基于神经网络的框架结构损伤多重分步识别
|
摘要
提出了基于神经网络的框架结构损伤多重分步识别方法,建立了用于框架结构损伤识别的高效神经网络。根据构件损伤的多重分步识别思路,把构件损伤识别过程分为:利用神经网络建立损伤异常过滤器对构件损伤进行预警;以频率构造的组合指标作为神经网络输入向量,对构件损伤进行初步定位;以频率和模态振型构造的组合指标作为神经网络输入向量,对构件损伤进行具体定位;以频率平方变化率作为神经网络输入向量,对构件损伤程度进行识别。最后针对三跨四层的框架结构进行了损伤识别数值模拟。结果表明:基于神经网络的框架结构损伤多重分步识别方法简化了网络的结构,能够有效地对框架结构损伤进行预警、定位和定量。
The multi-stage damage identification method for frame structures based on neural network was proposed.A kind of high efficient neural network to identify damage in frame structures was established.This method was divided into four steps according to the multi-stage identification ideas of member damage.Firstly,damage anomalous filter was set up by neural network to alarm the damage in structural members.Secondly,the primary location of the member damage was determined by the neural network with inputing the combined damage index of frequency.At the third step,the specific location of the member damage was determined by the neural network with inputing the combined damage index of frequency and vibration mode.Finally,the damage degree of the member was identified by neural network with inputing the change rate of squared modal frequency.Numerical simulation of damage identification for three-span four-floor frame structure was carried out.Results show that multi-stage damage identification method based on neural network simplifies network structure,and can alarm,locate and quantify the damage effectively.
The multi-stage damage identification method for frame structures based on neural network was proposed.A kind of high efficient neural network to identify damage in frame structures was established.This method was divided into four steps according to the multi-stage identification ideas of member damage.Firstly,damage anomalous filter was set up by neural network to alarm the damage in structural members.Secondly,the primary location of the member damage was determined by the neural network with inputing the combined damage index of frequency.At the third step,the specific location of the member damage was determined by the neural network with inputing the combined damage index of frequency and vibration mode.Finally,the damage degree of the member was identified by neural network with inputing the change rate of squared modal frequency.Numerical simulation of damage identification for three-span four-floor frame structure was carried out.Results show that multi-stage damage identification method based on neural network simplifies network structure,and can alarm,locate and quantify the damage effectively.
引文
[1]姜绍飞.基于神经网络的结构优化与损伤检测[M].北京:科学出版社,2002.JIANG Shao-fei.Structural Optimization and DamageDetection Based on Neural Networks[M].Beijing:Science Press,2002.
[2]KAMINSKI P C.The Approximate Location of Dam-age Through the Analysis of Natural Frequencies withArtificial Neural Networks[J].Journal of ProcessMechanical Engineering,1995,209(2):117-123.
[3]CAWLEY P,ADAMS R D.The Location of Defectsin Structures from Measurements of Natural Frequen-cies[J].Journal of Strain Analysis,1979,14(2):49-57.
[4]HEARN G,TESTA R B.Modal Analysis for DamageDetection in Structures[J].Journal of Structural En-gineering,1991,117(10):3042-3063.
[5]于德介,雷慧,程军圣.基于BP神经网络与柔度变化的结构破损诊断[J].振动工程学报,2001,14(3):345-348.YU De-jie,LEI Hui,CHENG Jun-sheng.A Methodfor Structural Damage Detection Based on Back Prop-agation Neural Network and Flexibility Changes[J].Journal of Vibration Engineering,2001,14(3):345-348.
[6]吴波,胡云霞.基于BP神经网络的空间索杆结构节点损伤识别研究[J].地震工程与工程振动,2006,26(1):83-88.WU Bo,HU Yun-xia.Research on Damage Identifica-tion of Joints in a Practical Spatial Cable-strut Struc-ture Based on Back-propagation Neural Networks[J].Earthquake Engineering and Engineering Vibration,2006,26(1):83-88.
[7]孙宗光,高赞明,倪一清.基于神经网络的损伤构件及损伤程度识别[J].工程力学,2006,23(2):18-22.SUN Zong-guang,KO Jan-ming,NI Yi-qing.Identifi-cation of Damaged Members and Damage Extent inBridge Deck by Neural Network[J].EngineeringMechanics,2006,23(2):18-22.
[8]刘义艳,段晨东,巨永锋,等.基于神经网络与特征融合的损伤诊断方法[J].长安大学学报:自然科学版,2008,28(6):106-110.LIU Yi-yan,DUAN Chen-dong,JU Yong-feng,et al.Diagnosis Method of Structure Damage Using NeuralNetwork and Feature Fusion[J].Journal of Chang anUniversity:Natural Science Edition,2008,28(6):106-110.
[9]张刚刚,王春生,徐岳.基于径向基函数神经网络的斜拉桥损伤识别[J].长安大学学报:自然科学版,2006,26(1):49-53.ZHANG Gang-gang,WANG Chun-sheng,XU Yue.Damage Detection of Cable-stayed Bridge Based onRBF Neural Network[J].Journal of Chang an Uni-versity:Natural Science Edition,2006,26(1):49-53.
[10]田洁,周楠.填充墙框架结构在地震作用下的滞回特性与损伤分析[J].西安建筑科技大学学报:自然科学版,2008,40(2):189-195.TIAN Jie,ZHOU Nan.Hysteretic Response andDamage Analysis of Masonry Infilled Frames UnderSevere Earthquake[J].Journal of Xi an University ofArchitecture&Technology:Natural Science Edition,2008,40(2):189-195.
[11]喻磊,姚谦峰,张荫.基于集中损伤力学的钢筋混凝土框架结构非线性分析[J].西安建筑科技大学学报:自然科学版,2006,38(4):518-522.YU Lei,YAO Qian-feng,ZHANG Yin.NonlinearAnalysis of Reinforced Concrete Frames Based onLumped Damage Mechanics[J].Journal of Xi an Uni-versity of Architecture&Technology:Natural Sci-ence Edition,2006,38(4):518-522.
[12]向天宇,赵人达.结构损伤识别的双重网格算法[J].中国公路学报,2006,19(4):94-97.XIANG Tian-yu,ZHAO Ren-da.Dual Mesh Methodfor Structure Damage Detection[J].China Journal ofHighway and Transport,2006,19(4):94-97.
[2]KAMINSKI P C.The Approximate Location of Dam-age Through the Analysis of Natural Frequencies withArtificial Neural Networks[J].Journal of ProcessMechanical Engineering,1995,209(2):117-123.
[3]CAWLEY P,ADAMS R D.The Location of Defectsin Structures from Measurements of Natural Frequen-cies[J].Journal of Strain Analysis,1979,14(2):49-57.
[4]HEARN G,TESTA R B.Modal Analysis for DamageDetection in Structures[J].Journal of Structural En-gineering,1991,117(10):3042-3063.
[5]于德介,雷慧,程军圣.基于BP神经网络与柔度变化的结构破损诊断[J].振动工程学报,2001,14(3):345-348.YU De-jie,LEI Hui,CHENG Jun-sheng.A Methodfor Structural Damage Detection Based on Back Prop-agation Neural Network and Flexibility Changes[J].Journal of Vibration Engineering,2001,14(3):345-348.
[6]吴波,胡云霞.基于BP神经网络的空间索杆结构节点损伤识别研究[J].地震工程与工程振动,2006,26(1):83-88.WU Bo,HU Yun-xia.Research on Damage Identifica-tion of Joints in a Practical Spatial Cable-strut Struc-ture Based on Back-propagation Neural Networks[J].Earthquake Engineering and Engineering Vibration,2006,26(1):83-88.
[7]孙宗光,高赞明,倪一清.基于神经网络的损伤构件及损伤程度识别[J].工程力学,2006,23(2):18-22.SUN Zong-guang,KO Jan-ming,NI Yi-qing.Identifi-cation of Damaged Members and Damage Extent inBridge Deck by Neural Network[J].EngineeringMechanics,2006,23(2):18-22.
[8]刘义艳,段晨东,巨永锋,等.基于神经网络与特征融合的损伤诊断方法[J].长安大学学报:自然科学版,2008,28(6):106-110.LIU Yi-yan,DUAN Chen-dong,JU Yong-feng,et al.Diagnosis Method of Structure Damage Using NeuralNetwork and Feature Fusion[J].Journal of Chang anUniversity:Natural Science Edition,2008,28(6):106-110.
[9]张刚刚,王春生,徐岳.基于径向基函数神经网络的斜拉桥损伤识别[J].长安大学学报:自然科学版,2006,26(1):49-53.ZHANG Gang-gang,WANG Chun-sheng,XU Yue.Damage Detection of Cable-stayed Bridge Based onRBF Neural Network[J].Journal of Chang an Uni-versity:Natural Science Edition,2006,26(1):49-53.
[10]田洁,周楠.填充墙框架结构在地震作用下的滞回特性与损伤分析[J].西安建筑科技大学学报:自然科学版,2008,40(2):189-195.TIAN Jie,ZHOU Nan.Hysteretic Response andDamage Analysis of Masonry Infilled Frames UnderSevere Earthquake[J].Journal of Xi an University ofArchitecture&Technology:Natural Science Edition,2008,40(2):189-195.
[11]喻磊,姚谦峰,张荫.基于集中损伤力学的钢筋混凝土框架结构非线性分析[J].西安建筑科技大学学报:自然科学版,2006,38(4):518-522.YU Lei,YAO Qian-feng,ZHANG Yin.NonlinearAnalysis of Reinforced Concrete Frames Based onLumped Damage Mechanics[J].Journal of Xi an Uni-versity of Architecture&Technology:Natural Sci-ence Edition,2006,38(4):518-522.
[12]向天宇,赵人达.结构损伤识别的双重网格算法[J].中国公路学报,2006,19(4):94-97.XIANG Tian-yu,ZHAO Ren-da.Dual Mesh Methodfor Structure Damage Detection[J].China Journal ofHighway and Transport,2006,19(4):94-97.
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