Bearing surface defect detection based on improved convolutional neural network

Xian Fu; Xiao Yang; Ningning Zhang; RuoGu Zhang; Zhuzhu Zhang; Aoqun Jin; Ruiwen Ye; Huiling Zhang; Xian Fu; Xiao Yang; Ningning Zhang; RuoGu Zhang; Zhuzhu Zhang; Aoqun Jin; Ruiwen Ye; Huiling Zhang

doi:10.3934/mbe.2023549

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 7: 12341-12359. doi: 10.3934/mbe.2023549

Previous Article Next Article

Research article Special Issues

Bearing surface defect detection based on improved convolutional neural network

1.
Department of Computer and Information Engineering, Hubei Normal University, Huangshi 435000, China
2.
Huangshi Bangke Technology Co., Ltd., Huangshi 435000, China

Academic Editor: Danilo Pelusi

Received: 21 March 2023 Revised: 27 April 2023 Accepted: 04 May 2023 Published: 22 May 2023

This paper addresses the issue of artificial visual inspection being overly reliant on subjective experience and the difficulty for the human eye to accurately identify dense and non-significant defects. To solve this problem, we have implemented an automatic object detection algorithm based on an improved version of YOLOv5.First, we use the K-means++ clustering algorithm to automatically calculate the Anchor of the model to reduce the effect of the close location of the initial clustering centers on the clustering of the sample data.Second, we add the Coordinate Attention (CA) attention mechanism to the model to allow the model to better capture and understand important features in the images. Then, we add a new detection layer with a downsampling multiplier of 4 to the Neck network to improve the precision of the model. Finally, we use the lightweight network MobileNetV3 instead of YOLOv5's backbone network to reduce the model detection time overhead.Our model achieves 85.87% mAP, which is 6.44% better than the YOLOv5 network, and the detection time for a single image is only 54ms, which is 50% faster than the YOLOv5 network. After testing, we have proven that our proposed algorithm can quickly and accurately detect the condition of bearing appearance defects, improving detection efficiency and reducing costs.
- target detection,
- defect detection,
- attention mechanism,
- lightweight network
Citation: Xian Fu, Xiao Yang, Ningning Zhang, RuoGu Zhang, Zhuzhu Zhang, Aoqun Jin, Ruiwen Ye, Huiling Zhang. Bearing surface defect detection based on improved convolutional neural network[J]. Mathematical Biosciences and Engineering, 2023, 20(7): 12341-12359. doi: 10.3934/mbe.2023549

Related Papers:

Abstract

This paper addresses the issue of artificial visual inspection being overly reliant on subjective experience and the difficulty for the human eye to accurately identify dense and non-significant defects. To solve this problem, we have implemented an automatic object detection algorithm based on an improved version of YOLOv5.First, we use the K-means++ clustering algorithm to automatically calculate the Anchor of the model to reduce the effect of the close location of the initial clustering centers on the clustering of the sample data.Second, we add the Coordinate Attention (CA) attention mechanism to the model to allow the model to better capture and understand important features in the images. Then, we add a new detection layer with a downsampling multiplier of 4 to the Neck network to improve the precision of the model. Finally, we use the lightweight network MobileNetV3 instead of YOLOv5's backbone network to reduce the model detection time overhead.Our model achieves 85.87% mAP, which is 6.44% better than the YOLOv5 network, and the detection time for a single image is only 54ms, which is 50% faster than the YOLOv5 network. After testing, we have proven that our proposed algorithm can quickly and accurately detect the condition of bearing appearance defects, improving detection efficiency and reducing costs.

References

[1]	L. Eren, A. Karahoca, M. J. Devaney, Neural network based motor bearing fault detection, in Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No. 04CH37510), 3 (2004), 1657–1660. https://doi.org/10.1109/IMTC.2004.1351399
[2]	P. K. Kankar, S. C. Sharma, S. P. Harsha, Fault diagnosis of ball bearings using machine learning methods, Expert Syst. Appl., 38 (2011), 1876–1886. https://doi.org/10.1016/j.eswa.2010.07.119 doi: 10.1016/j.eswa.2010.07.119
[3]	C. Tastimur, M. Karakose, I. Aydın, E. Akin, Defect diagnosis of rolling element bearing using deep learning, in 2018 International Conference on Artificial Intelligence and Data Processing(IDAP), (2018), 1–5. https://doi.org/10.1109/IDAP.2018.8620743
[4]	J. S. Senanayaka, H. V. Khang, K. G. Robbersmyr, Multiple fault diagnosis of electric powertrains under variable speeds using convolutional neural networks, in 2018 XIII International Conference on Electrical Machines(ICEM), (2018), 1900–1905. https://doi.org/10.1109/ICELMACH.2018.8507096
[5]	C. Sobie, C. Freitas, M. Nicolai, Simulation-driven machine learning: Bearing fault classification, Mech. Syst. Signal Process., 99 (2018), 403–419. https://doi.org/10.1016/j.ymssp.2017.06.025 doi: 10.1016/j.ymssp.2017.06.025
[6]	M. Sadoughi, C. Hu, Physics-based convolutional neural network for fault diagnosis of rolling element bearings, IEEE Sens. J., 19 (2019), 4181–4192. https://doi.org/10.1109/JSEN.2019.2898634 doi: 10.1109/JSEN.2019.2898634
[7]	D. W. Kim, E. S. Lee, W. K. Jang, B. H. Kim, Y. H. Seo, Effect of data preprocessing methods and hyperparameters on accuracy of ball bearing fault detection based on deep learning, Adv. Mech. Eng., 14 (2022), 1900–1905. https://doi.org/10.1177/16878132221078494 doi: 10.1177/16878132221078494
[8]	A. Bapir, İ. Aydin, A comparative analysis of 1D convolutional neural networks for bearing fault diagnosis, in 2022 International Conference on Decision Aid Sciences and Applications (DASA), (2022), 1406–1411. https://doi.org/10.1109/DASA54658.2022.9765229
[9]	S. E. M. P. Kone, K. Yatsugi, Y. Mizuno, H. Nakamura, Application of convolutional neural network for fault diagnosis of bearing scratch of an induction motor, Appl. Sci., 12 (2022), 1406–1411. https://doi.org/10.3390/app12115513 doi: 10.3390/app12115513
[10]	M. Chen, L. Yu, C. Zhi, Improved faster R-CNN for fabric defect detection based on Gabor filter with genetic algorithm optimization, Comput. Ind., 134 (2022), 103551. https://doi.org/10.1016/j.compind.2021.103551 doi: 10.1016/j.compind.2021.103551
[11]	J. Luo, Z. Yang, S. Li, Y. Wu, FPCB surface defect detection: A decoupled two-stage object detection framework, IEEE Trans. Instrum. Meas., 70 (2021), 1–11. https://doi.org/10.1109/TIM.2021.3092510 doi: 10.1109/TIM.2021.3092510
[12]	X. Zhang, R. Ma, M. Li, Feature enhancement based on regular sparse model for planetary Gearbox fault diagnosis, IEEE Trans. Instrum. Meas., 71 (2022), 1–16. https://doi.org/10.1109/TIM.2022.3176244 doi: 10.1109/TIM.2022.3176244
[13]	J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You only look once: Unified, real-time object detection, in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), 779–788. https://doi.org/10.48550/arXiv.1506.02640
[14]	B. Bahmani, B. Moseley, A. Vattani, Scalable k-means++, preprint, arXiv: 1203.6402. https://doi.org/10.48550/arXiv.1203.6402
[15]	G. Yuan, J. Liu, H. Liu, Detection of cigarette appearance defects based on improved YOLOv4, Electron. Res. Arch., 31 (2023), 1344–1346. https://doi.org/10.3934/era.2023069 doi: 10.3934/era.2023069
[16]	Q. Hou, D. Zhou, J. Feng, Coordinate attention for efficient mobile network design, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 13708–13717. https://doi.org/10.48550/arXiv.2103.02907
[17]	A. Howard, M. Sandler, G. Chu, Searching for mobilenetv3, in Proceedings of the IEEE/CVF International Conference on Computer Vision, (2019), 1314–1324. https://doi.org/10.1109/ICCV.2019.00140
[18]	S. Ren, K. He, R. Girshick, Faster r-cnn: Towards real-time object detection with region proposal networks, Adv. Neural Inf. Process. Syst., 28 (2015). https://doi.org/10.48550/arXiv.1506.01497
[19]	W. Liu, D. Anguelov, D. Erhan, SSD: Single shot multiBox detector, in Computer Vision–ECCV 2016. ECCV 2016. Lecture Notes in Computer Science, (2016), 21–37. https://doi.org/10.1007/978-3-319-46448-0_2
[20]	T. Y. Lin, P. Goyal, R. Girshick, Focal loss for dense object detection, in Proceedings of the IEEE International Conference on Computer Vision, (2017), 2980–2988. https://doi.org/10.48550/arXiv.1708.02002
[21]	J. Redmon, A. Farhadi, Yolov3: An incremental improvement, preprint, arXiv: 1804.02767. https://doi.org/10.48550/arXiv.1804.02767
[22]	C. Li, L. Li, H. Jiang, YOLOv6: A single-stage object detection framework for industrial applications, preprint, arXiv: 2209.02976. https://doi.org/10.48550/arXiv.2209.02976
[23]	C. Y. Wang, A. Bochkovskiy, H. Y. M. Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, preprint, arXiv: 2207.02696. https://doi.org/10.48550/arXiv.2207.02696
[24]	J. Terven, D. Cordova-Esparza, A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond, preprint, arXiv: 2304.00501. https://doi.org/10.48550/arXiv.2304.00501

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)