Fault diagnosis method for rolling bearings under small samples and variable working conditions based on MTF and SSCAM-MSCNN

被引：0

作者：

Lei, Chunli ^{[1
,2
]}

Jiao, Mengxuan ^{[1
,2
]}

Xue, Linlin ^{[1
,2
]}

Zhang, Huqiang ^{[1
,2
]}

Shi, Jiashuo ^{[1
,2
]}

机构：

[1] School of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou

[2] Key Laboratory of Digital Manufacturing and Application, Ministry of Education, Lanzhou University of Technology, Lanzhou

来源：

Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2025年 / 31卷 / 01期

基金：

中国国家自然科学基金;

关键词：

convolutional neural network; fault diagnosis; Markov transition field; rolling bearing; small sample; stripe self-calibrating attention mechanism;

D O I：

10.13196/j.cims.2022.0500

中图分类号：

学科分类号：

摘要：

To solve the problems of low diagnosis accuracy and poor generalization Performance caused by different sample distribution and insufficient samples, a fault diagnosis method for rolling bearings under small samples and variable working conditions based on MTF and SSCAM-MSCNN was proposed. The Markov Transition Field (MTF) was used to transform one-dimensional Vibration signal into two-dimensional feature map with time-depend-ent. A novel Stripe Self-calibrating Attention Mechanism (SSCAM) was put forward, which could not only enhance feature extraction ability in long-distance direction, but also establish inter-channel dependence and capture global ef-fective Information. Then, SSCAM was introduced into Multi-Scale Convolutional Neural Network (MSCNN) to construct SSCAM-MSCNN model. Finally, the MTF two-dimensional feature map was input into the proposed model for training, and the optimized network model was used to test and Output the Classification results. The proposed method was validated by both Case Western Reserve University data set and MFS rolling bearing data set of our laboratory. Meanwhile, the MFS data was noised up and compared with other fault diagnosis models. The ex-perimental results showed that the proposed method had higher recognition accuracy, stronger generalization Performance and anti-noise Performance under small samples and variable operating conditions. © 2025 CIMS. All rights reserved.

引用

页码：278 / 289

页数：11

共 27 条

[1]

SYED LKHADKIKAR, ZEINELDIN H H., Löss reduction in radial distribution networks using a solid-state transformer _J], IEEE Transactions on Industry Applications, 54, 5, pp. 5474-5482, (2018)

[2]

WANG H Q, KE Y L., LUO G G, Et al., Compressed sensing of roller bearing fault based on multiple down-sampling strategy _J], Measurement Science and Technology, 27, 2, (2015)

[3]

JIANG H K, XIA Y, WANG X D., Rolling bearing fault detec-tion using an adaptive lifting multiwavelet packet with a di-mension spectrum[J], Measurement Science and Technology, 24, 12, (2013)

[4]

ZHAO Xlaoqiang, ZHANG Yazhou, Improved CNN-based fault dl-agnosis method for rolling bearings under variable working condi-tions, Journal of Xi'an Jiaotong University, 55, 12, pp. 108-118, (2021)

[5]

YUAN Calyan, SUN Jledl, WEN Jlangtao, Et al., Bearing fault diagnosis based on Information fusion and improved residual dense networks[J], Journal of Vibration and Shock, 9, 4, pp. 200-208, (2022)

[6]

JEGADEESHWRRAN R, SUGUMARAN V., Fault diagnosis of automobile hydraulic brake System using Statistical features and Support vector machines[J], Mechanical Systems and Signal Processing, 52, pp. 436-446, (2015)

[7]

GU Y K, YU D P., Et al., Fault diagnosis method of rolling bearing using principal component analysis and Support vector machine[j], Journal of Mechanical Science and Technology, 32, 11, pp. 5079-5088, (2018)

[8]

HINTON G E, SALAKHUD1NOV R R., Reducmg the dimen-sionality of data with neural networks[J], Science, 313, 5786, pp. 504-507, (2006)

[9]

XU Yanwei, CAI Weiwei, XIE Tancheng, Et al., Intelligent fault diagnosis of metro traction motor bearing based on convolution neural network and information fusion[Jj, Computer Integrat-ed Manufacturing Systems, 27, 11, pp. 3247-3258, (2021)

[10]

ZHANG Xming, L1U Shuyu, YU Dl, Et al., Improved deep convolutional neural network with applications to bearing fault diagnosis under variable conditions, Journal of Xi'an Jiaotong University, 55, 6, pp. 1-8, (2021)

← 1 2 3 →