[1]刘义艳,陈 晨,俞竣瀚.基于多传感器信息融合的SVM 结构损伤诊断方法[J].西安建筑科技大学学报:自然科学版,2013,45(06):803-807.[doi:10.15986/j.1006-7930.2013.06.008]
　LIU Yi-yan,CHEN Chen,YU Jun-han.A structure damage diagnosis method based on multi-sensor information fusion and support vector machine[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2013,45(06):803-807.[doi:10.15986/j.1006-7930.2013.06.008]
点击复制

基于多传感器信息融合的SVM 结构损伤诊断方法()
分享到：

西安建筑科技大学学报:自然科学版[ISSN:1006-7930/CN:61-1295/TU]

卷:
45
期数:
2013年06期
页码:
803-807
栏目:
出版日期:
2013-12-31

文章信息/Info

Title:
A structure damage diagnosis method based on multi-sensor information fusion and support vector machine
文章编号:
1006-7930(2013)06-0803-05
作者:
刘义艳1; 陈 晨2; 俞竣瀚1
(1.长安大学电控学院,陕西 西安 710064; 2.汉中市建筑勘察设计研究院,陕西 汉中 723000)
Author(s):
LIU Yi-yan1; CHEN Chen2; YU Jun-han1
(1.School of Electronic and Control Engineering, Changan University, Xian 710064,China; 2.Institute of Construction Survey and Design of Hanzhong, Hanzhong 723000,China)
关键词:
聚类经验模式分解; 小波包频带能量; 支持向量机; 信息融合; 损伤诊断
Keywords:
ensemble empirical mode decomposition (EEMD); wavelet packet frequency band energy;  support vector machine (SVM);  information fusion;  damage diagnosis
分类号:
TU 973.2;TU 311.3
DOI:
10.15986/j.1006-7930.2013.06.008
文献标志码:
A
摘要:
为了能准确地诊断复杂结构损伤的发生、位置和程度,提出了一种聚类经验模式分解(EEMD)、小波包分解(WPT)、多传感器信息融合和SVM 模式分类相结合的结构损伤诊断方法.首先对多个传感器采集的加速度振动信号进行EEMD分解,选择包含结构损伤信息丰富的固有模态函数(IMF);其次对其进行正交小波包分解,并计算小波包相对能量分布;最后把这些传感器信号的小波包相对能量融合,构成SVM 分类器的输入特征向量,从而实现损伤的诊断和评价.研究结果表明:该方法在学习样本数较少的情况下仍然具有较好的适应性和分类能力;多传感器信息融合技术减小了损伤检测信息的不确定性,提高了损伤诊断准确率.
Abstract:
In order to make a diagnosis of damage occurrence, position and degree of the complex structures accurately, a structural damage diagnosis method was presented by means of ensemble empirical mode decomposition(EEMD),wavelet packet decomposition, and multi-sensor feature fusion theory and support vector machine(SVM)pattern classification. Firstly, the response signals of the ASCE benchmark structure are processed by using EEMD, and the intrinsic mode function(IMF)which contains structural damage information are selected. Secondly, the selected IMF is decomposed by orthogonal WPT, and also wavelet package energy(WPE)on decomposition frequency bands are calculated. Thirdly, the input feature vectors of SVM classifier were built by fusing wavelet packet relative energy distribution of these sensors. Finally, with the trained classifier, damage diagnosis and assessment was realized. The result indicated that it still has good adaptability and classification capability in the case of small samples and the fused feature can reduce the uncertainty of damage detection information, with the diagnosis accuracy improved

参考文献/References:

[1] GAETAN K, KEITH W, ALEXANDER F V, et al. Past, present and future of nonlinear system identification in structural dynamics [J].Mechanical systems and signal processing, 2006(20) :505-592.
[2] LEI Ya-guo, HE Zheng-jia, ZI Yan-yang. Application of the EEMD method to rotor fault diagnosis of rotating machinery [J].Mechanical Systems and Signal Processing, 2009, 23(4) :1327-1338.
[3] 边肇祺, 张学工. 模式识别[M]. 2 版. 北 京: 清华大学出版社,2000.
BIAN Zhao-qi, ZHANG Xue-gong. Workers Pattern Recognition [ M].2nd ed. Beijing: Tsinghua University Press, 2000.
[4] PARK Seunghee, INMAN DanielJ, LEE Jong-Jae, et al. Piezoelectric Sensor-Based Health Monitoring of Railroad Tracks Using a Two-Step Support Vector Machine Classifier [J].Journal of Infrastructure Systems, 2008, 14(1) :80-88.
[5] XIE Jian-hong. Structural damage detection based on fuzzy LS-SVM integrated quantum genetic algorithm [J].In-formation Technologyfor Manufacturing Systems, 2010(20/23) :1365-1371.
[6] 刘春城, 刘 佼. 基于支持向量机的大跨度拱桥损伤识别方法研究[J]. 振动与冲击,2010,29(7) :174-244.
LIU Chun-cheng, LIU Jiao. Damage identification of a long-span arch bridge based on support vector machine [J].Journal of Vibration and Shock, 2010, 29(7) :174-244.
[7] LIU Yi-Yan, JU Yong-Feng, DUAN Chen-Dong, et al. Structure Damage Diagnosis Using Neural Network and Feature Fusion [J].Engineering Applications and Artificial Intelligence, 2011, 24(1) :87-92.
[8] WU Z H, HUANG N E. Ensemble Empirical Mode Decomposition: A Noise Assisted Data Analysis Method [J].Advances in Adaptive Data Analysis, 2009(1) :1-41.
[9] 刘义艳, 贺栓海, 巨永锋, 等. 基 于 EEMD 和 WPT 的 结 构 损 伤 特 征 提 取[J]. 振 动? 测 试 与 诊 断,2012, 32(2) :256-260.
LIU Yi-yan, HE Shuan-hai, JU Yong-feng, et al. Structure Damage Feature Extraction Based on EEMD and WPT[J].Journal of Vibration, Measurement & Diagnosis, 2012, 32(2) :256-260.
[10] ZUBAIDAH Ismail, ZHI Chao-ong. Honey comb damage detection in a reinforced concrete beam using frequency mode shape regression [J]. Measurement, 2012, 45(4) : 950-959.
[11] REN Wei-Xin, SUN Zeng-Shou, XIA Yong. Damage Identification of Shear Connectors with Wavelet Packet Energy: Laboratory Test Study [J].Journal of Structural Engineering, 2008, 134(5) :832-841.
[12] JOHNSON E A, LAM H F, KATAFYGIOTIS L S, et al. Phase I IASC-ASCE structural health monitoring benchmark problem using simulated data [J].Journal of Engineering Mechanics, 2004, 130(1) : 3-15.

备注/Memo

备注/Memo:
收稿日期:2013-03-26 修改稿日期:2013-11-25
基金项目:中国博士后基金资助项目(20110491637);国家青年自然科学基金资助项目(61201407,61203374);中央高校基本科研业务费的资助项目(2013G1321044)
作者简介:刘义艳(1981-),女,陕西镇安人,博士研究生,副教授,从事结构健康监测与损伤诊断研究工作.
更新日期/Last Update: 2015-10-05