Abstract
The steel production equipment faults are mostly caused by wear faults, and the classification of wear debris in its lubrication system can monitor the wear status of the machine. The traditional methods of wear debris image classification mostly use digital image processing technology by extracting color, shape, texture and other multi-dimensional features of wear debris. It is so difficult to extract suitable multi-dimensional features that the classification accuracy is always kept at a low level. Convolutional Neural Network can directly take the image pixels as input, and extract features automatically, avoiding the poor applicability of manual extraction methods and complicated image pre-processing. An improved lightweight convolutional neural network for wear debris image classification named UstbNet is proposed in this paper. Data augmentation, number and size adjustment of convolution kernels, batch normalization and loss function optimization are used to speed up the model convergence and improve the classification accuracy. The classification accuracy of UstbNet model reaches 96%. After the step of determining the existence of wear debris, we use Faster RCNN to detect the quantity and size of wear debris and further improve it. Grabcut is applied to segment wear debris image based on detected region proposals.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
23 January 2020
The original version of this chapter contained an error in Table 10. The values in the last three rows of the table have been modified. The table has now been corrected.
References
Kun, X., Luxmoore, A.R., Deravi, F.: Comparison of shape features for the classification of wear particles. Eng. Appl. Artif. Intell. 10, 485 (1997)
Zhao, R.: Study on lubrication of metallurgical rolling equipment. Sci. Technol. Enterp. 357–358 (2013)
Qin, H., Ren, Z., Zhao, J., Ye, C., Doll, G.L., Dong, Y.: Effects of ultrasonic nanocrystal surface modification on the wear and micropitting behavior of bearing steel in boundary lubricated steel-steel contacts. Wear 392, 29 (2017)
Chang, Z., Jia, Q., Yuan, X., Chen, Y.: Main failure mode of oil-air lubricated rolling bearing installed in high speed machining. Tribol. Int. 112, 68 (2017)
Mosleh, M., Bradshaw, K., Belk, J.H., Waldrop, J.C.I.: Fatigue failure of all-steel and steel-silicon nitride rolling ball combinations. Wear 271, 2471 (2011)
Mao, J.: Study on preparation technology of self-lubricating wear-resistant coatings on mill gear surface by composite of laser cladding and shock peening. Master. Jiangsu University (2016)
Wang, F.: Study on the ferrography wear particle with image processing technology. Master. Wuhan University of Technology (2005)
Thomas, A.D.H., Davies, T., Luxmoore, A.R.: Computer image analysis for identification of wear particles. Wear 142, 213 (1991)
Stachowla, G.P., Stachowiak, G.W., Podsladlo, P.: Automated classification of wear particles based on their surface texture and shape features. Tribol. Int. 41, 34 (2008)
Roylance, B.J., ALbidewi, I.A., Laghari, M.S., Luxmoore, A.R., Deravi, F.: Computer-aided vision engineering (CAVE)–quantification of wear particle morphology. In: STLE 48th Annual Meeting, Calgary, Alberta, Canada, 6 pp. (1993)
Xu, K., Luxmoore, A.R., Jones, L.M., Deravi, F.: Integration of neural networks and expert systems for microscopic wear particle analysis. Knowl.-Based Syst. 11, 213 (1998)
Zuo, H., Wu, Z., Yang, Z.: Application of double BP-network in debris identification. Acta Aeronautica ET Astronautica Sinica 21, 372 (2000)
Li, Q., Zhao, T., Zhang, L., Sun, W., Xi, Z.: Ferrograghy wear particles image recognition based on extreme learning machine. J. Electr. Comput. Eng. 2017, 1 (2017)
Peng, Z.: An integrated intelligence system for wear debris analysis. Wear 252, 730 (2002)
Xiong, A., Kong, X., Wang, J., Chen, D.: The sharable wear particle recognition and wear diagnosis system. Mech. Sci. Technol. Aerosp. Eng. 421, 421–423 (2002)
Peng, Y., Wu, T., Wang, S., Peng, Z.: Wear state identification using dynamic features of wear debris for on-line purpose. Wear 376–377, 1885 (2017)
Yuan, W., Chin, K.S., Hua, M., Dong, G., Wang, C.: Shape classification of wear particles by image boundary analysis using machine learning algorithms. Mech. Syst. Signal Process. 72–73, 346 (2016)
Tian, Y., Wang, J., Peng, Z., Jiang, X.: A new approach to numerical characterisation of wear particle surfaces in three-dimensions for wear study. Wear 282–283, 59 (2012)
Isa, M.C., Yusoff, N.H.N., Nain, H., Yati, M.S.D., Muhammad, M.M., Nor, I.M.: Ferrographic analysis of wear particles of various machinery systems of a commercial marine ship. Procedia Eng. 68, 345 (2013)
Wang, J., Wang, X.: A wear particle identification method by combining principal component analysis and grey relational analysis. Wear 304, 96 (2013)
Wang, H., Huang, R., Gao, L., Wang, W., Xu, A., Yuan, F.: Wear debris classification of steel production equipment using feature fusion and case-based reasoning. ISIJ Int. 58, 1293 (2018)
Wang, J., Zhang, L., Lu, F., Wang, X.: The segmentation of wear particles in ferrograph images based on an improved ant colony algorithm. Wear 311, 123 (2014)
Wu, Z.: An vehicle type recognition method based on Convolution Neural Network. Mech. Electr. Eng. Technol. Z2, 608 (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84 (2017)
Yu, S., Jia, S., Xu, C.: Convolutional neural networks for hyperspectral image classification. Neurocomputing 219, 88 (2017)
Ferreira, A., Giraldi, G.: Convolutional Neural Network approaches to granite tiles classification. Expert Syst. Appl. 84, 1 (2017)
Gomez Villa, A., Salazar, A., Vargas, F.: Towards automatic wild animal monitoring: identification of animal species in camera-trap images using very deep convolutional neural networks. Ecol. Inform. 41, 24 (2017)
Dyrmann, M., Karstoft, H., Midtiby, H.S.: Plant species classification using deep convolutional neural network. Biosys. Eng. 151, 72 (2016)
Acknowledgment
This work is supported by National key R & D plan (2016YFB0601301), National Natural Science Foundation (51574032, 51674030) and Fundamental Research Funds for the Central Universities (FRF-TP-18-097A1).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, H., Yuan, F., Gao, L., Huang, R., Wang, W. (2019). Wear Debris Classification and Quantity and Size Calculation Using Convolutional Neural Network. In: Ning, H. (eds) Cyberspace Data and Intelligence, and Cyber-Living, Syndrome, and Health. CyberDI CyberLife 2019 2019. Communications in Computer and Information Science, vol 1137. Springer, Singapore. https://doi.org/10.1007/978-981-15-1922-2_33
Download citation
DOI: https://doi.org/10.1007/978-981-15-1922-2_33
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1921-5
Online ISBN: 978-981-15-1922-2
eBook Packages: Computer ScienceComputer Science (R0)