基于改进残差网络的旋转机械故障诊断

徐硕; 邓艾东; 杨宏强; 范永胜; 邓敏强; 刘东川

doi:10.19912/j.0254-0096.tynxb.2022-0393

PDF(2376 KB)

太阳能学报 ›› 2023, Vol. 44 ›› Issue (7) : 409-418. DOI: 10.19912/j.0254-0096.tynxb.2022-0393

基于改进残差网络的旋转机械故障诊断

徐硕^1,2, 邓艾东^1,2, 杨宏强³, 范永胜³, 邓敏强^1,2, 刘东川^1,2

作者信息 +

ROTATING MACHINERY FAULT DIAGNOSIS METHOD BASED ON IMPROVED RESIDUAL NEURAL NETWORK

Xu Shuo^1,2, Deng Aidong^1,2, Yang Hongqiang³, Fan Yongsheng³, Deng Minqiang^1,2, Liu Dongchuan^1,2

Author information +

文章历史 +

摘要

针对传统风电机组轴承和齿轮箱故障诊断方法需人工提取特征而易引入人为误差和浅层神经网络提取特征困难导致诊断效果不佳的问题,提出一种基于改进残差神经网络的风电机组轴承和齿轮箱故障诊断方法。引入选择性内核网络（SKNet）结构来对卷积核执行注意力机制,引入全局上下文网络（GCNet）结构来充分利用全局上下文信息对不同通道进行权值重标定。实验结果表明,所提方法对在强噪声情况下对风电机组轴承和多维度特征的风电机组齿轮箱具有良好的故障诊断能力。

Abstract

Aiming at the problem that the traditional fault diagnosis method of wind turbine bearings and gearboxes components requires manual extraction of features and is easy to introduce human error and shallow neural network is difficult to extract features, resulting in poor diagnostic results, a fault diagnosis method for wind power bearings and gearboxes based on improved residual neural network is proposed. The selective kernel network（SKNet） structure is introduced to perform attention mechanisms on the convolution kernel, and the global context network（GCNet） structure is introduced to take full advantage of the global context information to rescale the weights of different channels. Experimental results show that the proposed method has good fault diagnosis ability for wind turbine bearings under strong noise conditions and wind turbine gearbox with multi-dimensional characteristics.

导出引用

徐硕, 邓艾东, 杨宏强, 范永胜, 邓敏强, 刘东川. 基于改进残差网络的旋转机械故障诊断[J]. 太阳能学报. 2023, 44(7): 409-418 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0393

Xu Shuo, Deng Aidong, Yang Hongqiang, Fan Yongsheng, Deng Minqiang, Liu Dongchuan. ROTATING MACHINERY FAULT DIAGNOSIS METHOD BASED ON IMPROVED RESIDUAL NEURAL NETWORK[J]. Acta Energiae Solaris Sinica. 2023, 44(7): 409-418 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0393

中图分类号： TH165+.3

参考文献

[1] 王波, 王志乐, 熊鑫州, 等. 一种改进的MRVM方法及其在风电机组轴承诊断中的应用[J]. 太阳能学报, 2021, 42(1): 215-221.
WANG B, WANG Z L, XIONG X Z, et al.An improved multi-class relevance vector and its application to wind turbine bearing diagnosis[J]. Acta energiae solaris sinica, 2021, 42(1): 215-221.
[2] 滕伟, 丁显, 史秉帅, 等. 基于WGAN-GP的风电机组传动链故障诊断[J]. 电力系统自动化, 2021, 45(22):167-173.
TENG W, DING X, SHI B S, et al.Fault diagnosis of wind turbine drivetrain based on wasserstein generative adversarial network-gradient penalty[J]. Automation of electric power systems, 2021, 45(22): 167-173.
[3] 赵凯辉, 吴思成, 李涛, 等. 基于Inception-BLSTM的滚动轴承故障诊断方法研究[J]. 振动与冲击, 2021, 40(17): 290-297.
ZHAO K H, WU S C, LI T, et al.A study on method of rolling bearing fault diagnosis based on Inception-BLSTM[J]. Journal of vibration and shock, 2021, 40(17) :290-297.
[4] 陈保家, 陈学力, 沈保明, 等. CNN-LSTM深度神经网络在滚动轴承故障诊断中的应用[J]. 西安交通大学学报, 2021, 55(6): 28-36.
CHEN B J, CHEN X L, SHEN B M, et al.An application of convolution neural network and long short-term memory in rolling bearing fault diagnosis[J]. Journal of Xi’an Jiaotong University, 2021, 55(6): 28-36.
[5] 朱浩, 宁芊, 雷印杰, 等. 基于注意力机制-Inception-CNN模型的滚动轴承故障分类[J]. 振动与冲击, 2020, 39(19): 84-93.
ZHU H, NING Q, LEI Y J, et al.Fault classification of rolling bearing based on attention mechanism-Inception-CNN model[J]. Journal of vibration and shock, 2020, 39(19): 84-93.
[6] 赵敬娇, 赵志宏, 杨绍普. 基于残差连接和1D-CNN的滚动轴承故障诊断研究[J]. 振动与冲击, 2021, 40(10): 1-6.
ZHAO J J, ZHAO Z H, YANG S P.Rolling bearing fault diagnosis based on residual connection and 1D-CNN[J]. Journal of vibration and shock, 2021, 40(10): 1-6.
[7] 田科位, 董绍江, 姜保军, 等. 基于改进深度残差网络的轴承故障诊断方法[J]. 振动与冲击, 2021, 40(20): 247-254.
TIAN K W, DONG S J, JIANG B J, et al.A bearing fault diagnosis method based on an improved depth residual network[J]. Journal of vibration and shock, 2021, 40(20): 247-254.
[8] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA, 2016: 770-778.
[9] LI X, WANG W H, HU X L, et al.Selective kernel networks[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019: 510-519.
[10] CAO Y, XU J R, LIN S, et al.Gcnet: non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, Seoul, South Korea, 2019.
[11] WANG X L, GIRSHICK R, GUPTA A, et al.Non-local neural networks[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018: 7794-7803.
[12] HU J, SHEN L, SUN G.Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018: 7132-7141.
[13] 赵小强, 张亚洲. 利用改进卷积神经网络的滚动轴承变工况故障诊断方法[J]. 西安交通大学学报, 2021, 55(12): 108-118.
ZHAO X Q, ZHANG Y Z.Improved CNN-based fault diagnosis method for rolling bearings under variable working conditions[J]. Journal of Xi’an Jiaotong University, 2021, 55(12): 108-118.
[14] 谷晓娇, 陈长征. 基于VMD和QPSO-SR的风电机组轴承故障提取方法[J]. 太阳能学报, 2019, 40(10): 2946-2952.
GU X J, CHEN C Z.Fault extraction method of wind turbine bearing based on VMD and QPSO-SR[J]. Acta energiae solaris sinica, 2019, 40(10): 2946-2952.
[15] 余萍, 曹洁. 优化堆叠降噪自动编码器滚动轴承故障诊断[J]. 太阳能学报, 2021, 42(11): 307-314.
YU P, CAO J.Optimized stacked denoising auto-encoders(SDAE)-based fault diagnosis of rolling bearing[J]. Acta energiae solaris sinica, 2021, 42(11): 307-314.
[16] XU Z F, LI C, YANG Y.Fault diagnosis of rolling bearing of wind turbines based on the variational mode decomposition and deep convolutional neural networks[J]. Applied soft computing, 2020, 95: 106515.
[17] 王翔, 王金平, 许万军. 基于S-SLLE的风电机组齿轮箱故障诊断方法研究[J]. 太阳能学报, 2022, 43(3): 343-349.
WANG X, WANG J P, XU W J.Fault diagnosis method of wind turbine gearbox based on S-SLLE[J]. Acta energiae solaris sinica, 2022, 43(3): 343-349.
[18] LE C Y, BOTTOU L, BENGIO Y, et al.Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[19] ZHANG W, PENG G L, LI C H, et al.A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals[J]. Sensors, 2017, 17(2): 425.
[20] 许子非, 金江涛, 李春. 基于多尺度卷积神经网络的滚动轴承故障诊断方法[J]. 振动与冲击, 2021, 40(18): 212-220.
XU Z F, JIN J T, LI C.New method for the fault diagnosis of rolling bearings based on a multiscale convolutional neural network[J]. Journal of vibration and shock, 2021, 40(18): 212-220.