宽转速范围下的航发主轴轴承故障诊断方法

张伟涛1,崔丹1,刘璐1,黄菊2

振动与冲击 ›› 2023, Vol. 42 ›› Issue (5) : 253-262.

PDF(2346 KB)
PDF(2346 KB)
振动与冲击 ›› 2023, Vol. 42 ›› Issue (5) : 253-262.
论文

宽转速范围下的航发主轴轴承故障诊断方法

  • 张伟涛1,崔丹1,刘璐1,黄菊2
作者信息 +

Fault diagnosis method of aero engine main shaft rolling bearings in wide rotating speed range

  • ZHANG Weitao1, CUI Dan1, LIU Lu1, HUANG Ju2
Author information +
文章历史 +

摘要

针对航空发动机主轴转速范围大而导致现有卷积神经网络故障诊断性能急剧下降的问题,论文提出了一种基于小波包重构成像与深浅层特征融合分类网络的故障诊断方法。首先,利用小波包分解提取滚动轴承振动信号中的有效成分,消除与故障特征无关的干扰分量。然后采用短时傅里叶变换对重构后的振动信号进行成像,得到时频谱样本。最后针对转速时变下的轴承故障分类问题,通过跳跃连接方式建立具有深浅层特征融合特性的卷积神经网络,实现故障分类预测。利用航发轴承试验机采集得到的多路轴承振动信号对提出的方法进行有效性验证,结果表明,在训练集和测试集样本具有不同转速的情况下,使用提出方法对不同类型故障仍具有很高的识别精度。

Abstract

Aiming at the problem that the fault diagnosis performance of existing convolutional neural network(CNN)declines sharply due to the wide range of aero-engine rotate speed, fault diagnosis method based on wavelet packet reconstruction imaging and deep and shallow feature fusion classification network is proposed. Firstly, wavelet packet transform(WPT)is used to extract the effective components from the vibration signal and eliminate the interference components. Then, the reconstructed vibration signal is imaging by short-time Fourier transform(STFT), and the time-frequency spectrum samples are obtained. Finally, the problem of fault classification under time-varying rotating speed, the proposed network is established by jump connection to complete fault classification. The effectiveness of the proposed method is verified by the multi-channel vibration signals collected by bearing test machine, the results show that the proposed method still has higher recognition accuracy when the training set and test set samples have different speeds.

关键词

滚动轴承 / 故障诊断 / 小波包分解 / 卷积神经网络

Key words

rolling bearing / fault diagnosis / wavelet packet transform / convolution neural network

引用本文

导出引用
张伟涛1,崔丹1,刘璐1,黄菊2. 宽转速范围下的航发主轴轴承故障诊断方法[J]. 振动与冲击, 2023, 42(5): 253-262
ZHANG Weitao1, CUI Dan1, LIU Lu1, HUANG Ju2. Fault diagnosis method of aero engine main shaft rolling bearings in wide rotating speed range[J]. Journal of Vibration and Shock, 2023, 42(5): 253-262

参考文献

[1] LI B, CHOW M Y, TIPSUWAN Y, et al. Nerual-network-based motor rolling bearing fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2000, 47(5): 1060-1069.
 [2] MURUGANATHAM B, SANJITH M A, KRISHNAKUMAR B, et al. Roller element bearing fault diagnosis using singular spectrum analysis[J]. Mechanical Systems and Signal Processing, 2013, 35(1): 150-166.
 [3] 张俊鹏, 杨志勃, 陈雪峰, 等. 卷积神经网络在轴承故障诊断中的可解释性探讨[J]. 轴承, 2020, (7): 54-60.
     ZHANG Junpeng, YANG Zhibo, CHEN Xuefeng, et al. Interpretability discussion on convolutional neural network bearing fault diagnosis[J]. Bearing, 2020, (7): 54-60.
 [4] 陈是扦, 彭志科, 周鹏. 信号分解及其在机械故障诊断中的应用研究综述[J]. 机械工程学报, 2020, 56(17): 91-107.
     CHEN Shiqian, PENG Zhike, ZHOU Peng. Review of signal decomposition theory and its applications in machine fault diagnosis[J]. Journal of Mechanical Engineering, 2020, 56(17): 97-107.
 [5]  ZHANG W, LI C H, PENG G L, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018, 100(1): 439-453.
 [6] 董绍江, 裴雪武, 吴文亮, 等. 基于多层降噪技术及改进卷积神经网络的滚动轴承故障诊断方法[J]. 机械工程学报, 2021, 57(1): 148-156.
     DONG Shaojiang, PEI Xuewu, WU Wenliang, et al. Rolling bearing fault diagnosis method based on multilayer noise reduction technology and improved convolutional neural network[J]. Journal of Mechanical Engineering, 2021, 57(1): 148-156.
 [7] LU C, WANG Z, ZHOU B. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification[J]. Advanced Engineering Informatics, 2017, 32(1): 139-151.
 [8] 贺思艳, 任利娟, 田新诚. 基于卷积神经网络的滚动轴承故障诊断[J]. 兵工自动化, 2019, 38(3): 39-41.
 HE Siyan, REN Lijuan, TIAN Xincheng. Rolling bearing fault diagnosis based on convolutional neural network[J]. Ordnance Industry Automation, 2019, 38(3): 39-41.
 [9] 刘炳集, 熊邦书, 欧巧凤, 等. 基于时频图和CNN的滚动轴承故障诊断[J]. 南昌航空大学学报:自然科学版, 2018, 32(2): 87-91.
     LIU Bingji, XIONG Bangshu, QU Qiaofeng, et al. Fault diagnosis of rolling bearing based on time-frequency representations and CNN[J]. Journal of Nanchang Hangkong University: Natural Sicences, 2018, 32(2): 87-91.
[10] MA P, ZHANG H L, FAN W H, et al. A novel bearing fault diagnosis method based on 2D image representation and transfer learning-convolutional neural network[J]. Measurement Science and Technology, 2019, 30: 055402.
[11] 肖雄, 王健翔, 张勇军, 等. 一种用于轴承故障诊断的二维卷积神经网络优化方法[J]. 中国电机工程学报, 2019, 39(15): 4558-4567.
     XIAO Xiong, WANG Jianxiang, ZHANG Yongjun, et al. A tow-dimensional convolutional neural network optimization method for bearing fault diagnosis[J]. Processing of the CSEE, 2019, 39(15): 4558-4567.
[12] 黄鑫, 陈仁祥, 杨星, 等. 基于深度卷积神经网络与WPT-PWVD的轴承故障智能诊断[J]. 振动与冲击, 2020, 39(16): 236-243.
     HUANG Xin, CHEN Renxiang, YANG Xing, et al. A bearing fault intelligent diagnosis method based on deep convolution neural network and WPT-PWVD[J]. Journal of Vibration and Shock, 2020, 39(16): 236-243.
[13] ZhANG Y, XING K S, BAI R X, et al. An enhanced convolutional neural network for bearing diagnosis based on time-frequency image[J]. Measurement, 2020, 157: 107667.
[14] 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 Jingjiao, ZHAO Zhihong, YANG Shaopu. Rolling bearing fault diagnosis based on residual connection and 1D-CNN[J]. Journal of Vibration and Shock, 2021, 40(10): 1-6.
[15] 熊剑, 邓松, 时大方. 基于改进残差网络的滚动轴承故障诊断[J]. 轴承, 2020, (11): 50-55.
     XIONG Jian, DENG Song, SHI Dafang. Fault diagnosis for rolling bearings based on improved residual network[J]. Bearing, 2020, (11): 50-55.
[16] 刘建伟, 赵慧丹, 罗雄麟, 等. 深度学习批归一化及其相关算法研究进展[J]. 自动化学报, 2020, 46(6): 1090-1120.
 LIU Jinwei, ZHAO Huidan, LOU XiongLin, et al. Research progress on batch normalization of deep learning and its related algorithms[J]. Acta Automatica Sinica, 2020, 46(6): 1090-1120.
[17] 李恒, 张氢, 秦仙蓉, 等. 基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]. 振动与冲击, 2018, 37(19): 124-131.
     LI Heng, ZHANG Qin, QIN Xianrong, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration and Shock, 2018, 37(19): 124-131.
[18] 邢蓉, 高丙朋, 侯培浩, 等. 基于MSCNN与STFT的滚动轴承故障诊断研究[J]. 机械传动, 2020, 44(7): 41-45.
 XING Rong, Gao Bingpeng, Hou Peihao, et al. Research of fault diagnosis of rolling bearing based on MSCNN and STFT[J]. Journal of Mechanical Transmission, 2020, 44(7): 41-45.
[19] 熊鹏, 汤宝平, 邓蕾, 等. 基于动态加权密集连接网络的变转速行星齿轮故障诊断[J]. 机械工程学报, 2019, 55(7): 52-57.
     XIONG Peng, TANG Baoping, DENG Lei, et al. Fault diagnosis for planetary gearbox by dynamically weighted densely connected convolutional networks[J]. Journal of Mechanical Engineering, 2019, 55(7): 52-57.

PDF(2346 KB)

Accesses

Citation

Detail

段落导航
相关文章

/