轨道交通引起地面振动的智能分析方法
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
列车在运行时产生的振动会通过周围地层向外传播,并进一步诱发建筑物的二次振动,对建筑物以及其中居民的工作和日常生活产生了很大的影响。如何分析振动对环境造成的影响已经成为一个很重要的课题。
     轨道系统由铁轨、枕木和碎石垫层组成,列车在运行时车轮与轨道系统会产生相互作用,由于轮重的作用使轨道产生弯曲变形,弯曲变形转化成作用在地基上的荷载引起地基振动,这一振动通过周围地层向外传播,导致周围地面的振动。
     为了得到神经网络的训练样本,除了利用现有的实测数据外,本文还考虑利用某些解析方法计算得到的数据作为样本。为此本文基于振动产生及传播的机理,利用了分层法的轨道交通引起地面振动的解析算法,通过解三维弹性体的波动方程得到波数—频域的解,离散化波数域得到地基土的动力响应特性,再通过快速Fourier逆变换得到空间—时间域的解。
     为了利用神经网络进行有限元计算,本文给出了列车运行时移动荷载在时间域和空间域的分布表示,通过三维有限元方法的分析,详细推导出了轨道交通荷载引起地面振动的有限元计算中的刚度矩阵和质量矩阵,同时将动力有限元的计算问题通过矩阵变换,转换成了一个二次型的优化问题。
     本文融合神经网络技术和遗传算法,对轨道交通引起的地面振动进行了正分析和反演,并利用计算机技术实现了地面振动的三维动画模拟,这主要包括:
     (1)研究了压缩映射遗传算法,利用Banach空间的不动点定理证明了压缩映射遗传算法可以收敛到全局最优值,弥补了标准遗传算法不能收敛至全局最优值的不足。另外还详细论述了该算法中的编码、选择、交叉和变异等遗传操作。为后续与神经网络融合应用作理论准备。
     (2)研究了BP神经网络的结构、训练算法,并将该算法应用到土的本构关系的建模之中。考虑到BP神经网络训练时间长、容易收敛到局部最优的不足,本文将压缩映射遗传算法应用到BP神经网络的训练之中,使其较快地收敛到全局最优值。
     (3)研究了Hopfield反馈神经网络的结构和稳定性,并深入讨论了稳定性分析的Lyapunov第二方法(亦称为直接法),利用Lyapunov方法分析了Hopfield神经网络改进网络—TH神经网络的稳定性。本文详细论述了将TH神经网络应用到二次型优化问题上的方法,并首次将该方法用来计算前面得
    
    武汉理工大学博士学位论文
    到的动力有限元计算的二次型。在仿真计算中,首次将压缩映射遗传算法应
    用到了搜索TH神经网络的平衡点(二次型的最优值)上。
     (4)研究了自递归神经网络的结构及训练算法,利用LyaPunov方法研究
    了自递归神经网络训练算法的收敛性和稳定性,并首次利用自递归神经网络
    来反演轨道交通引起地面振动的振动场。考虑到自递归神经网络的结构影响
    到其反演效果,本文利用压缩映射遗传算法来搜索其最佳的结构。
     (5)论述了轨道交通引起地面振动智能分析软件中运用的面向对象方法
    和OpenGL技术,研究了OpenGL的三维体绘制算法,最后实现了轨道交通引
    起地面振动的振动场三维模拟。
     本文最后总结了研究结论并展望进一步的工作,认为包括模糊逻辑、灰
    色理论等多种智能方法和神经网络、遗传算法的融合应用到轨道交通引起地
    面振动的分析之中是一种新的可行方法,三维实时动画模拟也是研究方向。
The train-induced vibration will spread outward through the medium of around strata, and induce the secondary vibration of construction in further, which brings great influence to construction and people's daily life. How to analysis the environment effect cased by vibration has become a very important problem.
    The track system is composed of rail-, sleeper ballast and substrate. When the train moves, the wheel and'the track system will interact each other. Because of the action of the wheel, the track may bright bent transformation, and the transformation change into load, which act on the foundation. Then the ground will be vibration caused by the transformation spreads in the ground.
    In order to get the neural network' training samples, the paper will use the data computed by some analytic method as training samples besides using existing data which measured by in locale. The paper based on the mechanism of the vibration's production and transmission, uses the analytic method of finite elastic layer to calculate the transmission of the ground vibration caused by track traffics. Then gets the result of wave numbers-frequency field through solving the wave equation of the three-dimension elastic layer. Then gets the dynamic response characteristic of the ground through dispersing the wave numbers. Finally gets the result of the space-time field through using reverse fast Fourier transform.
    The paper gives the expressions of the moving load in the time-space field. The paper gives stiffness matrix and mass matrix in finite element analysis of the ground vibration problem caused by track traffic by using three-dimension finite element method. Because three-dimension finite element analysis is very difficult, it is transmitted into a quadratic programming, which can be calculated by neural network.
    The paper analyzes the ground vibration caused by track traffic in two ways by neural network and genetic algorithm fusion. One side is forward analysis, on the other side is inversion. And the paper implements the three-dimensional dynamic simulation of the ground vibration. It mainly includes five parts.
    (1) The paper has studied the contractive mapping genetic algorithm, which can be converged to a global optimal solution proved by fixed-point theorem of Banach space. It remedies the shortage of standard genetic algorithm. Furthermore, the paper discusses the genetic operation in the algorithm such as the coding, select, cross over and mutation etc. It will be help to the next work about fusion with the neural network.
    
    
    
    (2) The paper has studied the structure and training algorithm of BP neural network. And it is applied to the modeling of constitutive model. Considering the shortage of BP neural network such as too long training time and easily converging the local optimal value, the paper applies the contractive mapping genetic algorithm to BP neural network1 training, which make it consequently converges to the globe optimal value more quickly.
    (3) The paper has studied the structure and stability of Hopfield feedback neural network. And it uses the Lyapunov method to analysis the stability of the TH neural network, which id mended from Hopfield neural network. The paper applies the TH neural network to a quadratic programming, which is transmitted from finite element computing. Finally the paper applies the contractive mapping genetic algorithm to search the equilibrium point of TH neural network in a quadratic programming computing for the first time.
    (4) The paper has studied the structure and training algorithm of self-recursion neural network. It also studies the convergence and stability of self-recursion neural network' training algorithm by using Lyapunov method. Then the paper use inversion method to simulate the vibration field of ground vibration caused by track traffic by self-recursion neural network for the first time. Considering self-recursion' structure can work on its inversion effect, so the paper uses contractive mapping genetic algorithm to search its optimal struct
引文
[1] Grassie S. L., Gregory R. W., Johnson K. L.. The Dynamic Response of Railway Track to High Frequency Vertical Excitation. Journal of Mechanical Engineering Science, 1982(4)
    [2] Tatsuo OHMACHI, Shigeaki MORICHI, Takumi TOSHINAMA. Simplified Analysis Procedure on Damped Vibration Equivalent to Love Waves in Double-layered Visco-elastic Media, Proc. of JSCE Structural Eng./ Earthquake Eng. 1986(3)
    [3] Krylov V. V.. Vibrational Impact of High-speed Trains. I. Effect of Track Dynamics, J. Acoust. Soc. Am. 1996(5)
    [4] Kaynia Amir M., Madshus Christian, Linda Harvik. Ground Vibration from High Speed Railway Lines. Proc. Of International Conference on Soil-Structure Interaction in Urban Civil Engineering, 1998.
    [5] Sheng X., Jones C. J. C., Petyt M.. Ground Vibration Generated by a Harmonic Load Acting on a Railway Track. Journal of Sound and Vibration, 1999,225(1) .
    [6] Yau J. S., Wu Y. S., Yang Y. S.. Impact Response of Bridges with Elastic Bearings to Moving Loads. Journal of Sound and Vibration, 2001,248(1) .
    [7] Chen Y. H., Huang Y. H., Shih C. T.. Response of An Infinite Timoshenko Beam on a Viscoelastic Foundation to a Harmonic Moving Load. Journal of Sound and Vibration, 2001, 241(5) .
    [8] Bode Christopher, Hirschauer Reinhold, Savidis Stavros A.. Soil-structure Interaction in the Time Domain Using Halfspace Green's Functions. Soil Dynamics and Earthquake Engineering, 2002(22) .
    [9] Lei X., Noda N. A.. Analyses of Dynamic Response of Vehicle and Track Coupling System with Random Irregularity of Track Vehicle Profile. Journal of Sound and Vibration, 2002,258(1) .
    [10] Yang Y. B., Yau J. D, Hsu L. C.. Vibration of Simple Beams due to Trains Moving at High speeds. Engineering Structures, 1997(19) .
    [11] Moreno Delgado R., Santos R. C.. Modelling of Railway Bridge-vehicle Interaction on High Speed Tracks. Computers & Structures, 1997(63) .
    [12] Xia H., Xu Y. L., Chan H. T.. Dynamic Interaction of Long Suspension Bridges with Running Trains. Journal of Sound and Vibration, 2000, 237(2) .
    [13] Cheng Y. S., Au F. T. K., Cheung Y. K.. Vibration of Railway Bridges under A Moving Train by Using Bridges-track-vehicle Element. Engineering Structures, 2001(23) .
    [14] Wu Y. S., Yang Y. B.. Steady-state Response and Riding Comfort of Trains Moving over
    
    A Series of Simply Supported Bridges. Engineering Structures, 2002.
    [15] Yu H. S., Hossain M. Z.. Lower Bound Shakedown Analysis of Layered Pavements Using Discontinuous Stress Fields. Comput. Methods Appl. Mech. Engrg., 1998.
    [16] Wu J. S., Shih P.Y.. Dynamic Response of Railway and Carriage under the High-speed Moving Loads. Journal of Sound and Vibration, 2000, 236(2).
    [17] Ekevid Torbjrn, Wiberg Nils Erik. Wave Propagation Related to High-speed Train-A scaled Boundary FE-approach for Unbounded Domains. Comput. Methods Appl. Mech. Engrg., 2002.
    [18] Chang T. P., Liu Y. N.. Dynamic Finite Element Analysis of A Nonlinear Beam Subjected to A Moving Load, Int. J. Solids Structures, 1996(33).
    [19] 沈德明.小波网络在振动信号时间序列预报中的应用.振动、测试与诊断,2000,20(3).
    [20] Teng, Tso-Liang, et al. Study on the Application of Fuzzy Theory to Structural Active Control. Computer Methods in Applied Mechanics and Engineering, 2000, 189(2).
    [21] Jack LB, Nandi AK. Genetic Algorithms for Feature Selection in Machine Condition Monitoring with Vibration Signals. IEEE Proceedings: Vision, Image and Signal Processing, 2000, 147(3)
    [22] Yen Gary Y, Lin Kuo-Chung. Wavelet Packet Feature Extraction for Vibration Monitoring, Proc. Int. Jt. Conf. Neural Networks. IEEE, 1999, Vol. 5.
    [23] Takemiya H. and Kellezi L. Paraseismic behavior of Wave Impeding Block(WIB) measured for ground vibration reduction, 1998
    [24] Hunt H.and Forrest J. Floating slab track for vibration reduction: Why simple models don't work, 2000
    [25] Amir M.Kaynia, Christian Madshus. Ground vibration from high speed railway lines. International Conference on Soil-Structure Interaction in Urban Civil Engineering.8./9. October 1998
    [26] 徐劲.高速移动荷载作用下地基轨道系统的振动分析.武汉理工大学硕士学位论文.2002
    [27] 黄文虎、马兴瑞等.弹性动力学反问题的研究进展.哈尔滨工业大学学报.1997,29(1):1-5
    [28] 左鹏飞.高速列车作用下轨道系统的动力特性研究.武汉理工大学硕士学位论文.2002
    [29] 易伟建,刘霞等.基于遗传算法的结构损伤诊断研究.工程力学,2001,18(2).
    
    
    [30] 王素萍,李大伟.灰色模型在城市环境噪声预测中的应用.噪声与振动控制,2001,21(3).
    [31] 段雪平,朱宏平等.神经网络在建筑物有限元模型修正中的应用.噪声与振动控制,2000,20(2).
    [32] 梁燕春,计算智能与力学反问题中的若干问题.力学发展.2000.30(3):321-331
    [33] 谢官模,李卓求,沈大荣.力学中几个领域的反问题研究综述.武汉工业大学学报.1997,19(2):92-95
    [34] 谢康和,周健.岩土工程有限元分析理论与应用.北京:科学出版社,2002
    [35] 孙洪刚.移动荷载作用下基于有限元法的环境振动分析.武汉理工大学硕士学位论文.2003
    [36] Gubernatis J.E. et al. The born approximation in the theory of the scattering of elastic waves by flaws. Joural of Appl.Phys.1977,48(7):2812-2819
    [37] Rose J.H, et al. Time domain Born approximation .J.NDE, 1982,3:45
    [38] Stavroulakis G.E. el al. Neural crack identification in steading state elastodynamics. Comput. Methods Appl. Mech. Engrg. 1998, (165): 129~146
    [39] 冯夏庭.智能岩土力学导论.北京:科学出版社,2000
    [40] 尚钢.神经网络在结构识别中的应用研究.武汉工业大学博士论文.1997
    [41] 徐宜桂,史铁林等.神经网络及其在结构动力分析中的应用研究.技术力学学报.1998,15(2):210-215
    [42] 高行山等.结构分析和设计中神经网络计算研究评述.计算力学.学报.2000,17(2):223~228
    [43] 邵金林,沈成武等.遗传算法用于结构物内部缺陷识别的逆分析.武汉交通科技大学学报.1997,21(3):275-279
    [44] 王永骥等.神经元网络控制.北京:机械工业出版社,1998
    [45] 陈国良,王熙法,庄镇泉等.遗传算法及应用.北京:人民邮电出版社,2001
    [46] 李云.非线性动力学系统的现代数学方法及其应用.北京:人民交通出版社,1998
    [47] 玄光男,程润伟.遗传算法与工程设计.北京:科学出版社,2000
    [48] Levin R.I. and Lieven N.A.J..Dynamic finite element model updating using neural networks.J. Of Sound and Virbration. 1998 210(5):593-607
    [49] Osama abdel-wahhab. A new scheme for training feed-forward neural networks. Pattern Recognition. 1997,30(3):519-524
    [50] 梁燕春等.基于神经网络方法的包装件非线性特性识别的研究.力学学报.1997,29(4):497-500
    
    
    [51] 易晓山等.有限元结构分析神经网络计算.国防科技大学学报.1996,18(4):27-30
    [52] G.M.L.格拉德威尔.振动中的反问题.北京:北京大学出版社,1991
    [53] 施阳,李俊等.MATLAB语言工具箱-TOOLBOX使用指南.西安:西北工业大学出版社,1998
    [54] Sqrensen N.J.& Andersen, B.S..A paralled finite element method for the analysis of crystalline solids. Comput. Methods.Appl. Mech. Engrg. 1996,132(3-4):345-357
    [55] Lennart Johnsson S. et al. Data structures and algorithms for the finite element method on a data parallel supercomputer. J. For Numerical Methods in Engineering. 1990,29:881-908
    [56] 张立明.人工神经网络的模型及应用.上海:复旦大学出版社,1993
    [57] 周树荃,粱维泰,邓绍忠著.有限元结构分析并行计算.北京:科学出版社,1997
    [58] 吕西林,金国方,吴晓涵.钢筋混凝土结构非线性有限元理论与应用.上海:同济大学出版社.1997
    [59] 朱以文等.微机有限元前后处理系统Vizi CAD及其应用.北京:科学技术文献出版社.1993,12
    [60] 朱慈勉,汪榴,江利仁等.计算结构力学.上海:上海科学技术出版社,1992,4
    [61] 唐纪晔等.弹塑性结构优化的并行算法,计算力学学报.1998,15(4)
    [62] 钟珞,白振刚,夏红霞等.灰色问题神经网络建模优化及其应用[J].计算机工程与应用.2001,9.
    [63] 李云.非线性动力系统的现代数学方法及其应用[M].人民交通出版社,1998.
    [64] 钟珞,汤超,谢伟平等.修改的反向传播算法[J].武汉工业大学学报,1995,17(2):91~93.
    [65] 潘昊,钟珞,陈杰.BP神经网络训练的函数变步长搜索调整法[J].湖北工学院学报,1997,12(2):1~4.
    [66] 潘昊,陈杰,钟珞.BP神经网络结构与样本训练参数选取的初步探讨[J].湖北工学院学报,1997,12(3):1~4.
    [67] Zhong Luo, Liu Lisheng, Zou Chengming et al. The Application of Neural Network in Lifetime Prediction of Concrete[J]. Journal of Wuhan University of Technology, 2002,17(1): 79~81.
    [68] 胡守仁,余少波,戴葵.神经网络导论[M].长沙:国防科技大学出版社,1997.
    [69] 焦李成.神经网络系统理论.西安:西安电子科技大学出版社,1996
    [70] 焦李成.神经网络的应用与实现.西安:西安电子科技大学出版社,1996
    [71] 焦李成.神经网络计算.西安:西安电子科技大学出版社,1996
    [72] 王秀峰,陈心昭,利用边界点法计算结构振动声辐射的近边界声场,合肥工业大学
    
    学报(自然科学版),Vol.23,No.5,2000
    [73] 朱利民,钟秉林等,振动信号短时分析方法及在机械故障诊断中的应用,振动工程学报,Vol.12,No.3,2000
    [74] 张钋,杨长春等,三维多值走时地震波场重建及格林函数计算,地球物理学报,Vol.43,No.2,2000
    [75] Lee Aclans著,吴江,吴红艳等译,可视化与虚拟实现,学苑出版社,1994
    [76] 曹锦章,陈东明,科学计算可视化与图形的某些虚拟现实研究,计算机仿真,1998,(2)
    [77] 赵昭,徐彤,面向虚拟现实环境的任意形状模型的开发,中国图象图形学报,1999,(8)
    [78] 杨少波,Visual C++多媒体应用程序开发技术,电脑与信息技术,1999,(1)
    [79] 石教英,蔡文立编著,科学计算可视化算法与系统,科学出版社,1996
    [80] 唐果,赵晓东,汪元美,三维图像分割与可视化研究.计算机学报,1998,19(3)
    [81] 袁景凌,钟珞,楼梦麟.有限元分析结果的三维可视化.武汉理工大学学报,2001,23(3)
    [81] 王述红,潘开名,非线性振动中地层结构参数计算模型及其优化,东北大学学报(自然科学版),2000,21(4)
    [82] 罗晓辉,用遗传算法确定地基承载力,岩石力学与工程学报,2001,20(3)
    [83] 易伟建,刘霞等,基于遗传算法的结构损伤诊断研究,工程力学,2001,18(2)
    [84] 陈军,王家林等,应用改进的遗传算法反演多层密度界面,地球科学,2000,25(6)
    [85] 虞爱民,李享荣等,有限长弹性地基梁地基系数的识别,噪声与振动控制,2000,(6)
    [86] 刘枫,高日,城市高架轨道交通体系振动与噪声控制,噪声与振动控制,2000,(4)
    [87] 段雪平,朱宏平等,神经网络在建筑物有限元模型修正中的应用,噪声与振动控制,2000,(2)
    [88] 王宏志,陈云敏等,分层土中变截面桩振动问题半解析解的研究,振动与冲击,2001,20(1)
    [89] 宋海平,周传荣,结构振动响应逐步逼近模糊优化设计方法,振动与冲击,2000,19(4)
    [90] 姬亦工,栾茂田等,空间地基有限元分析及反问题,郑州工业大学学报,2000,21(2)
    [91] 竹宫宏和,里中修平,谢伟平.高速移动加振源轨道—底盘系动的応答周边地盘振动传播[J].土木学会论文集,2001,682(7):299-309
    [92] 竹宫宏和,合田和哉,小森大资.高速列车运行时对沿线地基振动的计算机模拟和预测土木学会论文集,No.488/Ⅰ-23,11-13,1998.7
    [93] 堰津吉彦.高速列车运行引起的地基振动特性研究.1998
    [94] 白旗弘实,三木千寿,馆石和雄.高速移动荷载作用下桥梁振动响应的解析算法.土
    
    木学会论文集,NO.549/Ⅰ-37,107-114,1996.10
    [95] 吉冈修,芦谷公稔.新干线铁道振动的产生和传播.BUTSURI-TANSA,1995,48(5):299-315
    [96] 行武宗轨.人工振动源对象传播线路振动轻减工法关研究.1998
    [97] 川谷充郎,山田靖则,金哲佑,川木秀昭.道路桥交通振动三次元解析床版应答评价.桥梁振动97论文集.
    [98] 冈林隆敏.桥梁振动制振·制御.桥梁振动97论文集.
    [99] 川谷充郎,小林羲和,今枝拓也.道路桥交通振动使用性确率论的评价.桥梁振动97论文集.
    [100] 古田胜.时间域积分方程式法轨道系振动解析关基础的研究.岡山大学博士论文,1998.9.
    [101] 阿部和久,古田胜.时间域积分表现式轨道振动解析法.土木学会构造工学论文集,Vol.43A,1997.
    [102] 合田和哉.移动加振移动载荷3次元成層地盘内波动伝播关研究应用.岡山大学博士论文,1997.3.
    [103] 佐藤泰夫.弹性波动论.岩波书屋,1977
    [104] 田春芝.地铁振动对周围建筑物影响的研究概况.北京联合大学机械工程学院,2000.
    [105] 刘学毅,王平.高速轨道频域响应特性分析.西南交通大学学报,2000,35(4)
    [106] 茅玉泉.交通运输车辆引起的地面振动特性和衰减.兵器工业部第六设计研究院,1987.
    [107] 夏禾,陈英俊.车-梁-墩体系动力相互作用分析,土木工程学报,1992,25(2)
    [108] 吴礼本.国外城市交通系统发展趋势.铁道部四方车辆研究所,1998.
    [109] 王逢朝,夏禾,张鸿儒.地铁列车振动对邻近建筑物的影响.北方交通大学学报1999,23(5)
    [110] 夏禾,吴萱,于大明.城市轨道交通系统引起的环境振动问题.北方交通大学学报,1999,23(4)
    [111] 房营光,地铁钢轨-道床系统参数的频域反演分析.广东工业大学学报,1999,16(1)
    [112] 杨光辉,张鸿儒,夏禾.列车运行引起的桥下地面振动衰减特性.北方交通大学学报,1999,23(5)
    [113] 潘昌实,谢正光.地铁区间隧道列车振动测试与分析.土木工程学报,1990,23(2):21-28
    [114] 潘昌实,G.N.Pande.黄土隧道列车动荷载响应有限元初步数定分析研究.土木工程学报,1984,17(4)
    [115] 马筠.我国铁路环境振动现状及传播规律.中国环境科学,1987,7(5):4-7
    [116] 孙道恒等.固体力学有限元的圣经计算原理.机械工程学报.1996,13(6):20-25
    [117] 孙道恒等.力学反问题的神经网络分析法.计算结构力学及其应用.1996,13(3):
    
    308-312
    [118] Yanchun Liang. Application og neural networks to identification of nonlinear characteristics in cushioning packaging. Mechanics Research Communications. 1996,23(6):607-613
    [119] Chandarshekhara K.. Active vibration control of laminated composite plates using piezoelectric devices: afinete element approach. J. Intell. Mat. Syst. Struct. 1993,4:496-507
    [120] 钟珞.神经网络在建筑结构设计专家系统开发工具中的应用研究.武汉工业大学博士学位论文.1995
    [121] 廖振鹏.工程波动理论导论.北京:科学出版社,2002

© 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