径向基网络在简支梁损伤识别中的应用
|
摘要
对简支梁进行了损伤分析,研究了不同损伤工况下的频率变化率和模态振型曲率变化,并采用径向基神经网络对结构进行了损伤识别研究,研究中采用了三种方案:仅利用频率变化率;仅用第1阶模态曲率变化;综合使用前3阶频率变化率和模态曲率变化。结果表明,基于动力参数和径向基神经网络的结构损伤识别方法能够准确地识别结构的损伤程度;神经网络的输入参数选择对结果有较大影响,综合使用频率变化率和模态曲率变化的第3种方案识别效果最好。
Damage analysis of simply supported beam is presented in this paper,involving rate of frequency change and change of mode shape curvature at different kinds of scenarios.RBF neural networks are adopted to identify the structural damage.Three schemes,which choose different parameters as input of networks,are used in the damage identification process:(1) only rate of frequency change;(2) only the first order mode shape curvature change;(3) the combination of the first three orders of rate of frequency change and change of mode shape curvature.Results show that the structural damage can be identified by using RBF networks and vibration characters,and the input parameters of networks do the bigger inf-luence on the identification effect.The combination scheme(3) makes the best results in this paper.
Damage analysis of simply supported beam is presented in this paper,involving rate of frequency change and change of mode shape curvature at different kinds of scenarios.RBF neural networks are adopted to identify the structural damage.Three schemes,which choose different parameters as input of networks,are used in the damage identification process:(1) only rate of frequency change;(2) only the first order mode shape curvature change;(3) the combination of the first three orders of rate of frequency change and change of mode shape curvature.Results show that the structural damage can be identified by using RBF networks and vibration characters,and the input parameters of networks do the bigger inf-luence on the identification effect.The combination scheme(3) makes the best results in this paper.
引文
[1]Doebling SW,Farrar CR,Prime MB.Damage Identi-fication and Health Monitoring of Structural and Me-chanical Systems From Changes in Their VibrationCharacteristics:A Literature Review[R].Los AlamosNational Laboratory,1996.
[2]Sohn H,CR Farrar,Hemez FM,et al.A review ofstructural health monitoring literature[R].Los AlamosNational Laboratory,2004.
[3]Wu X,Ghaboussi J,Garrett J H.Use of neural net-works in detection of structural damage[J].Comput-ers&Structures,1992,42(4):649-659.
[4]Elkordy M F,Chang K C,Lee G C.Application ofneural networks in vibrational signature analysis[J].Journal of Engineering Mechanics,1994,120(2):251-264.
[5]Pandey PC,Barai,SV.Multilayer perceptron in dam-age detection of bridge structures[J].Computers&Structures,1995,54(4):597-608.
[6]Choi M Y,Kwon I B.Damage detection system of areal steel truss bridge by neural networks[C]//SmartStructures and Materials 2000:Smart Systems toBridges Structures and Highways,2000.
[7]李忠献,杨晓明,丁阳.应用人工神经网络技术的大型斜拉桥子结构损伤识别研究[J].地震工程与工程振动,2003,23(3):92-99.
[8]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):72-77.
[9]胡良红,刘效尧.基于改进的BP神经网络的钢桁梁桥损伤识别[J].合肥工业大学学报:自然科学版,2006,29(5):576-579.
[10]Broomhead DS,Lowe D.Multivariable functional in-terpolation and adaptive networks[J].Complex Sys-tems,1988,(2):321-355.
[2]Sohn H,CR Farrar,Hemez FM,et al.A review ofstructural health monitoring literature[R].Los AlamosNational Laboratory,2004.
[3]Wu X,Ghaboussi J,Garrett J H.Use of neural net-works in detection of structural damage[J].Comput-ers&Structures,1992,42(4):649-659.
[4]Elkordy M F,Chang K C,Lee G C.Application ofneural networks in vibrational signature analysis[J].Journal of Engineering Mechanics,1994,120(2):251-264.
[5]Pandey PC,Barai,SV.Multilayer perceptron in dam-age detection of bridge structures[J].Computers&Structures,1995,54(4):597-608.
[6]Choi M Y,Kwon I B.Damage detection system of areal steel truss bridge by neural networks[C]//SmartStructures and Materials 2000:Smart Systems toBridges Structures and Highways,2000.
[7]李忠献,杨晓明,丁阳.应用人工神经网络技术的大型斜拉桥子结构损伤识别研究[J].地震工程与工程振动,2003,23(3):92-99.
[8]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):72-77.
[9]胡良红,刘效尧.基于改进的BP神经网络的钢桁梁桥损伤识别[J].合肥工业大学学报:自然科学版,2006,29(5):576-579.
[10]Broomhead DS,Lowe D.Multivariable functional in-terpolation and adaptive networks[J].Complex Sys-tems,1988,(2):321-355.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心