A variable-speed-condition bearing fault diagnosis methodology with recurrence plot coding and MobileNet-v3 model

被引:11
作者
Gu, Yingkui [1 ]
Chen, Ronghua [1 ]
Wu, Kuan [1 ]
Huang, Peng [1 ]
Qiu, Guangqi [1 ]
机构
[1] Jiangxi Univ Sci & Technol, Sch Mech & Elect Engn, Ganzhou 341000, Jiangxi, Peoples R China
基金
中国国家自然科学基金;
关键词
IDENTIFICATION; DECOMPOSITION; SIGNAL;
D O I
10.1063/5.0125548
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
To improve the quality of the non-stationary vibration features and the performance of the variable-speed-condition fault diagnosis, this paper proposed a bearing fault diagnosis approach with Recurrence Plot (RP) coding and a MobileNet-v3 model. 3500 RP images with seven fault modes were obtained with angular domain resampling technology and RP coding and were input into the MobileNet-v3 model for bearing fault diagnosis. Additionally, we performed a bearing vibration experiment to verify the effectiveness of the proposed method. The results show that the RP image coding method with 99.99% test accuracy is superior to the other three image coding methods such as Gramian Angular Difference Fields, Gramian Angular Summation Fields, and Markov Transition Fields with 96.88%, 90.20%, and 72.51%, indicating that the RP image coding method is more suitable for characterizing variable-speed fault features. Compared with four diagnosis methods such as MobileNet-v3 (small), MobileNet-v3 (large), ResNet-18, and DenseNet121, and two state-of-the-art approaches such as Symmetrized Dot Pattern and Deep Convolutional Neural Networks, RP and Convolutional Neural Networks, it is found that the proposed RP+MobileNet-v3 model has the best performance in all aspects with diagnosis accuracy, parameter numbers, and Graphics Processing Unit usage, overcoming the over-fitting phenomenon and increasing the anti-noise performance. It is concluded that the proposed RP+MobileNet-v3 model has a higher diagnostic accuracy with fewer parameters and is a lighter model.
引用
收藏
页数:14
相关论文
共 43 条
[21]   Application of order cyclostationary demodulation to damage detection in a direct-driven wind turbine bearing [J].
Liu, Xiaofeng ;
Bo, Lin ;
Peng, Chang .
MEASUREMENT SCIENCE AND TECHNOLOGY, 2014, 25 (02)
[22]   A Novel Contactless Angular Resampling Method for Motor Bearing Fault Diagnosis Under Variable Speed [J].
Lu, Siliang ;
Guo, Jie ;
He, Qingbo ;
Liu, Fang ;
Liu, Yongbin ;
Zhao, Jiwen .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2016, 65 (11) :2538-2550
[23]   Matching Synchroextracting Transform for Mechanical Fault Diagnosis Under Variable-Speed Conditions [J].
Ma, Yubo ;
Lv, Yong ;
Yuan, Rui ;
Song, Gangbing .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
[24]  
Mukhopadhyay S., P 10 INT C INT THING, V4, P1
[25]   Improved Structural Rotor Fault Diagnosis Using Multi-Sensor Fuzzy Recurrence Plots and Classifier Fusion [J].
Nath, Aneesh G. ;
Udmale, Sandeep S. ;
Raghuwanshi, Divyanshu ;
Singh, Sanjay Kumar .
IEEE SENSORS JOURNAL, 2021, 21 (19) :21705-21717
[26]   Symplectic geometry mode decomposition and its application to rotating machinery compound fault diagnosis [J].
Pan, Haiyang ;
Yang, Yu ;
Li, Xin ;
Zheng, Jinde ;
Cheng, Junsheng .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2019, 114 :189-211
[27]   Modeling the SOFC by BP neural network algorithm [J].
Song, Shaohui ;
Xiong, Xingyu ;
Wu, Xin ;
Xue, Zhenzhong .
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2021, 46 (38) :20065-20077
[28]   A fault diagnosis method using Interval coded deep belief network [J].
Tang, Jiahui ;
Wu, Jimei ;
Hu, Bingbing ;
Guo, Chang ;
Zhang, Jialing .
JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2020, 34 (05) :1949-1956
[29]   Transient feature identification from internal encoder signal for fault detection of planetary gearboxes under variable speed conditions [J].
Wang, Baoxiang ;
Ding, Chuancang .
MEASUREMENT, 2021, 171
[30]  
Wang C., 2021, 2021 7 INT C COND MO