• 中国科技论文统计源期刊
  • 中文核心期刊
  • 中国科技核心期刊
  • 中国机械工程学会无损检测分会会刊
高级检索

基于CEEMDAN能量熵和SVM的风电叶片缺陷检测

蒋菲, 赵朝友, 张素慧

蒋菲, 赵朝友, 张素慧. 基于CEEMDAN能量熵和SVM的风电叶片缺陷检测[J]. 无损检测, 2021, 43(6): 36-40. DOI: 10.11973/wsjc202106009
引用本文: 蒋菲, 赵朝友, 张素慧. 基于CEEMDAN能量熵和SVM的风电叶片缺陷检测[J]. 无损检测, 2021, 43(6): 36-40. DOI: 10.11973/wsjc202106009
JIANG Fei, ZHAO Chaoyou, ZHANG Suhui. Defect testing of wind turbine blades based on CEEMDAN energy entropy and SVM[J]. Nondestructive Testing, 2021, 43(6): 36-40. DOI: 10.11973/wsjc202106009
Citation: JIANG Fei, ZHAO Chaoyou, ZHANG Suhui. Defect testing of wind turbine blades based on CEEMDAN energy entropy and SVM[J]. Nondestructive Testing, 2021, 43(6): 36-40. DOI: 10.11973/wsjc202106009

基于CEEMDAN能量熵和SVM的风电叶片缺陷检测

详细信息
    作者简介:

    蒋菲(1990-),女,硕士,工程师,主要从事电力设备的运维检修工作

    通讯作者:

    蒋菲, E-mail:cailiaojiangfei@163.com

  • 中图分类号: TG115.28

Defect testing of wind turbine blades based on CEEMDAN energy entropy and SVM

  • 摘要: 针对目前风电叶片缺陷特征提取的问题,提出了一种基于完全噪声辅助集总经验模态分解(CEEMDAN)和支持向量机(SVM)相结合的叶片缺陷诊断识别方法。通过对采集的声发射信号进行CEEMDAN,借助互相关系数筛选叶片缺陷的主要模态分量,然后构造主要模态分量的能量熵向量。为验证能量熵向量构造的可靠性,对叶片不同缺陷进行能量熵向量的支持向量机模式识别。结果表明,SVM模式识别准确率高达96.7%,说明基于CEEMDAN结合SVM的叶片缺陷识别方法能够实现叶片模拟缺陷的识别,为在役叶片缺陷的识别提供了一定的参考。
    Abstract: Considering the difficulty of the extracting for the fault feature of blade in service, an intelligent recognition method for defects in blade based on Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) combined with support vector machine (SVM) is proposed. First of all, the signals originated from defects of the blade were decomposed by Complete Ensemble Empirical Mode Decomposition with adaptive noise, and the intrinsic mode functions (IMF) containing the main feature information were selected by cross-correlation number. Then, the main Energy Entropy of the intrinsic mode functions was calculated and the vectors of Complete Ensemble Empirical Mode Decomposition with adaptive noise energy entropy were constructed. Finally, in order to verify the reliability of vector of energy entropy, the pattern recognition was carried out by the support vector machine (SVM) for different defects. The results show that the average recognition rate for different faults were as high as 96.7%, and it suggests that the method of Complete ensemble empirical mode decomposition with adaptive noise energy entropy combined with SVM can be supplied well for recognizing and warning in blade during the early process.
  • [1] 张晓霞, 戚海东,王芳,等.风电叶片复合材料层间剪切破坏声发射监测[J].工程塑料应用,2012,40(8):77-80.
    [2] 周勃, 陈维涛,贺森亮,等.风力发电机叶片多裂纹随机扩展和损伤容限研究[J].太阳能学报,2015,36(12):2837-2843.
    [3] 李海斌, 阳建红,刘承武,等.复合材料随机渐进失效分析与声发射监测[J].复合材料学报,2011,28(1):223-229.
    [4]

    JOOSSE P A,BLANCH M J, DUTTONET A G, et al. Acoustic emission monitoring of small wind turbine blades[J]. Journal of Tribology-Transactions of the ASME, 2002,124(11):446-454.

    [5]

    TANG J L,SOUA S,MARES C,et al.An experimental study of acoustic emission methodology for in service condition monitoring of wind turbine blades[J].Renewable Energy,2016,99:170-179.

    [6] 陈长征, 赵新光,周勃,等.风电机组叶片裂纹缺陷特征提取方法[J].中国电机工程学报,2013,33(2):112-117.
    [7] 周勃, 谷艳玲,项宏伟,等.风力机叶片裂纹扩展预测与疲劳损伤评价[J].太阳能学报,2015,36(1):41-47.
    [8] 曹婷, 郑源.风力机缺陷诊断神经网络特征参数确定方法[J].排灌机械工程学报,2014,32(3):247-251.
    [9] 饶金根, 顾桂梅.基于谐波小波包和支持向量机的风电叶片损伤识别研究[J].玻璃钢/复合材料,2014(4):37-40.
    [10] 何刘, 丁建明,林建辉,等. 完全互补小波噪声辅助集总经验模态分解[J]. 振动与冲击,2017,36(4):232-242.
    [11] 王文哲, 吴华,王经商. 基于CEEMDAN的雷达信号脉内细微特征提取法[J].北京航空航天大学学报,2016,42(11):2532-2539.
    [12] 于明月, 陈果,李成刚,等. 基于小波包分析和支持向量机的转静碰摩部位识别[J]. 航空动力学报,2013,28(1):46-53.
计量
  • 文章访问数:  6
  • HTML全文浏览量:  0
  • PDF下载量:  3
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-10-18
  • 刊出日期:  2021-06-09

目录

    /

    返回文章
    返回