基于增强型卷积神经网络的风力发电机行星齿轮箱故障诊断方法

梁舒曼; 谷艳玲; 罗园庆; 陈长征

doi:10.19912/j.0254-0096.tynxb.2021-1109

PDF(1989 KB)

太阳能学报 ›› 2023, Vol. 44 ›› Issue (2) : 146-152. DOI: 10.19912/j.0254-0096.tynxb.2021-1109

基于增强型卷积神经网络的风力发电机行星齿轮箱故障诊断方法

梁舒曼¹, 谷艳玲^1,2, 罗园庆¹, 陈长征^1,2

作者信息 +

FAULT DIAGNOSIS METHOD OF WIND TURBINE PLANETARY GEARBOX BASED ON ENHANCED CONVOLUTIONAL EURAL NETWORK

Liang Shuman¹, Gu Yanling^1,2, Luo Yuanqing¹, Chen Changzheng^1,2

Author information +

文章历史 +

摘要

针对风力发电机行星齿轮箱的健康维护和状态检测难以诊断的问题,该文提出一种初始网与膨胀卷积相融合的初始膨胀卷积神经网络（IDCNN）的故障诊断研究方法。该方法首先构建初始膨胀卷积层以扩大感受野来使学习到的故障特征更加丰富。随后为了方便信号输入且确保信息丰富,将采用将一维原始信号序列转化为二维矩阵的预处理方法。最终将生成的二维信号输入到IDCNN中进行模型训练,并用测试数据对模型进行评估。实验结果表明,提出的IDCNN方法在风力发电机行星齿轮箱的故障诊断中精度高,在对比结果中该文提出方法的诊断精度要高于传统的深度学习方法。

Abstract

Aiming at the problem that the health maintenance and state detection of wind turbine planetary gearboxes are difficult to diagnose, a fault diagnosis research method of the initial dilated convolutional neural network （IDCNN） that combines the initial net and dilated convolution is proposed in this paper. This method first constructs an initial dilated convolutional layer to expand the receptive field to enrich the learned fault features. Subsequently, in order to facilitate signal input and ensure rich information, a preprocessing method of transforming the one-dimensional original signal sequence into a two-dimensional matrix will be adopted. Finally, the generated two-dimensional signal is input into IDCNN for model training, and the model is evaluated with test data. The experimental results show that the proposed IDCNN method has high accuracy in the fault diagnosis of the planetary gearbox of the wind turbine. In the comparison results, the diagnosis accuracy of the proposed method is higher than that of the traditional deep learning method.

导出引用

梁舒曼, 谷艳玲, 罗园庆, 陈长征. 基于增强型卷积神经网络的风力发电机行星齿轮箱故障诊断方法[J]. 太阳能学报. 2023, 44(2): 146-152 https://doi.org/10.19912/j.0254-0096.tynxb.2021-1109

Liang Shuman, Gu Yanling, Luo Yuanqing, Chen Changzheng. FAULT DIAGNOSIS METHOD OF WIND TURBINE PLANETARY GEARBOX BASED ON ENHANCED CONVOLUTIONAL EURAL NETWORK[J]. Acta Energiae Solaris Sinica. 2023, 44(2): 146-152 https://doi.org/10.19912/j.0254-0096.tynxb.2021-1109

中图分类号： TK83 TH133

参考文献

[1] BLAABJERG F, MA K.Future on power electronics for wind turbine systems[J]. IEEE journal of emerging & selected topics in power electronics, 2013, 1(3): 139-152.
[2] QIAO W, LU D G.A survey on wind turbine condition monitoring and fault diagnosis—part I: components and subsystems[J]. IEEE transactions on industrial electronics, 2015, 62(10): 6546-6557.
[3] 李宇恒, 蒋章雷, 梁好, 等. 基于HEI量化故障信息的行星齿轮箱故障诊断方法研究[J]. 机电工程, 2021, 38(7): 836-842.
LI Y H, JIANG Z L, LIANG H, et al.Research on fault diagnosis method of planetary gearbox based on HEI quantitative fault information[J]. Journal of mechanical & electrical engineering, 2021, 38(7): 836-842.
[4] 胡瑞杰, 庞学博, 佘彩青, 等. 基于最优窗函数Gabor变换的变工况行星齿轮箱故障诊断[J]. 风机技术, 2021, 63(2): 79-90.
HU R J, PANG X B, SHE C Q, et al.Fault diagnosis of planetary gearbox under variable conditions based on Gabor transformation of optimal window function[J]. Chinese journal of turbomachinery, 2021, 63(2): 79-90.
[5] WANG J J, GAO R X, YAN R Q.Integration of EEMD and ICA for wind turbine gearbox diagnosis[J]. Wind energy, 2014, 17(5): 757-773.
[6] 李东东, 刘宇航, 赵阳, 等. 基于改进生成对抗网络的风机行星齿轮箱故障诊断方法[J]. 中国电机工程学报, 2021, 41(21): 7496-7506.
LI D D, LIU Y H, ZHAO Y, et al.A fault diagnosis method for fan planetary gearbox based on improved generative countermeasure network[J]. Proceedings of the CSEE, 2021, 41(21): 7496-7506.
[7] 徐文博, 任亚峰, 韩冰. 一种基于深度学习理论的齿轮系统故障诊断方法[J]. 机械传动, 2020, 44(8): 78-83.
XU W B, REN Y F, HAN B.A fault diagnosis method for gear system based on deep learning theory[J]. Journal of mechanical transmission, 2020, 44(8): 78-83.
[8] 王庆荣, 杨磊, 王松松. 基于S变换和卷积神经网络的滚动轴承故障诊断[J]. 激光与光电子学进展, 2021, 58(22): 57-66.
WANG Q R, YANG L, WANG S S.Fault diagnosis of rolling bearing based on S-transform and convolutional neural network[J]. Laser & optoelectronics progress, 2021, 58(22): 57-66.
[9] 揭震国, 王细洋, 龚廷恺. 基于深度学习与子域适配的齿轮故障诊断[J]. 中国机械工程, 2021, 32(22): 2716-2723.
JIE Z G, WANG X Y, GONG T K.Gear fault diagnosis based on deep learning and subdomain adaptation[J]. China mechanical engineering, 2021, 32(22): 2716-2723.
[10] JING L Y, WANG T Y, ZHAO M, et al.An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox[J]. Sensors (Switzerland), 2017, 17(2): 414-428.
[11] HAN Y, TANG B P, DENG L.Multi-level wavelet packet fusion in dynamic ensemble convolutional neural network for fault diagnosis[J]. Measurement, 2018, 127: 246-255.
[12] ZHANG Y, XIN C.Motif difference field: a simple and effective image representation of time series for classification[J]. 2020, DOI: 10.48550/arXiv. 2001. 07582.
[13] WANG Z G, OATES T.Imaging time-series to improve classification and imputation[C]//Proceedings of the 24 th International Conference on Artificial Inteuigence, Buenos Aires, Argentina, 2015.
[14] WEN L, LI X Y, GAO L, et al.A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE transactions on industrial electronics, 2018, 68(7):5990-5998.
[15] 王昊, 肖慧灵, 王丽亚, 等. 一种基于改进迁移策略与膨胀卷积神经网络的轴承故障诊断方法[J]. 工业工程与管理, 2022, 27(1): 8.
WANG H, XIAO H L, WANG L Y, et al.A bearing fault diagnosis method based on improved migration strategy and expanded convolutional neural network[J]. Industrial engineering and management, 2022, 27(1): 8.
[16] 朱斌, 刘子龙. 基于新型初始模块的卷积神经网络图像分类方法[J]. 电子科技, 2021, 34(2): 52-56.
ZHU B, LIU Z L.Image classification method of convolutional neural network based on new initial module[J]. Electronic science and technology, 2021, 34(2): 52-56.
[17] 董迎朝, 王彬, 马洒洒, 等. 基于t-SNE的脑网络状态观测矩阵降维方法研究[J]. 计算机工程与应用, 2018, 54(1): 42-47.
DONG Y C, WANG B, MA S S, et al.Research on dimensionality reduction method of brain network state observation matrix based on t-SNE[J]. Computer engineering and applications, 2018, 54(1): 42-47.