复杂结构损伤识别的广义子结构法
|
摘要
为实现对复杂结构损伤位置的识别,采用分步识别策略,将原结构划分为多个广义子结构,先进行广义子结构的识别,再进行损伤单元的识别.为克服广义子结构划分的主观性,提出了基于聚类分析的广义子结构划分方式.以悬臂桁架结构为数值算例,对比了3种划分方式的网络训练收敛情况以及网络对带噪声检验样本的识别结果.研究结果表明,按基于聚类分析的广义子结构划分方式构造的网络易于收敛,且对带噪声检验样本的正确识别率高于另外2种划分方式1%~5%.
In order to improve the identification effect for damage location of complex structures,a multi-step identification method was adopted.With this method,the damaged sub-structure can be found after a structure is decomposed into several sub-structures,then the damaged element in the sub-structure can be recognised.To solve the problem that the conventional modes to decompose a structure will lead to incorrect results,a decomposition mode of sub-structures based on a clustering analysis was put forward.Three decomposition modes were adopted by taking a suspension truss structure as an example.By comparing the training convergence and identification results of their neural networks with noise samples,the result shows that the decomposition mode of sub-structures based on a clustering analysis can make it easier to train neural networks,and compared with the other two decomposition modes,its correct identification rate increases by 1% to 5%.
In order to improve the identification effect for damage location of complex structures,a multi-step identification method was adopted.With this method,the damaged sub-structure can be found after a structure is decomposed into several sub-structures,then the damaged element in the sub-structure can be recognised.To solve the problem that the conventional modes to decompose a structure will lead to incorrect results,a decomposition mode of sub-structures based on a clustering analysis was put forward.Three decomposition modes were adopted by taking a suspension truss structure as an example.By comparing the training convergence and identification results of their neural networks with noise samples,the result shows that the decomposition mode of sub-structures based on a clustering analysis can make it easier to train neural networks,and compared with the other two decomposition modes,its correct identification rate increases by 1% to 5%.
引文
[1]CHUNG B Y,HYEONG J L.Substructural identification for damage estimation of structures[J].Structural Safety,1997,19(1):121-140.
[2]KO J M,SUM Z G,NI Y Q.Multi-stage identification scheme for detecting damage in cable-stayed Kap Shui Mun bridge[J].Engineering Structures,2002,24(7):857-868.
[3]瞿伟廉,陈伟,李秋胜.基于神经网络技术的复杂框架结构节点损伤的两步诊断法[J].土木工程学报,2003,36(5):37-45.QU Weilian,CHEN Wei,LI Qiusheng.Two-step approach for joints damage diagnosis of framed structures by artificialneural networks[J].China Civil Engineering Journal,2003,36(5):37-45.
[4]CHUNG B Y,BAHNG E Y.Substructural identification using neural networks[J].Computers&Structures,2000,77(1):41-52.
[5]陈素文,李国强.基于BP网络的框架结构损伤的多重分步识别理论[J].地震工程与工程振动,2002,22(5):18-23.CHEN Suwen,LI Guoqiang.A muti-hierarchical damage identification approach based on BP network for frame structures[J].Earthquake Engineering and Engineering Vibration,2002,22(5):18-23.
[6]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.LI Zhongxian,YANG Xiaoming,DING Yang.Research on substructural damage identification of large cable-stayed bridgesusing artificial neural networks[J].Earthquake Engineering and Engineering Vibration,2003,23(3):92-99.
[7]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 Guoqiang,HAO Kunchao,LUYe.Two-step approach for damage identification of frame structures[J].Journal of TongjiUniversity,1998,26(5):483-487.
[8]TOPLE K G,STUBBS N.Nondestructive damage evaluation of a structure from limited modal parameters[J].EarthquakeEngineering and Structural Dynamics,1995,24(11):1427-1436.
[9]楼梦麟.结构动力分析的子结构方法[M].上海:同济大学出版社,1997:71-103.
[10]张育智.基于神经网络与数据融合的结构损伤识别理论研究[D].成都:西南交通大学土木工程学院,2007:72-94.
[11]张云涛,龚玲.数据挖掘原理与技术[M].北京:电子工业出版社,2004:49-59.
[2]KO J M,SUM Z G,NI Y Q.Multi-stage identification scheme for detecting damage in cable-stayed Kap Shui Mun bridge[J].Engineering Structures,2002,24(7):857-868.
[3]瞿伟廉,陈伟,李秋胜.基于神经网络技术的复杂框架结构节点损伤的两步诊断法[J].土木工程学报,2003,36(5):37-45.QU Weilian,CHEN Wei,LI Qiusheng.Two-step approach for joints damage diagnosis of framed structures by artificialneural networks[J].China Civil Engineering Journal,2003,36(5):37-45.
[4]CHUNG B Y,BAHNG E Y.Substructural identification using neural networks[J].Computers&Structures,2000,77(1):41-52.
[5]陈素文,李国强.基于BP网络的框架结构损伤的多重分步识别理论[J].地震工程与工程振动,2002,22(5):18-23.CHEN Suwen,LI Guoqiang.A muti-hierarchical damage identification approach based on BP network for frame structures[J].Earthquake Engineering and Engineering Vibration,2002,22(5):18-23.
[6]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.LI Zhongxian,YANG Xiaoming,DING Yang.Research on substructural damage identification of large cable-stayed bridgesusing artificial neural networks[J].Earthquake Engineering and Engineering Vibration,2003,23(3):92-99.
[7]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 Guoqiang,HAO Kunchao,LUYe.Two-step approach for damage identification of frame structures[J].Journal of TongjiUniversity,1998,26(5):483-487.
[8]TOPLE K G,STUBBS N.Nondestructive damage evaluation of a structure from limited modal parameters[J].EarthquakeEngineering and Structural Dynamics,1995,24(11):1427-1436.
[9]楼梦麟.结构动力分析的子结构方法[M].上海:同济大学出版社,1997:71-103.
[10]张育智.基于神经网络与数据融合的结构损伤识别理论研究[D].成都:西南交通大学土木工程学院,2007:72-94.
[11]张云涛,龚玲.数据挖掘原理与技术[M].北京:电子工业出版社,2004:49-59.
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