Abstract
The intelligent recognition of wear debris in ferrography images is a great challenge. Aiming at the detection characteristics of multi-scale objects, small objects and overlapping objects in ferrography images, a real-time on-line object detection model combining feature fusion, self-attention mechanism and improved NMS is proposed. Based on YOLOv3, a fully convolutional network based on feature fusion is constructed, and a residual unit with self-attention mechanism and an object selection mechanism based on improved non-maximum suppression are introduced. The performance of the model is compared with three advanced object detection algorithms on a great number of ferrography images. The experimental results show that the model has high detection accuracy, short detection time and strong adaptability. The proposed model can be further developed and applied to fault diagnosis and condition monitoring of machinery and equipment in future.
Similar content being viewed by others
References
Jardine AK, Lin D, Banjevic D (2006) A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process 20(7):1483–1510
Stachowiak GP, Stachowiak GW, Podsiadlo P (2008) Automated classification of wear particles based on their surface texture and shape features. Tribol Int 41(1):34–43
Kumar M, Mukherjee PS, Misra NM (2013) Advancement and current status of wear debris analysis for machine condition monitoring: a review. Ind Lubricat Tribol 65(1):3–11
Raadnui S (2005) Wear particle analysis—utilization of quantitative computer image analysis: a review. Tribol Int 38(10):871–878
Li W, Pham H (2005) An inspection-maintenance model for systems with multiple competing processes. IEEE Trans Reliab 54(2):318–327
Kowandy C, Richard C, Chen YM, Tessier JJ (2007) Correlation between the tribological behaviour and wear particle morphology—case of grey cast iron 250 versus Graphite and PTFE. Wear 262(7):996–1006
Upadhyay RK (2013) Microscopic technique to determine various wear modes of used engine oil. J Microsc Ultrastruct 1(3):111–114
Ebersbach S, Peng Z, Kessissoglou N (2006) The investigation of the condition and faults of a spur gearbox using vibration and wear debris analysis techniques. Wear 260(1):16–24
Roylance BJ (2005) Ferrography—then and now. Tribol Int 38(10):857–862
Cao W, Dong G, Xie YB, Peng Z (2018) Prediction of wear trend of engines via on-line wear debris monitoring. Tribol Int 120:510–519
Feng S, Zeng Q, Fan B, Luo J, Xiao H, Mao J (2021) Wear debris segmentation of reflection ferrograms using lightweight residual U-Net. IEEE Trans Instrum Meas 70:1–11
Roylance BJ, Albidewi IA, Laghari MS (1994) Computer-aided vision engineering (CAVE)-quantification of wear particle morphology. Lubricat Eng 50(2):111–116
Peng Z, Kirk TB (1999) Wear particle classification in a fuzzy grey system. Wear 225:1238–1247
Peng Z, Goodwin S (2001) Wear-debris analysis in expert systems. Tribol Lett 11(3–4):177–184
Wang J, Yao P, Liu W, Wang X (2016) A hybrid method for the segmentation of a ferrograph image using marker-controlled watershed and grey clustering. Tribol Trans 59(3):513–521
Wu H, Wu T, Peng Y, Peng Z (2014) Watershed-based morphological separation of wear debris chains for on-line ferrograph analysis. Tribol Lett 53(2):411–420
Li Q, Zhao T, Zhang L, Sun W, Zhao X (2017) Ferrography wear particles image recognition based on extreme learning machine. J Electric Comput Eng 2017:1–6
Wang S, Wu T, Wang K, Sarkodie-Gyan T (2020) Ferrograph analysis with improved particle segmentation and classification methods. J Comput Inf Sci Eng 20(2):021001
Peng Y, Wu T, Cao G, Huang S, Wu H, Kwok N, Peng Z (2017) A hybrid search-tree discriminant technique for multivariate wear debris classification. Wear 392:152–158
Wu T, Peng Y, Wang S, Chen F, Kwok N, Peng Z (2017) Morphological feature extraction based on multiview images for wear debris analysis in on-line fluid monitoring. Tribol Trans 60(3):408–418
Wang S, Wu T, Yang L, Kwok N, Sarkodie-Gyan T (2019) Three-dimensional reconstruction of wear particle surface based on photometric stereo. Measurement 133:350–360
Peng P, Wang J (2019) FECNN: a promising model for wear particle recognition. Wear 432: 202968
Peng P, Wang J (2019) Wear particle classification considering particle overlapping. Wear 422:119–127
Fan S, Zhang T, Guo X, Wulamu A (2021) FFWR-Net: a feature fusion wear particle recognition network for wear particle classification. J Mech Sci Technol 35(4):1699–1710
Peng Y, Cai J, Wu T, Cao G, Kwok N, Zhou S, Peng Z (2019) A hybrid convolutional neural network for intelligent wear particle classification. Tribol Int 138:166–173
Peng Y, Cai J, Wu T, Cao G, Kwok N, Peng Z (2020) WP-DRnet: a novel wear particle detection and recognition network for automatic ferrograph image analysis. Tribol Int 151:106379
Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In European conference on computer vision. Springer, Cham, pp 21–37
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263–7271
Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv: 1804.02767
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv: 1502.03167.
Wang SH, Phillips P, Sui Y, Liu B, Yang M, Cheng H (2018) Classification of Alzheimer’s disease based on eight-layer convolutional neural network with leaky rectified linear unit and max pooling. J Med Syst 42(5):85
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998–6008
Woo S, Park J, Lee JY, So Kweon I (2018) Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3–19
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141
Gregor K, Danihelka I, Graves A, Rezende DJ, Wierstra D (2015) Draw: a recurrent neural network for image generation. arXiv preprint arXiv: 1502.04623.
Neubeck A, Van Gool L (2006) Efficient non-maximum suppression. In: 18th International conference on pattern recognition (ICPR'06). IEEE, vol 3, pp 850–855
He Y, Zhang X, Savvides M, Kitani K (2018) Softer-nms: rethinking bounding box regression for accurate object detection. arXiv preprint arXiv: 1809.08545, 2, 3.
Roylance BJ, Williams JA, Dwyer-Joyce R (2000) Wear debris and associated wear phenomena—fundamental research and practice. Proc Inst Mech Eng Part J J Eng Tribol 214(1):79–105
Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big Data 3(1):1–40
Acknowledgements
This work was supported by the key research and development plan of Shandong province (2018GGX105002) and the key research and development plan of Shandong province (2019JZZY020712).
Author information
Authors and Affiliations
Corresponding author
Additional information
Technical Editor: Celso Kazuyuki Morooka.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jia, F., Wei, H., Sun, H. et al. An object detection network for wear debris recognition in ferrography images. J Braz. Soc. Mech. Sci. Eng. 44, 67 (2022). https://doi.org/10.1007/s40430-022-03375-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-022-03375-4