登录    |    注册

您好,欢迎来到中国测试科技资讯平台!

首页>《中国测试》期刊>本期导读>基于VMD能量熵和BP神经网络风电叶片缺陷研究

基于VMD能量熵和BP神经网络风电叶片缺陷研究

406    2018-09-27

¥0.50

全文售价

作者:张鹏林1, 徐旭2, 杨超1, 董拴涛1

作者单位:1. 兰州理工大学材料科学与工程学院, 甘肃 兰州 730050;
2. 兰州兰石检测技术有限公司, 甘肃 兰州 730314


关键词:叶片缺陷;变分模态分解;能量熵;BP神经网络


摘要:

针对叶片在服役过程中缺陷特征提取困难,提出一种基于变分模态能量熵结合BP神经网络的叶片缺陷诊断方法。首先对声发射信号进行变分模态分解,通过方差贡献率筛选不同缺陷的主要模态分量,之后求取不同缺陷主要模态分量的能量熵构造不同缺陷的特征向量。为验证特征向量选取的准确性,将不同缺陷能量熵向量输入BP神经网络进行缺陷模式识别。结果表明:缺陷识别正确率高达90%,表明变分模态能量熵结合BP神经网络的叶片缺陷诊断方法能够实现叶片早期缺陷识别,具有一定的应用价值。


Research on the fault of the wind turbine based on variational mode energy entropy and BP neural network

ZHANG Penglin1, XU Xu2, YANG Chao1, DONG Shuantao1

1. School of Materials Science and Engineering, Lanzhou University of Technology, Lanzhou 730050, China;
2. Lanzhou LS Testing Technology Co., Ltd., Lanzhou 730314, China

Abstract: Given the difficulty to extract the defect features of blades during service, a diagnosis method of blade defects based on variational mode decomposition (VMD) energy entropy and BP neural network is proposed in this paper. Firstly, the acoustic emission signal originated from blade was decomposed by VMD, and the intrinsic mode functions (IMF) containing main feature information were selected through the variance contribution rate. Then, the energy entropy of IMF of different defects is obtained to construct the eigenvector of different defects. Finally, in order to verify the accuracy of the eigenvector selected, the energy entropy vector of different defects was input to BP neural network to achieve defect mode recognition. The results show that the accuracy of defect recognition is higher than 90%, and the diagnosis method of blade defect with a combination of VMD energy entropy and BP neural network can realize the blade defect recognition in early stage, with certain application value.

Keywords: fault of blade;VMD;energy entropy;BP neural netwok

2018, 44(9): 115-120,130  收稿日期: 2017-12-03;收到修改稿日期: 2018-01-25

基金项目: 

作者简介: 张鹏林(1973-),男,甘肃景泰县人,副研究员,博士,主要从事无损检测新技术、无损评价等方面的研究

参考文献

[1] MAHMOOD M S, ROHAM R. Simulation of fatigue failure in a full composite wind turbine blade[J]. Composite Structure, 2006(74):332-342
[2] 袁洪芳, 周璐, 柯细勇, 等. 基于声发射信号的风机叶片裂纹定位分析[J]. 计算机工程与设计, 2011, 32(1):320-323
[3] 周伟, 孙诗茹, 冯艳娜, 等. 叶片复合材料拉伸损伤破坏声发射行为[J]. 复合材料学报, 2013, 30(2):240-246
[4] 徐锋, 刘云飞. 基于EMD-SVD的声发射信号特征提取及分类方法[J]. 应用基础与工程科学学报, 2014, 22(6):1238-1247
[5] JOOSSE P A, BLANCH M J, DUTTON A C, et al. Acoustic emission monitoring of small wind turbine blades[J]. Journal of Tribology-Transactions of The ASME, 2002, 124(11):446-454
[6] GOUTHAM R K, VISHAL S, MARK J S, et al. Monitoring multisite damage growth during quasi-static testing of a wind turbine blade using a structural neural system[J]. Structural Health Monitoring, 2008, 7(2):157-173
[7] 曹婷, 郑源. 风力机故障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
[8] JIALIN T, SLIM S, CRISTINEL M. An experimental study of acoustic emission methodology for in service condition monitoring of wind turbine blades[J]. Renewable Energy, 2016, 99(1):170-179
[9] 陈长征, 赵新光, 周勃, 等. 风电机组叶片裂纹故障特征提取方法[J]. 中国电机工程学报, 2013, 33(2):112-117
[10] 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
[11] 张宁, 朱永利, 高艳丰, 等. 基于变分模态分解和概率密度估计的变压器绕组变形在线检测方法[J]. 电网技术, 2016, 40(1):297-302
[12] 唐贵基, 王晓龙. 参数优化变分模态分解方法在滚动轴承早期故障诊断中的应用[J]. 西安交通大学学报, 2015, 49(5):73-81
[13] 刘长良, 武英杰, 甄成刚. 基于变分模态和模糊C均值聚类的滚动轴承故障诊断[J]. 中国电机工程学报, 2015, 35(13):3358-3365
[14] 武英杰, 甄成刚, 刘长良. 变分模态分解在风电机组故障诊断中的应用[J]. 机械传动, 2015, 39(10):129-132
[15] CHRISTOPHER B, GREGORY N, MORSCHER, V, et al. Transverse cracking in carbon fiber reinforced polymer composites:Modal acoustic emission and peak frequency analysis[J]. Composites Science and Technology, 2015(116):26-32
[16] GUTKIN R, GREEN CJ, VANGRATTANACHAIS, et al. On acoustic emission for failure investigation in CFRP:pattern recognition and peak frequency analyses[J]. Mechanical systems and Signal Process, 2011(25):1393-1407
[17] 蒋丽英, 高爽, 崔建国, 等. 基于VMD和平均能量的齿轮故障特征提取[J]. 沈阳航空航天大学学报, 2016, 33(6):59-65
[18] 郭晶, 孙伟娟. 神经网络理论与MATLAB7实现[M]. 北京:电子工业出版社, 2005:32-41.
[19] 史峰, 王小川, 郁磊, 等. MATLAB神经网络30个案例分析[M]. 北京:北京航空航天大学出版社, 2010:55-69.
[20] 林琳. 基于BP神经网络的网格性能预测[D]. 长春:吉林大学, 2004.
[21] 吴松林, 张福明, 林晓东. 基于小波神经网络的滚动轴承故障诊断[J]. 空军工程大学学报, 2008, 9(1):50-53
[22] 周开利, 康耀红. 神经网络模型及其MATLAB仿真程序设计[M]. 北京:清华大学出版社, 2005:55-69.