基于振型差值曲率与神经网络的海洋平台结构损伤识别研究

英文篇名：Damage identification of an offshore platform based on curvature of modal shape difference and BP neural network
中文刊名：振动与冲击
英文刊名：Journal of Vibration and Shock
作者：于菲 ; 刁延松 ; 佟显能 ; 张启亮
英文作者：YU Fei1 ; DIAO Yan-song1 ; TONG Xian-neng2 ; ZHANG Qi-liang1 (1.College of Civil Engineering ; Qingdao University of Technology ; Shandong Qingdao 266033 ; China ; 2.Qingdao Branch ; Shandong Tongyuan Design Group Co.Ltd. ; Shandong Qingdao 266000 ; China )
中文关键词：损伤识别 ; 海洋平台 ; 振型差值曲率 ; BP神经网络 ; 两步法
英文关键词：damage identification ; offshore platform ; curvature of modal shape difference ; BP neural network ; two-step approach
出版日期：2011-10-25
机构：青岛理工大学土木工程学院;山东同圆设计集团青岛分公司;
年：2011
期：10
出版单位：振动与冲击

摘要

利用神经网络进行复杂结构损伤识别时,会遇到网络规模过大以致难以收敛的问题。为此,提出了一种基于振型差值曲率与神经网络的结构损伤识别两步法。第一步,利用振型差值曲率得到损伤的大致区域。第二步,在第一步选定的区域内,利用BP神经网络确定损伤构件的准确位置。四层海洋平台数值模拟和实验结果验证了该方法的有效性。
When a neural network is used to identify damage of complex structures,a problem that the network size is too large to converge will be encountered.So,a two-step structural damage identification approach based on curvature of modal shape difference and BP neural network was proposed here.Firstly,the damage areas were localized approximately using curvature of modal shape difference.Secondly,the damaged elements were determined accurately with a BP neural network in the selected areas.The effectiveness of the method was validated with the results of numerical simulation and experiments for a four-floor offshore platform.

引文

[1]Charles R F,Scott W D,David A N.Vibration basedstructure damage identification[J].The Royal Society,Philosophical Transactions:Mathematical Physical andEngineering Sciences,2001,359(1778):131-149.
    [2]瞿伟康,黄东梅.大型复杂结构的两阶段损伤诊断方法[J].世界地震工程,2003,19(2):72-78.
    [3]郭惠勇,李正良,彭川.结构损伤动力识别技术的研究与进展[J].重庆建筑大学学报,2008,30(1):140-145.
    [4]刁延松,李华军,李军,等.一种框架结构损伤诊断两步法[J].工业建筑,2005,35(S1):966-969.
    [5]陈长征,罗跃纲,白秉三,等.结构损伤检测与智能诊断[M].北京:科学出版社:183-233.
    [6]罗跃纲,彭永恒,闻邦椿.工程结构的集成神经网络识别研究[J].振动与冲击,2006,25(1):14-17.
    [7]Oh B H,Jung B S.Structural damage assessment withcombined data of static and modal tests[J].Journal ofStructural Engineering,ASCE,1998,124(8):956-965.
    [8]罗晓健,于国良.几种模态分析方法在结构无损检测中的应用[J].中国海洋平台,2006,21(5):44-49.
    [9]董长虹.Matlab神经网络与应用[M].北京:国防工业出版社:1-106.
    [10]刁延松.基于神经网络和小波分析的海洋平台结构损伤检测研究[D].青岛:中国海洋大学,2006.