[1]邓敏强,邓艾东,朱静,等.基于BFD和MSCNN的风电滚动轴承智能故障诊断[J].东南大学学报(自然科学版),2021,51(3):521-528.[doi:10.3969/j.issn.1001-0505.2021.03.022]
 Deng Minqiang,Deng Aidong,Zhu Jing,et al.Intelligent fault diagnosis of wind turbine rolling bearings based on BFD and MSCNN[J].Journal of Southeast University (Natural Science Edition),2021,51(3):521-528.[doi:10.3969/j.issn.1001-0505.2021.03.022]
点击复制

基于BFD和MSCNN的风电滚动轴承智能故障诊断()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
51
期数:
2021年第3期
页码:
521-528
栏目:
能源与动力工程
出版日期:
2021-05-20

文章信息/Info

Title:
Intelligent fault diagnosis of wind turbine rolling bearings based on BFD and MSCNN
作者:
邓敏强12邓艾东12朱静12史曜炜12马天霆123
1东南大学能源与环境学院, 南京 210096; 2东南大学火电机组振动国家工程研究中心, 南京 210096; 3 国华太仓发电有限公司, 苏州 215000
Author(s):
Deng Minqiang12 Deng Aidong12 Zhu Jing12 Shi Yaowei12 Ma Tianting1 23
1 School of Energy and Environment, Southeast University, Nanjing 210096, China
2 National Engineering Research Center of Turbo-Generator Vibration, Southeast University, Nanjing 210096, China
3 Guohua Taicang Power Plant Co. Ltd., Suzhou 215000, China
关键词:
风电 滚动轴承 故障诊断 带宽傅里叶分解 多尺度卷积神经网络
Keywords:
wind turbine rolling bearing fault diagnosis bandwidth Fourier decomposition(BFD) multi-scale convolutional neural network(MSCNN)
分类号:
TK83
DOI:
10.3969/j.issn.1001-0505.2021.03.022
摘要:
针对变工况下风电滚动轴承的健康状态评估问题,提出了一种基于带宽傅里叶分解(BFD)和多尺度卷积神经网络(MSCNN)的智能故障诊断方法.首先,通过BFD算法将原始振动信号分解为一系列带宽模态函数(BMF);然后,通过希尔伯特阶次变换(HOT)计算各BMF的包络阶次谱,并根据特征阶次比筛选出分解结果中包含故障信息最多的有效分量.最后,通过MSCNN学习有效分量的包络阶次谱与故障类别之间的映射关系以实现滚动轴承健康状态的自动识别.实验结果表明,所提方法采用BFD分解结果的包络阶次谱作为故障识别的特征量,能有效提高模型在不同工况下的泛化能力,其测试准确率达到97%以上,可应用于变工况条件下风电滚动轴承的智能故障诊断.
Abstract:
A novel intelligent fault diagnosis method for wind tribune rolling bearings is proposed on the basis of bandwidth Fourier decomposition(BFD)and multi-scale convolutional neural network(MSCNN). First, the measured vibration signal is decomposed into bandwidth mode functions(BMFs)through the BFD method. Then, the Hilbert order transform(HOT)is employed to obtain the envelope order spectra(EOS)of BMFs. After that, the effective component containing the most fault information is selected according to the characteristic order ratio(COR). Finally, an MSCNN is established to learn the mapping relationship between the EOS of the effective component and the fault category.The experimental results demonstrate that taking the EOS for fault identification can improve the generalization ability of the fault diagnosis model under different working conditions. The test accuracy exceeds 97%, indicating the feasibility of the proposed method in practical applications.

参考文献/References:

[1] Syed I, Khadkikar V, Zeineldin H H. Loss reduction in radial distribution networks using a solid-state transformer[J]. IEEE Transactions on Industry Applications, 2018, 54(5): 5474-5482. DOI:10.1109/TIA.2018.2840533.
[2] Ishaq H, Dincer I, Naterer G F. Development and assessment of a solar, wind and hydrogen hybrid trigeneration system[J]. International Journal of Hydrogen Energy, 2018, 43(52): 23148-23160. DOI:10.1016/j.ijhydene.2018.10.172.
[3] 万书亭, 张雄, 南冰, 等. 基于PPCA-1.5维能量谱的滚动轴承故障诊断[J]. 电力自动化设备, 2018, 38(6): 172-176,182. DOI:10.16081/j.issn.1006-6047.2018.06.025.
Wan S T, Zhang X, Nan B, et al. Fault diagnosis of rolling bearing based on PPCA and 1.5-dimensional energy spectrum[J]. Electric Power Automation Equipment, 2018, 38(6): 172-176,182. DOI:10.16081/j.issn.1006-6047.2018.06.025. (in Chinese)
[4] 唐明, 吴宏亮, 魏略, 等. 基于阶次解调谱的滚动轴承故障诊断方法[J]. 太阳能学报, 2019, 40(9): 2486-2494. DOI:10.11975/j.issn.1002-6819.2020.14.016.
Tang M, Wu H L, Wei L, et al. Fault diagnosis method for rolling bearing based on order demodulation spectrum[J]. Acta Energiae Solaris Sinica, 2019, 40(9): 2486-2494. DOI:10.11975/j.issn.1002-6819.2020.14.016. (in Chinese)
[5] 刘东东, 程卫东, 温伟刚. 基于线调频小波路径追踪和逐步解调滤波的滚动轴承故障诊断[J]. 振动与冲击, 2019, 38(11): 88-94. DOI:10.13465/j.cnki.jvs.2019.11.014.
Liu D D, Cheng W D, Wen W G. Rolling element bearing fault diagnosis based on CPP and stepwise demodulation filtering[J]. Journal of Vibration and Shock, 2019, 38(11): 88-94. DOI:10.13465/j.cnki.jvs.2019.11.014. (in Chinese)
[6] Ji D Z, Pan H Y, Cheng J S. Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]. Mechanical Systems and Signal Processing, 2017, 85: 746-759. DOI:10.1016/j.ymssp.2016.09.010.
[7] 唐贵基, 田甜, 庞彬. 基于快速谱相关和PSO-SVM的变工况滚动轴承状态识别[J]. 电力自动化设备, 2019, 39(7): 168-174. DOI:10.16081/j.issn.1006-6047.2019.07.025.
Tang G J, Tian T, Pang B. State identification of rolling bearing under variable working condition based on fast spectral correlation and PSO-SVM[J]. Electric Power Automation Equipment, 2019, 39(7): 168-174. DOI:10.16081/j.issn.1006-6047.2019.07.025. (in Chinese)
[8] 赵小强, 张青青. 改进Alexnet的滚动轴承变工况故障诊断方法[J]. 振动 测试与诊断, 2020, 40(3): 472-480,623. DOI:10.16450/j.cnki.issn.1004-6801.2020.03.007.
Zhao X Q, Zhang Q Q. Improved alexnet based fault diagnosis method for rolling bearing under variable conditions[J]. Journal of Vibration,Measurement & Diagnosis, 2020, 40(3): 472-480,623. DOI:10.16450/j.cnki.issn.1004-6801.2020.03.007. (in Chinese)
[9] 施杰, 伍星, 柳小勤, 等. 变分模态分解结合深度迁移学习诊断机械故障[J]. 农业工程学报, 2020, 36(14): 129-137. DOI:10.11975/j.issn.1002-6819.2020.14.016.
Shi J, Wu X, Liu X Q, et al. Mechanical fault diagnosis based on variational mode decomposition combined with deep transfer learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(14): 129-137. DOI:10.11975/j.issn.1002-6819.2020.14.016(in Chinese)
[10] Deng M Q, Deng A D, Zhu J, et al. Bandwidth Fourier decomposition and its application in incipient fault identification of rolling bearings[J]. Measurement Science and Technology, 2020, 31(1): 015012. DOI:10.1088/1361-6501/ab4069.
[11] Deng M Q, Deng A D, Zhu J, et al. Adaptive bandwidth Fourier decomposition method for multi-component signal processing[J]. IEEE Access, 2019, 7: 109776-109791. DOI:10.1109/ACCESS.2019.2933897.
[12] Capdessus C, Sekko E, Antoni J. Speed transform, a new time-varying frequency analysis technique [J]. Advances in Condition Monitoring of Machinery in Non-Stationary Operations, 2013, 1: 23-35. DOI:10.1007/978-3-642-39348-8_2.
[13] Jiang X B, Jin Y, Yao Y. Low-dose CT lung images denoising based on multiscale parallel convolution neural network[J]. The Visual Computer, 2020(3): 1-13. DOI:10.1007/s00371-020-01996-1.
[14] Liu R N, Wang F, Yang B Y, et al. Multiscale kernel based residual convolutional neural network for motor fault diagnosis under nonstationary conditions[J]. IEEE Transactions on Industrial Informatics, 2020, 16(6): 3797-3806. DOI:10.1109/TII.2019.2941868.
[15] Peng D D, Wang H, Liu Z L, et al. Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4949-4960. DOI:10.1109/TII.2020.2967557.

备注/Memo

备注/Memo:
收稿日期: 2020-12-07.
作者简介: 邓敏强(1993—),男,博士生;邓艾东(联系人),男,博士,教授,博士生导师,dnh@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(51875100)、东南大学优秀博士学位论文培育基金资助项目(YBPY1950).
引用本文: 邓敏强,邓艾东,朱静,等.基于BFD和MSCNN的风电滚动轴承智能故障诊断[J].东南大学学报(自然科学版),2021,51(3):521-528. DOI:10.3969/j.issn.1001-0505.2021.03.022.
更新日期/Last Update: 2021-05-20