基于支持向量机的碳纤维增强复合材料梁的分层损伤识别

玻璃钢/复合材料 ›› 2018, Vol. 0 ›› Issue (7): 12-18.

基于支持向量机的碳纤维增强复合材料梁的分层损伤识别

贺梦悦, 梁智洪, 张芝芳^*

广州大学-淡江大学工程结构灾害与控制联合研究中心,广州 510006

收稿日期:2018-04-09 出版日期:2018-07-20 发布日期:2018-07-20
通讯作者: 张芝芳(1985-),女,博士,副研究员,主要从事复合材料损伤识别和健康监测方面的研究,zfzhang@gzhu.edu.cn。
作者简介:贺梦悦(1994-),女,硕士生,主要从事复合材料损伤识别方面的研究。
基金资助:
国家自然科学基金项目(51508118);广东省自然科学基金项目(2016A030310261);广东省科技计划项目(2016B050501004)

DELAMINATION IDENTIFICATION OF COMPOSITE LAMINATED BEAMS BASED ON SUPPORT VECTOR MACHINE

HE Meng-yue, LIANG Zhi-hong, ZHANG Zhi-fang^*

Guangzhou University-Tamkang University Joint Research Center for Engineering Structure Disaster Prevention and Control, Guangzhou 510006, China

Received:2018-04-09 Online:2018-07-20 Published:2018-07-20

摘要/Abstract

摘要： 针对目前支持向量机(SVM)运用于复合材料的分层损伤识别的有关研究尚少,采用归一化后的模态频率,基于SVM回归理论对碳纤维增强复合材料(CFRP)悬臂梁的分层损伤位置、大小及分层界面进行了损伤识别。首先建立了CFRP梁的有限元模型,得到“损伤变量-模态频率”的数据库和数值测试案例,对比不同参数优化方法下的SVM回归预测效果。然后使用德国Polytec激光扫描测振仪进行模态试验获取CFRP梁试件的模态频率值,将实测频率值用于SVM回归预测,进一步证实了SVM在CFRP梁结构的分层损伤识别领域的应用前景。

关键词: 支持向量机, 碳纤维增强复合材料, 损伤识别, 频率

Abstract: Support vector machine (SVM) has not yet been introduced to detect delaminations for fibre reinforced composite materials, and this paper is proposed to assess the delaminations in carbon fiber reinforced polymer (CFRP) beams based on SVM regression, through the changes in modal frequencies due to the damage occurs. Firstly, the finite element model of CFRP beam was established to generate the database of "delamination variables vs. modal frequencies" as well as the test cases for numerical validation. Three different parameter optimization methods, namely, cross validation (CV), genetic algorithm (GA) and particle swarm optimization (PSO), were applied to obtain the suitable parameters for SVM to improve the prediction accuracy. Furthermore, the Polytec laser scanning vibrameter was adopted to conduct the model testing for CFRP beam specimens. The measured frequencies of the specimens were used for validating the SVM regression experimentally, which confirmed that the SVM can be used to detect delamination in CFRP beams.

Key words: support vector machine, CFRP, damage detection, frequency

中图分类号:

TB332

贺梦悦, 梁智洪, 张芝芳. 基于支持向量机的碳纤维增强复合材料梁的分层损伤识别[J]. 玻璃钢/复合材料, 2018, 0(7): 12-18.

HE Meng-yue,LIANG Zhi-hong,ZHANG Zhi-fang*. DELAMINATION IDENTIFICATION OF COMPOSITE LAMINATED BEAMS BASED ON SUPPORT VECTOR MACHINE[J]. Fiber Reinforced Plastics/Composites, 2018, 0(7): 12-18.

参考文献

[1] Bolotin V V. Delaminations in composite structures: Its origin, buck-ling, growth and stability[J]. Composites Part B Engineering, 1996, 27(2): 129-145.
[2] Bolotin V V. Mechanics of delaminations in laminate composite structures[J]. Mechanics of Composite Materials, 2001, 37(5-6): 367-380.
[3] 陆荣林, 费云鹏, 白宝泉. 微波检测原理及其在复合材料中的应用[J]. 玻璃钢/复合材料, 2001(2): 40-41.
[4] Doebling S W, Farrar C R, Prime M B. A summary review of vibration-based damage identification methods[J]. Shock and vibration digest, 1998, 30(2): 91-105.
[5] 高芳清, 金建明. 基于模态分析的结构损伤检测方法研究[J]. 西南交通大学学报, 1998, 33(1): 108-113.
[6] Hearn G, Testa R B. Modal analysis for damage detection in structures[J]. Journal of structural engineering, 1991, 117(10): 3042-3063.
[7] Bottou L, Cortes C, Denker J S, et al. Comparison of classifier methods: a case study in handwritten digit recognition[C]//International Conference on Pattern Recognition. IEEE Xplore, 1994: 77-82.
[8] Ng J, Gong S. Multi-View face detection and pose estimation using a composite support vector machine across the view sphere[C]//International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems. IEEE Computer Society, 1999: 14.
[9] Park S, Inman D J, Lee J J, 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.
[10] He F, Shi W. WPT-SVMs based approach for fault detection of valves in reciprocating pumps[C]//American Control Conference, Proceedings of the IEEE, 2002: 4566-4570.
[11] Worden K, Lane A J. Damage identification using support vector machines[J]. Smart Materials and Structures, 2001, 10(3): 540.
[12] 何浩祥, 闫维明, 彭凌云. 基于支持向量机的钢筋混凝土桥梁损伤识别[J]. 公路交通科技, 2008, 25(3): 65-69.
[13] 孙卫泉. 基于支持向量机的梁桥损伤识别[D]. 成都: 西南交通大学, 2008.
[14] Vapnik V. Statistical learning theory[M]. New York, 1998.
[15] Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines[J]. IEEE transactions on Neural Networks, 2002, 13(2): 415-425.
[16] Zhang Z, Shankar K, Morozov E V, et al. Vibration-based delamination detection in composite beams through frequency changes[J]. Journal of Vibration and Control, 2016, 22(2): 496-512.
[17] Ramkumar R L, Kulkarni S V, Pipes R B. Free vibration frequencies of a delaminated beam[J]. Reinforcing the future, 1979.
[18] Mujumdar P M, Suryanarayan S. Flexural vibrations of beams with delaminations[J]. Journal of sound and vibration, 1988, 125(3): 441-461.
[19] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACM transactions on intelligent systems and technology (TIST), 2011, 2(3): 27.