Towards the intelligent analysis of ferrograph images

  • Jingqiu WangEmail author
  • Xinliang Liu
  • Ming Wu
  • Lianjun Wang
  • Xiaolei Wang
Conference paper
Part of the Mechanisms and Machine Science book series (Mechan. Machine Science, volume 73)


Ferrography determines the wear condition and failure mechanisms of the equipments through quantitative and qualitative analysis on the quantity, size, shape, and color of wear particles. Computer aided intelligent analysis of ferrograph images is an essential way to improve the efficiency and accuracy of ferrography. The historical progress of ferrograph image processing and analysis is reviewed, and a new strategy for ferrograph image analysis based on convolutional neural network is proposed and studied in this paper.


Ferrography Image processing Convolutional neural network 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hinton, G.E. and Salakhutdinov, R.R.: Reducing the Dimensionality of Data with Neural Networks. Science 313, 504-507 (2006).MathSciNetCrossRefGoogle Scholar
  2. 2.
    Roylance, B.J. and Pocock, G.: Wear studies through particle size distribution I: Application of the Weibull distribution to ferrography. Wear 90(1), 113-136 (1983).CrossRefGoogle Scholar
  3. 3.
    Price, A.L. and Roylance, B.J.: Image analysis and other metallographic techniques as an aid to machine health monitoring. Microstruct Sci 9, 123-136 (1981).Google Scholar
  4. 4.
    Wang, J., Zhang, L., and WANG, X.: Combining k-means clustering and watershed algorithm for the segmentation of color ferrograph image. Journal of China University of Minning & Technology 42(5), 866-872 (2013).Google Scholar
  5. 5.
    Wu, H., Wu, T., Peng, Y., et al.: Watershed-Based Morphological Separation of Wear Debris Chains for On-Line Ferrograph Analysis. Tribology Letters 53(2), 411-420 (2014).CrossRefGoogle Scholar
  6. 6.
    Wang, J., Yao, P., Liu, W., et al.: A Hybrid Method for the Segmentation of a Ferrograph Image Using Marker-Controlled Watershed and Grey Clustering. Tribology Transactions 59(3), 513-521 (2016).CrossRefGoogle Scholar
  7. 7.
    Thomas, A.D.H., Davies, T., and Luxmoore, A.R.: Computer image analysis for identification of wear particles. Wear 142(2), 213-226 (1991).CrossRefGoogle Scholar
  8. 8.
    Laghari, M.h. and Ahmed, F.: Wear Particle Profile Analysis. In: 2009 International Conference on Signal Processing Systems,pp.546-550. Singapore (2009).Google Scholar
  9. 9.
    Yuan, W., Chin, K.S., Hua, M., et al.: Shape classification of wear particles by image boundary analysis using machine learning algorithms. Mechanical Systems and Signal Processing 72-73, 346-358 (2016).CrossRefGoogle Scholar
  10. 10.
    Pintaude, G. and Coseglio, M.: A discussion on the application of bi-dimensional shape factors of particles causing severe wear of metals. In: Technical contribution to the 2nd International Brazilian Conference on Tribology – TriboBR 2014,pp. Foz do Iguaçu.(2014).Google Scholar
  11. 11.
    Stachowiak, G.P., Stachowiak, G.W., and Podsiadlo, P.: Automated classification of wear particles based on their surface texture and shape features. Tribology International 41(1), 34-43 (2008).CrossRefGoogle Scholar
  12. 12.
    Peng, Z. and Kirk, T.B.: Computer image analysis of wear particles in three-dimensions for machine condition monitoring. Wear 223, 157-166 (1998).CrossRefGoogle Scholar
  13. 13.
    Myshkin, N.K. and Grigoriev, A.Y.: Morphology: Texture, shape, and color of friction surfaces and wear debris in tribodiagnostics problems. Journal of Friction and Wear 29(3), 192-199 (2008).CrossRefGoogle Scholar
  14. 14.
    Liu, H., Wei, H., Wei, L., et al.: An experiment on wear particle’s texture analysis and identification by using deterministic tourist walk algorithm. Industrial Lubrication and Tribology 67(6), 582-593 (2015).CrossRefGoogle Scholar
  15. 15.
    Wolski, M., Podsiadlo, P., and Stachowiak, G.W.: Characterization of Surface Topography from Small Images. Tribology Letters 61(1), 1-14 (2015).Google Scholar
  16. 16.
    Tamura, H., Mori, S., and Yamawaki, T.: Textural features corresponding to visual perception. IEEE Transactions on Systems, Man and Cybernetics 8(6), 460-473 (1978).CrossRefGoogle Scholar
  17. 17.
    Laghari, M.S.: Recognition of texture types of wear particles. Neural Computing & Applications 12(1), 18-25 (2003).Google Scholar
  18. 18.
    Podsiadlo, P. and Stachowiak, G.W.: Development of advanced quantitative analysis methods for wear particle characterization and classification to aid tribological system diagnosis. Tribology International 38(10), 887-897 (2005).CrossRefGoogle Scholar
  19. 19.
    Stachowiak, G.W. and P.Podsiadlo: Characterization and classification of wear particles and surfaces. Wear (249), 194-200 (2001).CrossRefGoogle Scholar
  20. 20.
    Mcculloch, W.S. and Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathimatical Biophysics 5(4), 115-133 (1943).MathSciNetCrossRefGoogle Scholar
  21. 21.
    Hubel, D.H. and Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visualcortex. The Journal of Physiology 160(1), 106-154 (1962).CrossRefGoogle Scholar
  22. 22.
    ROSENBLATT, F.: The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review 65(6), 386-408 (1968).CrossRefGoogle Scholar
  23. 23.
    Rumelhart, D.E., Hinton, G.E., and Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533-536 (1986).CrossRefGoogle Scholar
  24. 24.
    Peng, Z. and Kirk, T.B.: Automatic wear particle classification using neural networks. Tribology Letters 5, 249-257 (1998).CrossRefGoogle Scholar
  25. 25.
    Gonçalves, V.D., Almeida, L.F.d., and Mathias, M.H.: Wear Particle Classifier System Based on an Artificial Neural Network. Journal of Mechanical Engineering (56), 284-289 (2010).Google Scholar
  26. 26.
    Gu, D., Zhou, L., and Wang, J.: Ferrography wear particle pattern recognition based on support vector machine. China Mechanical Engineering 17, 1391-1394 (2006).Google Scholar
  27. 27.
    Bao, C., Liu, X., and Yang, Z.: ColorTexture FeatureExtracting and Recognition of Ferrograph Image. Lubrication engineering 32(4), 17-19 (2007).Google Scholar
  28. 28.
    Li, Q., Zhao, T., Zhang, L., et al.: Ferrography Wear Particles Image Recognition Based on Extreme Learning Machine. Journal of Electrical and Computer Engineering 2017, 1-6 (2017).Google Scholar
  29. 29.
    Liu, Z., Feng, X., and Zhang, J.: Action recognition based on deep convolution neural network and depth sequences. Journal of Chongqing University 40(11), 99-106 (2017).Google Scholar
  30. 30.
    LeCun, Y., Boser, B., Denker, J.S., et al.: Handwritten digit recognition with a back-propagation network. Advances in Neural Information Processing Systems, Colorado, USA, 396-404 (1990).Google Scholar
  31. 31.
    A, K., I, S., and Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Proceedings of Advances in Neural Information Processing Systems South Lake Tahoe, USA, IEEE Press, 1097-1105 (2012).Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jingqiu Wang
    • 1
    Email author
  • Xinliang Liu
    • 1
  • Ming Wu
    • 1
  • Lianjun Wang
    • 1
  • Xiaolei Wang
    • 1
  1. 1.National Key Laboratory of Science and Technology on Helicopter TransmissionNanjing University of Aeronautics and AstronauticsNanjingChina

Personalised recommendations