A Smart Roll Wear Check Scheme for Ensuring the Rolling Quality of Steel Plates

  • Kui Zhang
  • Xiaohu Zhou
  • Heng HeEmail author
  • Yonghao Wang
  • Weihao Wang
  • Huajian Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11910)


Roll surface wear morphology directly affects the surface quality of steel plates and even affects the texture composition of plates and strip steel products. Using image processing methods to judge the wear state of a roll is low cost, easy to operate, and easy to realize an automatic smart data processing system. In this paper, we propose a Smart Roll Wear Check (SRWC) scheme for ensuring the rolling quality of steel plates. In the SRWC scheme, roll surface images in different wear stages are analyzed, from which seventeen dimension features are extracted. At the same time, the fractal theory is introduced to explore the relationship between fractal dimensions and roll wear degree. The results show that four characteristic parameters, such as roundness, equivalent area circle radius, second moment and texture entropy, and the fractal dimension can be used as effective parameters to quantitatively judge roll wear state. Lastly, a back-propagation (BP) neural network model for recognition and judgment for roll wear is established. It provides an experimental test to show that the five parameters as a quantitative evaluation for roll wear morphology are effective. By processing the data on the images, the SRWC scheme can demonstrate whether the roll needs to get off mill in time, so as to avoid the hidden danger of safety and ensure the rolling quality of the steel plate.


Roll wear Image features Fractal dimension BP neural network Image processing 


  1. 1.
    Kong, X.W., Shi, J., Xu, J.Z., Wang, G.D.: Wear prediction of roller for hot mill during service. J. Northeast. Univ. (Natl. Sci.) 23(8), 790–792 (2002)Google Scholar
  2. 2.
    Huang, Y.G.: Research of image feature and fractal on roll surface morphology in the wear process (轧辊磨损形貌图像特征及分形研究). Master thesis, Wuhan University of Science and Technology, Wuhan (2015)Google Scholar
  3. 3.
    Liu, X.L., Xu, C.G., Zhang, X.K.: Optimization technology of original surface roughness of rolls in cold continuous rolling mill. J. Iron Steel Res. (11), 888–893 (2018)Google Scholar
  4. 4.
    Song, F.: For the design of a reflective sensor system for the detection of roller. Electron. Test (5), 122–123 (2015)Google Scholar
  5. 5.
    Ge, Q.: Research on laser texturing roller surface roughness detection system using a light-section method (基于光切法的激光毛化轧辊表面粗糙度检测系统的研究). Master thesis, Huazhong University of Science and Technology, Wuhan (2011)Google Scholar
  6. 6.
    Chen, P.P., Su, L.H.: Detection of parallelism of hot rolling roll system based on embedded image processing. In: Proceedings of the 11th Annual meeting of China Iron and Steel, pp. 1–7. The Chinese Society for Metals, Beijing (2017)Google Scholar
  7. 7.
    Yang, G., Zhang, X.H., He, G.P., Huang, J.H.: Anomaly detection SVDD algorithm based on non-subsampled contoured transform. Autom. Instrum. 6, 63–65 (2016)Google Scholar
  8. 8.
    Majumdar, A., Tian, C.L.: Fractal characterization and simulation of rough surfaces. Wear 136(2), 313–327 (2016)CrossRefGoogle Scholar
  9. 9.
    Lan, Y., Li, Y.H., Zhang, S.S.: Research of oxide film control on high chrome work roll surface in Maanshan Steel CSP. Chinese Metallurgy 21(1), 33–37 (2011)Google Scholar
  10. 10.
    Li, L., Huang, Y.G., Zhang, K., Lv, X.Y., Li, B., Wu, X.D.: Image feature and fractal on roll surface morphology in the wear process. Iron Steel 50(4), 98–103 (2015)Google Scholar
  11. 11.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 4th edn. Pearson Prentice Hall, Upper Saddle River (2017)Google Scholar
  12. 12.
    Hou, Q.L.: Investigation on the technology of tool wear detection based on machine vision (基于机器视觉的刀具检测技术研究). Master thesis, Shandong University, Shandong (2018)Google Scholar
  13. 13.
    Lee, J.H., Kim, Y.S., Kim, S.R.: Real-time application of critical dimension measurement of TFT-LCD pattern using a newly proposed 2D image-processing algorithm. Opt. Lasers Eng. 1, 558–569 (2008)CrossRefGoogle Scholar
  14. 14.
    Zhai, J.H., Zhao, W.X., Wang, X.Z.: Research on the image feature extraction. J. Hebei Univ. (Natl. Sci. Ed.) 29(1), 106–112 (2009)Google Scholar
  15. 15.
    Meng, H.D., Liu, L.: Study on steel slag grinding characteristics. Iron Steel 45(2), 28 (2010)Google Scholar
  16. 16.
    Ge, S.H., Zhu, H.: Fractal of Tribology (摩擦学的分形). Mechanical Industry Publishing House, Beijing (2005)Google Scholar
  17. 17.
    Cui, Z.M., Li, Y.L., Ying Chen, Y.: Surface structure and fractal dimension calculation of pore in low silicon sinter. Iron Steel 49(9), 10–14 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kui Zhang
    • 1
    • 2
  • Xiaohu Zhou
    • 3
  • Heng He
    • 1
    • 2
    Email author
  • Yonghao Wang
    • 3
  • Weihao Wang
    • 3
  • Huajian Li
    • 3
  1. 1.College of Computer Science and TechnologyWuhan University of Science and TechnologyWuhanPeople’s Republic of China
  2. 2.Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial SystemWuhanPeople’s Republic of China
  3. 3.Faculty of Computing, Engineering and the Built EnvironmentBirmingham City UniversityBirminghamUnited Kingdom

Personalised recommendations