基于谐波小波包和支持向量机的风机叶片损伤识别研究

复合材料科学与工程 ›› 2014, Vol. 0 ›› Issue (4): 37-41.

基于谐波小波包和支持向量机的风机叶片损伤识别研究

饶金根^*, 顾桂梅

兰州交通大学自动化与电气工程学院,兰州730070

收稿日期:2013-11-25 发布日期:2021-09-17
作者简介:饶金根(1987-),男,硕士生,主要从事风电叶片损伤研究,527169120@qq.com。
基金资助:
兰州交通大学科技支撑基金资助项目(ZC2012008)

WIND TURBINE BLADE DAMAGE IDENTIFICATION BASED ON HARMONIC WAVELET PACKET AND SUPPORT VECTOR MACHINE

RAO Jin-gen^*, GU Gui-mei

College of Automation and Electrical Engineering, Lanzhou Jiao Tong University, Lanzhou 730070, China

Received:2013-11-25 Published:2021-09-17

摘要/Abstract

摘要： 为了解决风机叶片损伤类型识别的问题,提出了一种基于谐波小波包和支持向量机相结合的声发射源识别方法。由叶片损伤产生的声发射信号经过4层谐波小波包分解后,提取各频段的能量作为特征向量构建支持向量机分类器,通过支持向量机判别叶片损伤类型。在对叶片损伤进行识别时,分别采用谐波小波包和Daubechies小波包分解声发射信号,并进行比较。实验结果表明,采用谐波小波包和支持向量机相结合的方法可以得到良好的识别效果。

关键词: 风机叶片, 声发射, 谐波小波包, 支持向量机

Abstract: In order to solve the wind turbine blade damage type identification problem, a new approach for acoustic emission (AE) source type identification based on harmonic wavelet packet (HWP)and support vector machine is proposed. The type of blade damage was distinguished by SVM which was built by using the energy as the feature vectors for the support vector machine classifier, where the energy was extracted in different frequency bands from the acoustic emission generated by the blades after a four-level decomposition of HWP.In recognition of the blade for damage, the AE signals were decomposed using harmonic wavelet packet and daubechies wavelet packet and compared with each other. The results show that good recognition results could be obtained using HWP and SVM combined method.

Key words: wind turbine blade, acoustic emission, harmonic wavelet packet, support vector machines

中图分类号:

TB332
TN98

饶金根, 顾桂梅. 基于谐波小波包和支持向量机的风机叶片损伤识别研究[J]. 复合材料科学与工程, 2014, 0(4): 37-41.

RAO Jin-gen, GU Gui-mei. WIND TURBINE BLADE DAMAGE IDENTIFICATION BASED ON HARMONIC WAVELET PACKET AND SUPPORT VECTOR MACHINE[J]. COMPOSITES SCIENCE AND ENGINEERING, 2014, 0(4): 37-41.

参考文献

[1] 萨昊两,李成良,余启明等.风电叶片疲劳试验振动分析与研究[J].玻璃钢/复合材料,2013,(2): 57-59.
[2] 徐阳,刘卫生,乔光辉.兆瓦级大型风力发电机叶片的无损检测[J].玻璃钢/复合材料,2013,(3): 76-79.
[3] Chotard T J.New applications of acousticemisssion technique for real-time monitoring of material processes[J].Journal of Material ScienceLetters, 2002,(21):1261-1266.
[4] 邓宗白,单珂.风机叶片复合材料裂纹损伤的声发射实验研究[J].机械与电子,2013,(3):13-17.
[5] 葛邦,杨涛,高殿斌等.复合材料无损检测技术研究进展[J].玻璃钢/复合材料,2009,(6):67-71.
[6] Doutton A G,Blanch M.Acoustic emission monito-ring from wind turbine blades undergoing satic dynamic fatigue testing[J].Insight,2000,42(12):805-808.
[7] Bent F S,Lars L,Peter S,et al.Fundamentals for remote structural health montioring of wind turbine blades-A preproject[R].Roskilde:Riso National Laboratory,2002.
[8] Goutham R K,Vishal S,Mark J S,et al. Montioring multisite damage growth during quasi-satic testing of a wind turbine blades using a structural neura system[J].Structural Health Montioring,2008,7(2):157-173.
[9] 韩敬宇.基于声发射技术的风电叶片裂纹无线监测系统研究[D].北京:北京化工大学,2010.
[10] 朱永凯,潘仁前,陈盛粟.基于声发射传感器阵列的风机叶片结构监测方法[J].无损检测,2010, 32(10):753-761.
[11] Newland D E.Harmonic wavelet analysis[J]. Soc .Land:A,1993,443:203-225.
[12] 高强,何正嘉.谐波小波及其时频剖面图在旋转机械诊断中的应用[J].西安交通大学学报, 2000,34(9):62-66.
[13] 章克来,朱海明.微弱信号检测技术[J].航空电子技术,2009,40(2):30-35.
[14] 贾伟广,胡丹,车畅.基于小波分析和支持向量机的刀具故障诊断[J].组合机床与自动化加工技术,2010,(12): 65-68.
[15] Yu Jintao,Ding Mingli,Meng Fangang,etal.Acou-stic emission source identification based on har-monic wavelet packet and support vectormachine [J].Journal of Southeast University,2011,27(3):300-304.