基于模态应变能和BP神经网络的混凝土框架结构损伤识别
|
摘要
采用模态应变能变化率和BP神经网络的两步损伤识别方法,对钢筋混凝土框架结构进行损伤识别研究.首先,利用单元的模态应变能变化率作为结构损伤定位因子,运用通用有限元ANSYS的APDL语言编制程序,计算模态应变能变化率;然后,利用BP神经网络进行损伤程度识别.该方法将二者优点相结合,并克服了单纯利用模态应变能难以准确计算损伤程度以及单纯利用BP神经网络样本巨大的困难.数值仿真结果表明,该方法适用于框架结构的损伤识别.
Damage identification of reinforced concrete frame structures is investigated by using the changing ratio of modal strain energy and BP neural network.The changing ratio of modal strain energy MSECR is taken as the damage location factor.MSECR is calculated by using the language APDL in the commercial FEM software ANSYS.Then,BP neural network is used to determine the damage degree.Modal strain energy method can not know the damage degree while the BP neural network method has to treat many data of samples.The above shortcomings have been overcome.The results show that the proposed method can be applied to the damage detection of frame structures.
Damage identification of reinforced concrete frame structures is investigated by using the changing ratio of modal strain energy and BP neural network.The changing ratio of modal strain energy MSECR is taken as the damage location factor.MSECR is calculated by using the language APDL in the commercial FEM software ANSYS.Then,BP neural network is used to determine the damage degree.Modal strain energy method can not know the damage degree while the BP neural network method has to treat many data of samples.The above shortcomings have been overcome.The results show that the proposed method can be applied to the damage detection of frame structures.
引文
[1]李国强,郝坤超,陆烨.框架结构损伤识别的两步法[J].同济大学学报,1998,26(5):483-487.(LI Guo-qiang,HAO Kun-chao,LU Ye.The two-step methodin damage identification for frame structures[J].Journal of Tongji University,1998,26(5):483-487.(in Chinese))
[2]李洪泉,欧进萍.剪切型钢筋混凝土框架的地震损伤识别方法[J].哈尔滨建筑大学学报,1996,29(2):8-12.(LI Hong-quan,OU Jin-ping.The seismicdamage identification method in shear of reinforcedconcrete frame[J].Journal of Harbin University ofAiehiteeture and Engineering,1996,29(2):8-12.(in Chinese))
[3]Shi Z Y,Law S S,Zhang L M.Structural damage de-tection from modal strain energy change[J].Journalof Engineering Mechanics,2000,126(12):1216-1223.
[4]王锋,李毅谦,李传习.基于模态应变能法识别板类结构损伤的数值研究[J].长沙理工大学学报:自然科学版,2006,3(1):27-30.(WANG Feng,LI Yi-qian,LI Chuan-xi.The numerical study of damage i-dentification for plate structure by using modal strainenergy[J].Journal of Changsha University of Scienceand Technology:Natural Science,2006,3(1):27-30.(in Chinese))
[5]管德清,黄燕.基于转角模态小波变换的平面框架裂缝识别研究[J].长沙理工大学学报:自然科学版,2008,5(3):20-25.(GUAN De-qing,HUANG Yan.Crackidentification of plane frames based on wavelettransformof angle displacement mode[J].Journal ofChangsha University of Science and Technology:Natural Science,2008,5(3):20-25.(in Chinese))
[6]徐丽,易伟建.应变模态在框架结构节点损伤诊断中的应用研究[J].振动、测试与诊断,2006,26(2):102-107.(XU Li,YI Wei-jian.Strain mode diagno-sis of joint damage in the frame structure of the ap-plied research[J].Journal of Vibration,Measurement&Diagnosis,2006,26(2):102-107.(in Chinese))
[7]Zhao Li,Xuesong Tang,Xingye Chen.Damageidenti-fication for concrete continuous rigid frame bridgebased on curvature mode and BP neural network[A].Sih G C,Tu S T,Wang Z D.Integrated Approa-ches for Materials and Structural Safety[C].Shang-hai:East China University of Science and TechnologyPress,2007:57-62.
[8]Kudva R,Surace C.Damage assessment of multiplecracked beams:Numerical results and experi mentalvalidation[J].Journal of Sound and Vibration,1997,206(4):567-588.
[9]Masri S F,Smyth A W.Application of neural net-works for detection of changes in nonlinear systems[J].Journal of Engineering Mechanics,2000,126(7):666-676.
[10]杨英杰,虞和济.结构损伤状态识别的神经网络方法.东北大学学报:自然科学版,1994,15(2):210-214.(YANG Ying-jie,YU He-ji.Neural network isusedin pattern recognition of structural damage[J].Journal of Northeastern University:Natural Sci-ence,1994,15(2):210-214.(in Chinese))
[11]郭国会.钢筋混凝土结构破损评估的神经网络方法研究[J].湖南大学学报:自然科学版,1998,25(1):71-76.(GUO Guo-hui.The research on artificialneural network method of damage assessment of re-inforced concrete structure[J].Journal of Hunan U-niversity:Naturnal Science,1998,25(1):71-76.(inChinese))
[12]史治宇.结构破损定位的单元模态应变能变化率法[J].振动工程学报,1998,11(3):356-360.(SHIZhi-yu.Structural damage positioning unit rate ofchange of modal strain energy method[J].Journal ofVibration Engineering,1998,11(3):356-360.(inChinese))
[13]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.(ZHOU Kai-li,KANG Yao-hong.Neural networkmodel and its MATLAB si mulation program design[M].Beijing:Tsinghua University Press,2005.(inChinese))
[14]飞思科技产品研发中心.神经网络理论与MAT-LAB 7实现[M].北京:电子工业出版社,2005.(FlySynopsys R&D Center.Neural networktheo-ry and MATLAB 7 i mplementation[M].Beijing:E-lectronics Industry Press,2005.(in Chinese))
[15]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,2000.(YUAN Zeng-ren.Artificialneural network and its application[M].Beijing:Ts-
[2]李洪泉,欧进萍.剪切型钢筋混凝土框架的地震损伤识别方法[J].哈尔滨建筑大学学报,1996,29(2):8-12.(LI Hong-quan,OU Jin-ping.The seismicdamage identification method in shear of reinforcedconcrete frame[J].Journal of Harbin University ofAiehiteeture and Engineering,1996,29(2):8-12.(in Chinese))
[3]Shi Z Y,Law S S,Zhang L M.Structural damage de-tection from modal strain energy change[J].Journalof Engineering Mechanics,2000,126(12):1216-1223.
[4]王锋,李毅谦,李传习.基于模态应变能法识别板类结构损伤的数值研究[J].长沙理工大学学报:自然科学版,2006,3(1):27-30.(WANG Feng,LI Yi-qian,LI Chuan-xi.The numerical study of damage i-dentification for plate structure by using modal strainenergy[J].Journal of Changsha University of Scienceand Technology:Natural Science,2006,3(1):27-30.(in Chinese))
[5]管德清,黄燕.基于转角模态小波变换的平面框架裂缝识别研究[J].长沙理工大学学报:自然科学版,2008,5(3):20-25.(GUAN De-qing,HUANG Yan.Crackidentification of plane frames based on wavelettransformof angle displacement mode[J].Journal ofChangsha University of Science and Technology:Natural Science,2008,5(3):20-25.(in Chinese))
[6]徐丽,易伟建.应变模态在框架结构节点损伤诊断中的应用研究[J].振动、测试与诊断,2006,26(2):102-107.(XU Li,YI Wei-jian.Strain mode diagno-sis of joint damage in the frame structure of the ap-plied research[J].Journal of Vibration,Measurement&Diagnosis,2006,26(2):102-107.(in Chinese))
[7]Zhao Li,Xuesong Tang,Xingye Chen.Damageidenti-fication for concrete continuous rigid frame bridgebased on curvature mode and BP neural network[A].Sih G C,Tu S T,Wang Z D.Integrated Approa-ches for Materials and Structural Safety[C].Shang-hai:East China University of Science and TechnologyPress,2007:57-62.
[8]Kudva R,Surace C.Damage assessment of multiplecracked beams:Numerical results and experi mentalvalidation[J].Journal of Sound and Vibration,1997,206(4):567-588.
[9]Masri S F,Smyth A W.Application of neural net-works for detection of changes in nonlinear systems[J].Journal of Engineering Mechanics,2000,126(7):666-676.
[10]杨英杰,虞和济.结构损伤状态识别的神经网络方法.东北大学学报:自然科学版,1994,15(2):210-214.(YANG Ying-jie,YU He-ji.Neural network isusedin pattern recognition of structural damage[J].Journal of Northeastern University:Natural Sci-ence,1994,15(2):210-214.(in Chinese))
[11]郭国会.钢筋混凝土结构破损评估的神经网络方法研究[J].湖南大学学报:自然科学版,1998,25(1):71-76.(GUO Guo-hui.The research on artificialneural network method of damage assessment of re-inforced concrete structure[J].Journal of Hunan U-niversity:Naturnal Science,1998,25(1):71-76.(inChinese))
[12]史治宇.结构破损定位的单元模态应变能变化率法[J].振动工程学报,1998,11(3):356-360.(SHIZhi-yu.Structural damage positioning unit rate ofchange of modal strain energy method[J].Journal ofVibration Engineering,1998,11(3):356-360.(inChinese))
[13]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.(ZHOU Kai-li,KANG Yao-hong.Neural networkmodel and its MATLAB si mulation program design[M].Beijing:Tsinghua University Press,2005.(inChinese))
[14]飞思科技产品研发中心.神经网络理论与MAT-LAB 7实现[M].北京:电子工业出版社,2005.(FlySynopsys R&D Center.Neural networktheo-ry and MATLAB 7 i mplementation[M].Beijing:E-lectronics Industry Press,2005.(in Chinese))
[15]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,2000.(YUAN Zeng-ren.Artificialneural network and its application[M].Beijing:Ts-
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