Damage Identification for Bridge Structures Based on the Wavelet Neural Network Method
-
摘要: 桥梁结构在服役期间会承受复杂的荷载,长期使用会不可避免地出现各种损伤。若这些损伤不能被及时发现和适当处理,将有可能造成严重的事故。因此,桥梁结构的局部小损伤识别对于其及时检修有重要意义。通常,损伤结构的全局动态特性测试可能对局部的结构损伤不敏感,特别是对小损伤,这就需要从结构动态响应信号中提取对损伤更敏感的特征量。建立了桥梁结构的有限元模型并进行动力特性分析;采用小波包分析方法处理结构动态响应信号以构造结构损伤指标,并结合结构损伤指标和人工神经网络方法进行桥梁结构的损伤定位.Abstract: Bridge structures will suffer complex loading environment during their service, and inevitable damages of structures may occur in long term service. If a damage can’t be found in time and treated properly, it may cause serious accidents. Therefore, the local small damage identification for bridge structures is of great significance for the timely maintenance. Generally, the measured global dynamic properties of a damaged structure are not sensitive enough to the local structural damages, especially to small damages, thus, it is necessary to extract more sensitive feature information to structural damages from the structural dynamic response signals. The finite element model of a bridge structure was established, and the dynamic characteristics were analyzed. The wavelet packet analysis was used to process the structural dynamic response signals and the structural damage index was presented. Then the damages of the bridge structure were positioned according to the damage index with the artificial wavelet neural network method. The results show that the wavelet packet energy change ratio makes an effective damage index; the properly trained neural network can fairly precisely position the bridge structural damages in the numerical test; the higher the damage degree is, the lower the positioning error comes.
-
[1] Chang P C, Flatau A, Liu S C. Review paper: health monitoring of civil infrastructure[J].Structural Health Monitoring,2003,2(3): 257-267. [2] Taha M M R, Noureldin A, Lucero J L, Baca T J. Wavelet transform for structural health monitoring: a compendium of uses and features[J].Structural Health Monitoring,2006,5(3): 267-295. [3] 姜绍飞, 徐云良, 张春梅. 基于小波包分解的数据融合损伤识别方法[J]. 沈阳建筑大学学报(自然科学版), 2006,22(6): 881-884.(JIANG Shao-fei, XU Yun-liang, ZHANG Chun-mei. The damage identification method of data fusion based on wavelet packet decomposition[J].Journal of Shenyang Jianzhu University(Natural Science),2006,22(6): 881-884.(in Chinese)) [4] 丁幼亮, 李爱群. 基于振动测试与小波包分析的结构损伤预警[J]. 力学学报, 2006,38(5): 639-644.(DING You-liang, LI Ai-qun. Structural damage early warning based on vibration testing and wavelet packet analysis[J].Chinese Journal of Theoretical and Applied Mechanics,2006,38(5): 639-644.(in Chinese)) [5] Law S S, Li X Y, Lu Z R. Structural damage detection from wavelet coefficient sensitivity with model errors[J].Journal of Engineering Mechanics,2006,132(10): 1077-1087. [6] 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 Damage Detection Based on Neural Networks [M]. Beijing: Science Press, 2002.(in Chinese)) [7] Dworakowski Z, Ambrozinski L, Packo P, Dragan K, Stepinski T. Application of artificial neural networks for compounding multiple damage indices in Lamb-wave-based damage detection[J].Structural Control and Health Monitoring,2015,22(1): 50-61. [8] Yu S N, Chou K T. Integration of independent component analysis and neural networks for ECG beat classification[J].Expert Systems With Applications,2008,34(4): 2841-2846. [9] 虞和济, 陈长征, 张省, 周建男. 基于神经网络的智能诊断[M]. 北京: 冶金工业出版社, 2000.(YU He-ji, CHEN Chang-zheng, ZHANG Xing, ZHOU Jian-nan.Intelligent Diagnosis Based on Neural Networks [M]. Beijing: Metallurgical Industry Press, 2000.(in Chinese)) [10] Hakim S J S, Abdul R H. Structural damage detection of steel bridge girder using artificial neural networks and finite element models[J].Steel and Composite Structures,2013,4(14): 367-377. [11] Arangio S, Bontempi F. Structural health monitoring of a cable-stayed bridge with Bayesian neural networks[J].Structure and Infrastructure Engineering: Maintenance, Management, Life-Cycle Design and Performance,2015,11(4): 575-587. [12] Dackermann U, Smith W A, Randall R B. Damage identification based on response-only measurements using cepstrum analysis and artificial neural networks[J].Structural Health Monitoring,2014,13(4): 430-444. [13] 闫云聚, 韩莉, 余龙, 姜节胜. 改进的小损伤结构动力学有限元建模方法[J]. 应用力学学报, 2005,22(3): 431-434.(YAN Yun-ju, HAN Li, YU Long, JIANG Jie-sheng. Improved dynamical modeling method for structure with small damage[J].Chinese Journal of Applied Mechanics,2005,22(3): 431-434.(in Chinese))
点击查看大图
计量
- 文章访问数: 1668
- HTML全文浏览量: 172
- PDF下载量: 759
- 被引次数: 0