| Citation: | DUAN Xiaoyan, JIAO Mengxuan, LEI Chunli, et al. A rolling bearing fault diagnosis method based on MTF-MSMCNN with small sample[J]. Journal of Aerospace Power, 2024, 39（1）：20230517 doi: 10.13224/j.cnki.jasp.20230517
|
Considering the problem of low fault identification accuracy caused by insufficient sample size and complex working conditions, a fault diagnosis method of rolling bearing with small sample based on Markov transition field and multidimensional supervised module convolutional neural network (MTF-MSMCNN) was proposed. The one-dimensional rolling bearing signal was transformed into two-dimensional feature image using MTF coding method to preserve temporal correlation. Multidimensional supervision module (MSM) was presented to monitor important fault features in both spatial and channel dimension and assign weight adaptively, which can improve the model’s ability to capture key features. MSM was embedded into the convolutional neural network to build a MSMCNN model. The complex working conditions were constructed through experiments, and the MTF images were input into the MTF-MSMCNN network model for fault diagnosis. Two data sets were used to verify the model validity. The experimental results showed that the MTF-MSMCNN had only 10 samples in each type of fault training set, and its fault diagnosis accuracy can still reach about 90% under 0 dB noise pollution. Compared with other diagnostic models, the method proposed had higher recognition accuracy, stronger generalization ability and anti-noise performance under the conditions of small samples, variable working conditions and noise interference.
| [1] |
任磊,贾子翟,赖李媛君,等. 数据驱动的工业智能: 现状与展望[J]. 计算机集成制造系统,2022,28(7): 1913-1939.
REN Lei,JIA Zidi,LAI Liyuanjun,et al. Data-driven industrial intelligence: current status and future directions[J]. Computer Integrated Manufacturing Systems,2022,28(7): 1913-1939. (in Chinese)
|
| [2] |
RAI A,UPADHYAY S H. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings[J]. Tribology International,2016,96: 289-306. doi: 10.1016/j.triboint.2015.12.037
|
| [3] |
HINTON G E,SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786): 504-507. doi: 10.1126/science.1127647
|
| [4] |
GU Xiaojiao,XIE Yuntao,TIAN Yang,et al. A lightweight neural network based on GAF and ECA for bearing fault diagnosis[J]. Metals,2023,13(4): 822. doi: 10.3390/met13040822
|
| [5] |
GUO Yurong,MAO Jian,ZHAO Man. Rolling bearing fault diagnosis method based on attention CNN and BiLSTM network[J]. Neural Processing Letters,2023,55(3): 3377-3410. doi: 10.1007/s11063-022-11013-2
|
| [6] |
JIANG Li,WU Lin,TIAN Yu,et al. An ensemble fault diagnosis method for rotating machinery based on wavelet packet transform and convolutional neural networks[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science,2022,236(24): 11600-11612. doi: 10.1177/09544062221102721
|
| [7] |
ZHANG Kai,TANG Baoping,QIN Yi,et al. Fault diagnosis of planetary gearbox using a novel semi-supervised method of multiple association layers networks[J]. Mechanical Systems and Signal Processing,2019,131: 243-260. doi: 10.1016/j.ymssp.2019.05.049
|
| [8] |
沈长青,汤盛浩,江星星,等. 独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究[J]. 机械工程学报,2019,55(7): 81-88. doi: 10.3901/JME.2019.07.081
SHEN Changqing,TANG Shenghao,JIANG Xingxing,et al. Bearings fault diagnosis based on improved deep belief network by self-individual adaptive learning rate[J]. Journal of Mechanical Engineering,2019,55(7): 81-88. (in Chinese) doi: 10.3901/JME.2019.07.081
|
| [9] |
韩淞宇,邵海东,姜洪开,等. 基于提升卷积神经网络的航空发动机高速轴承智能故障诊断[J]. 航空学报,2022,43(9): 625479.
HAN Songyu,SHAO Haidong,JIANG Hongkai,et al. Intelligent fault diagnosis of aero-engine high-speed bearings using enhanced CNN[J]. Acta Aeronautica et Astronautica Sinica,2022,43(9): 625479. (in Chinese)
|
| [10] |
高浩寒,潮群,徐孜,等. 小样本下基于孪生神经网络的柱塞泵故障诊断[J]. 北京航空航天大学学报,2023,49(1): 155-164.
GAO Haohan,CHAO Qun,XU Zi,et al. Piston pump fault diagnosis based on Siamese neural network with small samples[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,49(1): 155-164. (in Chinese)
|
| [11] |
孙洁娣,刘保,温江涛,等. 类别标签辅助改进稠密网络的变工况轴承故障诊断[J]. 振动与冲击,2022,41(17): 204-212.
SUN Jiedi,LIU Bao,WEN Jiangtao,et al. Fault diagnosis of variable condition bearing based on improved dense network aided by class labels[J]. Journal of Vibration and Shock,2022,41(17): 204-212. (in Chinese)
|
| [12] |
WANG Zhiguang, OATES T. Encoding time series as images for visual inspection and classification using tiled convolutional neural networks[R]. Menlo Park, US: 29th AAAI Conference on Artificial Intelligence, 2014.
|
| [13] |
LECUN Y,BOSER B,DENKER J S,et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation,1989,1(4): 541-551. doi: 10.1162/neco.1989.1.4.541
|
| [14] |
常春,梅检民,赵慧敏,等. 基于CUM3-CNN的柴油机高压油路故障诊断[J]. 振动与冲击,2023,42(3): 174-180.
CHANG Chun,MEI Jianmin,ZHAO Huimin,et al. Fault diagnosis of diesel engine high pressure oil circuit based on CUM3-CNN[J]. Journal of Vibration and Shock,2023,42(3): 174-180. (in Chinese)
|
| [15] |
赵小强, 张亚洲. 改进CNN的滚动轴承变工况故障诊断[J/OL]. 西安交通大学学报, 2021: 1-11. (2021-08-10). https://kns.cnki.net/kcms/detail/61.1069.T.20210810.1435.007.html
ZHAO Xiaoqiang, ZHANG Yazhou. Improved CNN fault diagnosis method of rolling bearings under variable working conditions[J/OL]. Journal of Xi’an Jiaotong University, 2021: 1-11. (2021-08-10). https://kns.cnki.net/kcms/detail/61.1069.T.20210810.1435.007.html. (in Chinese)
|
| [16] |
冯李航,陈铭,章伟. 基于增强卷积神经网络的电子鼻长期漂移抑制方法[J]. 仪器仪表学报,2021,42(2): 207-217. doi: 10.19650/j.cnki.cjsi.J2006982
FENG Lihang,CHEN Ming,ZHANG Wei. Long-term drift suppression method for electronic nose based on the augmented convolutional neural network[J]. Chinese Journal of Scientific Instrument,2021,42(2): 207-217. (in Chinese) doi: 10.19650/j.cnki.cjsi.J2006982
|
| [17] |
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. doi: 10.13465/j.cnki.jvs.2020.19.013
ZHU Hao,NING Qian,LEI Yinjie,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. (in Chinese) doi: 10.13465/j.cnki.jvs.2020.19.013
|
| [18] |
SMITH W A,RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study[J]. Mechanical Systems and Signal Processing,2015,64: 100-131.
|
| [19] |
ZHANG Lei,LÜ Yong,HUANG Wenyi,et al. Bearing fault diagnosis under various operation conditions using synchrosqueezing transform and improved two-dimensional convolutional neural network[J]. Measurement Science and Technology,2022,33(8): 085002. doi: 10.1088/1361-6501/ac69b1
|
| [20] |
MANJURUL ISLAM M M,KIM J M. Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural network[J]. Computers in Industry,2019,106: 142-153. doi: 10.1016/j.compind.2019.01.008
|
DownLoad:
