(2):29~36
    [5] 陈伟,瞿伟廉,姜正国 人工神经网络技术在结构损伤诊断中的应用 世界地震工程,2002,28(1):146~149
    [6] 曹照平,王社良,马胜利 光线传感器在土木工程中的应用 南京建筑工程学院院报,2000(4):47~50
    [7] 欧进萍,关新春 土木工程智能结构体系的研究与发展 地震工程与工程振动:1999,19(2):21~28
    [8] 张徽敬,欧进萍 智能控制算法及其在结构振动控制中的应用世界地震工程 2002,18(2):32~38
    [9] 王社良,巨生国,苏三庆 形状记忆合金的动力响应特性及振动控制 西安建筑科技大学学报 1999,31(1):14~17
    [10] 黄尚廉 智能结构系统-减灾防灾的研究前沿 土木工程学报,2000,33(4):1~5
    [11] Lau ,C.K, Wong,K.Y.,Flint A.R. The structural health montoring system for cable-supported bridges is Tsing Ma control area. Proceedings of Workshop on Reseach and Mornitoring of Long Span Bridge, 26~28 April 2000,Hong Kong, pp. 14~23.
    [12] Chen W.M. Fu Y.M. Huang S.L. Inline sensing system for muff-parameter remote measurment of bridge. Proceedings of Workshop on Research and Morforing of Long shan Bridge,26~28 April 2000,pp. 173~179
    [13] 蔡得所.大坝裂缝光线监测技术研究及坝基稳定性分析.哈尔滨建筑大学博士后研究报告 1997:1~5
    [14] 黄尚廉 智能材料系统与结构—工程构造安全监控的一条崭新思路 世界科学研究与发展;1996,6(3):61~64
    [15] Rogersc.A. Intelligent material system-the down of a new materials Agc. J. Intelligent material systems and structures, 1993,4:4~12
    [16] Lius.c., Chong K.P., Singh M.P. Civil infrastructure systems research: Hazard mitigation and intelligent material systems, J. Smart Materials and Structures,Vol.4,suplementl A, March 1995, A169~174
    
    
    [17] H.A.D. Kirston Determination of rock mass elastic moduli by back analysis of deformation measurement. Proceedings of Symp on Exploration on rock Eng. Johnnesburg. 1976
    [18] 刘维宁.逆问题的信息理论及其在岩土工程中的应用.西南交通大学博士论文.1991
    [19] 郭怀志,马启超,薛玺成等.岩体初始反应力场的分析方法.岩土工程学报.1983,3
    [20] 王永庆 人工智能原理与方法 西安交通大学出版社.1998:374~375
    [21] 王永庆 人工智能原理与方法 西安交通大学出版社.1998:412~413
    [22] 戴汝为 人工智能 化学工业出版社 2002:32~33
    [23] 姜绍飞 基于神经网络的结构优化与损伤检测.科学出版社,2002:18~19。
    [24] Venkatasubramanian V and Chan K. A neural network methodology for process fault diagnaosis[J]. Journal of AICAE. 1989,35(12): 1993~2002
    [25] 钱永久.既有钢筋混凝土桥梁的评估与诊断.西南交通大学博士学位论文.1992:1~15
    [26] 程明,朱莜.信息论讲座.科学出版社.1984:10~15
    [27] 吕大刚 王光远 结构智能健康诊断的信息融合原理 哈尔滨建筑大学学报,2002,35(4):1-5
    [28] 李惠彬,郑兆昌等.对国内外桥梁损伤诊断几种方法的评述[J].工程力学,1998(s):407~414
    [29] Wang B S, Liang X Betal. Comprative study of damage indices in appliction to a long-span suspension bridge[A]. Proce. Of Inter, Conf. On Advances in Structrual Dynamics[C]. Hong Kong,2000
    [30] Law S S ,Howe D and Zhu X Q .Modal strain energy in neural network damage assessment[A]. International Conference on Advances in Structural Dynamics[C]. Hong Kong ,2000
    [31] Pandey A K et al. Damage detection from changes in curvature mode shapes[J]. Journal of Sound and Vibration ,1991,145:321~332
    [32] Stubbs N et al .Field verification of a nondestructive damage localization and severity estimation algorithm[A].Proc, of the 13~(th) Inter. Modal Analysis Conf. IAI.USA ,1: 210~218
    [33] Kohonen T. Associative memory: A system theory approach[M]. Springer: New York
    [34] 李士勇.模糊控制·神经控制和智能控制[M].哈尔滨:哈尔滨工业出版社,1996
    
    
    [35] 陈长征,罗跃刚,白秉三等.结构损伤检测与智能诊断[M].北京:科学出版社,2001
    [36] 何振亚.神经智能[M].长沙:湖南科学技术出版社,1997
    [37] Martin T.Hagan Howard B.Demuth Mark H.Beale戴葵等译神经网络设计 机械工业出版社2002:9~11
    [38] Rumelhert D.E. Hinton G.E. and Willions R.J. Learning representation by back-propagation errors. Nature 1986,323(9):533~536
    [39] Martin T.Hagan Howard B.Demuth Mark H.Beale戴葵等译神经网络设计 机械工业出版社2002:9~11p:203~204
    [40] 闻新 周露 王丹力 熊小英 MATLAB神经网络应用设计科学出版社2000:231~232
    [41] 姜绍飞,张春丽,钟善桐 BP网络模型的改进方法探讨[J].哈尔滨建筑大学学报,2000,33(5):57~60
    [42] 徐宜桂,史铁林.BP网络的全局最优化学习算法[J].计算机科学,1996(1):73~75
    [43] 董聪,刘西拉.广义BP算法及网络容错性和泛化能力的研究[J].控制与决策,1998,13(2):120~124
    [44] 杨晓红,刘乐善.用遗传算法优化神经网络结构[J].计算机应用与软件,1997(3):59~65
    [45] 赵英,赵恒勇.用“基因算法”调节人工神经元网络模型[J].计算机工程与应用,1997(6):35~37
    [46] 杜泽超,孙光伟,所胜军.前向神经网络学习算法研究[J].哈尔滨建筑大学学报,2001,34(1):94~96
    [47] 姜绍飞,刘之洋.人工神经网络在外包钢筋混凝土框架柱设计参数预报中的适应性[J].土木工程学报,1997,33(1):73~77
    [48] 徐雷,迟惠生.静态前馈神经网络的监督学习方法研究进展[J].电子学报,1992(10):106~109
    [49] William C C and Margerry E H. Guidelines for the selection of network architecture[J]. Artificial Intelligence for Engineering Design Analysis and Manufaturing,1997,11(5): 395~408
    [50] Kaminski.P.C. The approximate location of damage through the analysis of natural frequencies with artificial neural networks[J]. Journal of Process Mechanical Engineering. 1995,20(9),117~123
    [51] 陈伟,瞿伟廉,姜正国.人工神经网络技术在结构损伤诊断中的应用 世界地震工程,2002,28(1):146~149
    [52] 温利明,黄奕辉 神经网络用于结构损伤识别的几个关键问题研究工业建筑
    
    2002,32(8):39~40
    [53] 姜绍飞 基于神经网络的结构优化与损伤检测.科学出版社,2002:112~114

© 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