Gear Pitting Measurement by Multi-Scale Splicing Attention U-Net

Yi Qin; Dejun Xi; Weiwei Chen; Yi Wang

doi:10.1186/s10033-023-00874-w

摘要

The judgment of gear failure is based on the pitting area ratio of gear. Traditional gear pitting calculation method mainly rely on manual visual inspection. This method is greatly affected by human factors, and is greatly affected by the working experience, training degree and fatigue degree of the detection personnel, so the detection results may be biased. The non-contact computer vision measurement can carry out non-destructive testing and monitoring under the working condition of the machine, and has high detection accuracy. To improve the measurement accuracy of gear pitting, a novel multi-scale splicing attention U-Net (MSSA U-Net) is explored in this study. An image splicing module is first proposed for concatenating the output feature maps of multiple convolutional layers into a splicing feature map with more semantic information. Then, an attention module is applied to select the key features of the splicing feature map. Given that MSSA U-Net adequately uses multi-scale semantic features, it has better segmentation performance on irregular small objects than U-Net and attention U-Net. On the basis of the designed visual detection platform and MSSA U-Net, a methodology for measuring the area ratio of gear pitting is proposed. With three datasets, experimental results show that MSSA U-Net is superior to existing typical image segmentation methods and can accurately segment different levels of pitting due to its strong segmentation ability. Therefore, the proposed methodology can be effectively applied in measuring the pitting area ratio and determining the level of gear pitting.

关键词： Gear pitting; Image segmentation; Attention module; Computer vision; Quantitative detection

本文引用格式

Yi Qin , Dejun Xi , Weiwei Chen , Yi Wang . Gear Pitting Measurement by Multi-Scale Splicing Attention U-Net[J]. Chinese Journal of Mechanical Engineering, 2023 , 36(2) : 50 -50 . DOI: 10.1186/s10033-023-00874-w

Abstract

The judgment of gear failure is based on the pitting area ratio of gear. Traditional gear pitting calculation method mainly rely on manual visual inspection. This method is greatly affected by human factors, and is greatly affected by the working experience, training degree and fatigue degree of the detection personnel, so the detection results may be biased. The non-contact computer vision measurement can carry out non-destructive testing and monitoring under the working condition of the machine, and has high detection accuracy. To improve the measurement accuracy of gear pitting, a novel multi-scale splicing attention U-Net (MSSA U-Net) is explored in this study. An image splicing module is first proposed for concatenating the output feature maps of multiple convolutional layers into a splicing feature map with more semantic information. Then, an attention module is applied to select the key features of the splicing feature map. Given that MSSA U-Net adequately uses multi-scale semantic features, it has better segmentation performance on irregular small objects than U-Net and attention U-Net. On the basis of the designed visual detection platform and MSSA U-Net, a methodology for measuring the area ratio of gear pitting is proposed. With three datasets, experimental results show that MSSA U-Net is superior to existing typical image segmentation methods and can accurately segment different levels of pitting due to its strong segmentation ability. Therefore, the proposed methodology can be effectively applied in measuring the pitting area ratio and determining the level of gear pitting.

Key words： Gear pitting; Image segmentation; Attention module; Computer vision; Quantitative detection

参考文献

[1] M Amarnath, S Lee. Assessment of surface contact fatigue failure in a spur geared system based on the tribological and vibration parameter analysis. Measurement, 2015, 76: 32-44.
[2] Y Qin, S Xiang, Y Chai, et al. Macroscopic-microscopic attention in LSTM networks based on fusion features for gear remaining life prediction. IEEE Transactions on Industrial Electronics, 2020, 67(12): 10865-10875.
[3] F Shen, C Chen, J Xu, et al. A fast multi-tasking solution: NMF-theoretic co-clustering for gear fault diagnosis under variable working conditions. Chinese Journal of Mechanical Engineering, 2020, 33(1). https://doi.org/10.1186/s10033-020-00437-3
[4] R Chen, X Huang, L Yang, et al. Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform. Computers in Industry, 2019, 106: 48-59.
[5] Y Qin, Y Mao, B Tang, et al. M-band flexible wavelet transform and its application to the fault diagnosis of planetary gear transmission systems. Mechanical Systems and Signal Processing, 2019, 134: 106298.
[6] S Xiang, Y Qin, C Zhu, et al. Long short-term memory neural network with weight amplification and its application into gear remaining useful life prediction. Engineering Applications of Artificial Intelligence, 2020, 91: 103587.
[7] X Wang, Y Qin, A Zhang. An intelligent fault diagnosis approach for planetary gearboxes based on deep belief networks and uniformed features. Journal of Intelligent & Fuzzy Systems, 2018, 34: 3619-3634.
[8] Z Pu, D Cabrera, Y Bai, et al. A one-class generative adversarial detection framework for multifunctional fault diagnoses. IEEE Transactions on Industrial Electronics, 2021, 69(8): 1-11.
[9] D Xi, Y Qin, S Wang. YDRSNet: an integrated Yolov5- Deeplabv3+ real-time segmentation network for gear pitting measurement. Journal of Intelligent Manufacturing, 2021: 1-15.
[10] Y Qin, Z Wang, and D Xi. Tree CycleGAN with maximum di-versity loss for image augmentation and its application into gear pitting detection. Applied Soft Computing, 2022, 114: 108130.
[11] T Niu, B Li, W Li, et al. Positive-sample-based surface defect detection using memory-augmented adversarial autoencoders. IEEE/ASME Transactions on Mechatronics, 2022, 27(1): 46-57.
[12] J Wang, K Song, D Zhang, et al. Collaborative learning attention network based on RGB image and depth image for surface defect inspection of no-service rail. IEEE/ASME Transactions on Mechatronics, 2022.
[13] W Zhang, X Wang, W You, et al. RESLS: region and edge synergetic level set framework for image segmentation. IEEE Transactions Image Process, 2020, 29: 57-71.
[14] L Wang, L Xu, J Yu, et al. Context-aware edge similarity segmentation algorithm of time series. Cluster Computing, 2016, 19: 1421-1436.
[15] Z Zhu, P Luo, X Wang, et al. Deep learning identity-preserving face space. IEEE International Conference on Computer Vision, Sydney, Australia, December 3-6, 2013: 113-120.
[16] Y Sun, X Wang, X Tang. Deep learning face representation from predicting 10, 000 classes. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, June 23-28, 2014: 1891-1898.
[17] Z Jin, J Yang, Z Hu, et al. Face recognition based on the uncorrelated discriminant transformation. Pattern Recognition, 2001, 34: 1405-1416.
[18] A Krizhevsky, I Sutskever, G Hinton. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60: 84-90.
[19] E Shelhamer, J Long, T Darrell. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39: 640-651.
[20] O Ronneberger, P Fischer, T Brox. U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention, 2015, 9351: 234-241.
[21] V Badrinarayanan, A Kendall, R Cipolla. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39: 2481-2495.
[22] L Chen, G Papandreou, I Kokkinos, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40: 834-848.
[23] O Oktay, J Schlemper, L Folgoc, et al. Attention U-Net: Learning where to look for the pancreas. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, June 19-21, 2018: 1804.03999.
[24] S Song, C Lan, J Xing, et al. An end-to-end spatio-temporal attention model for human action recognition from skeleton data. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, California USA, February 4-9, 2017, 31(1).
[25] G Hassan, A Hassanien, N Elbendary, et al. Blood vessel segmentation approach for extracting the vasculature on retinal fundus images using particle swarm optimization. International Computer Engineering Conference, Giza, Egypt, December 29-30, 2015: 290-296.
[26] C Deng, M Wang, L Liu, et al. Extended feature pyramid network for small object detection. IEEE Transactions on Multimedia, 2022, 24: 1968-1979.
[27] D Xi, Y Qin, Y Wang. Vision measurement of gear pitting under different scenes by deep mask R-CNN. Sensors, 2020, 20(15): 4298.
[28] C Goutte, E Gaussier. A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. Advances in Information Retrieval, 2005, 3408: 345-359.
[29] F Ahmed, D Tarlow, D Batra. Optimizing expected intersection-over-union with candidate-constrained CRFs. IEEE International Conference on Computer Vision, Santiago, Chile, USA, December 7-13, 2015: 1850-1858.
[30] L Hamers, Y Hemeryck, G Herweyers, et al. Similarity measures in scientometric research - the jaccard index versus salton cosine formula. Information Processing & Management, 1989, 25: 315-318.
[31] Y Shi, L Cui, Z Qi, et al. Automatic road crack detection using random structured forests. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(12): 3434-3445.
[32] M Everingham, S M A Eslami, L Van Gool, et al. The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 2015, 111: 98-136.

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献