基于应变模态差和神经网络的管道损伤识别
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
应变模态差对结构微小损伤具有很高的敏感性且对结构损伤处具有较高的定位识别率,故在工程实际中可以利用其对管道进行损伤识别。然而,应变模态差只能定性地反映结构的损伤程度,并不能直接量化损伤结构的损伤程度,故采用神经网络和应变模态差相结合的方法对损伤管道进行损伤位置和损伤程度的识别。利用有限元分析软件ANSYS进行模态分析提取管道的应变模态参数,并把管道损伤前后的应变模态差作为神经网络的输入参数,以损伤位置和损伤程度作为神经网络的输出参数,对损伤管道分别进行单损伤和双损伤的损伤定位和程度识别。研究结果表明,利用应变模态差和神经网络相结合的方法能够准确识别出管道的损伤位置以及损伤程度。
Strain modal difference is used to identify the location of damage in pipelines,due to its precise recognition in engineering practice and its sensitivity to small structural damage.However,this method fails to quantify the structure′s degree of damage,so a new method that combines the neural network with the strain modal differenceis presented to identify the degree of pipeline damage.It takes the strain modal difference obtained through the finite element as the input parameter and the damage location and degreeas the output parameter of the network to identify the location and degree of both single and double damage.The simulation results of damage identification in the pipeline show that this method can not only determine the location of pipeline damage,but also accuratelyquantify the degree of damage.
引文
[1]蒋济同,于红理.基于应变模态差的海洋平台构件的损伤识别研究[J].灾害学,2010,25(S0):67-69.Jiang Jitong,Yu Hongli.Study on identification of offshore platform component damage based on strain modal difference[J].Journal of Catastrophology,2010,25(S0):67-69.(in Chinese)
    [2]陈素文,李国强.人工神经网络在结构损伤识别中的应用[J].振动、测试与诊断,2001,21(2):116-124.Chen Suwen,Li Guoqiang.Application of artificial neural networks to damage identification of structures[J].Journalof Vibration,Measurement&Diagnosis,2001,21(2):116-124.(in Chinese)
    [3]王步宇.结构损伤的分形神经网络检测方法[J].振动、测试与诊断,2005,25(4):260-262.Wang Buyu.Structural damage detection based on fractal neural network[J].Journal of Vibration,Measurement&Diagnosis,2005,25(4):260-262.(in Chinese)
    [4]于菲,刁延松,佟显能,等.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[J].振动与冲击,2011,30(10):190-194.Yu Fei,Diao Yansong,Tong Xianneng,et al.Damage identification of an offshore platform based on curvature of modal shape difference and BP neural network[J].Journal of Vibration and Shock,2011,30(10):190-194.(in Chinese)
    [5]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 Zongguang,Gao Zanming,Ni Yiqing.Structural damage detection based on fractal neural network[J].Engineering Mechanics,2006,23(2):18-22.(in Chinese)
    [6]范建设,郑飞,许金余.基于应变模态能与神经网络的地下拱形结构损伤诊断[J].噪声与振动控制,2011,31(3):120-124.Fan Jianshe,Zheng Fei,Xu Jinyu.Damage diagnosis for underground arch structure based on modal strain energy and neural networks[J].Noise and Vibration Control,2011,31(3):120-124.(in Chinese)
    [7]赵卓,王晓阳,梁军.基于模态分析和神经网络的裂缝损伤识别[J].世界地震工程,2006,22(2):104-109.Zhao Zhuo,Wang Xiaoyang,Liang Jun.The crack damage identification by the modal analysis and artificial neural networks[J].World Earthquake Eenineering,2006,22(2):104-109.(in Chinese)
    [8]Dong Xiaoma,Wang Zhonghui.Damage severity assessment using modified BP neural network[C]∥Materials Science and Engineering,2010 International Conference on Materials Science and Engineering Science.Shenzhen,China:Trans Tech Publications,2011:1016-1020.
    [9]Zhang Jun.Structural damage detection using parameters combined with changes in flexibility based on BP neural networks[C]∥Advances in Civil Engineering and Architecture,1st International Conference on Civil Engineering.Haikou,China:Trans Tech Publications,2011:5475-5480.
    [10]Diao Yansong,Yu Fei,Meng Dongmei.Structural damage localization based on AR model and BP neural network[C]∥Advances in Structural Engineering,2011International Conference on Civil Engineering and Transportation.Jinan,China:Trans Tech Publications,2011:1211-1215.
    [11]Guo Lin,Wei Jianjun.Structural damage detection based on BP neural network technique[C]∥2010International Conference on Intelligent Computation Technology and Automation.Changsha,China:IEEE Computer Society,2010:398-401.
    [12]李德葆,陆秋海.实验模态分析及其应用[M].北京:科学出版社,2001:216-225.
    [13]Fu Jiyang,Liang Shuguo,Li Qiusheng.Prediction of wind-induced pressures on a large gymnasium roof using artificial neural networks[J].Computers&Structures,2007,85(3):179-192.
    [14]Sundareshan M K,Amoozegar F.Neural network fusion capabilities for efficient implementation of tracking algorithms[J].Optical Engineering,1997,36(3):682-707.

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