Skip to main content Accessibility help

Research on Edge Surface Warping Defect Diagnosis Based on Fusion Dimension Reduction Layer DBN and Contribution Plot Method

  • Sun Jianliang (a1), Sun Mengqian (a1), Guo Hesong (a1), Peng Yan (a1), Ji Jiang (a2) and Xu Lipu (a2)...


The edge surface warping defect seriously affect the surface quality of strips. In this paper, a technology for diagnosis of warping defects in hot-rolled strip based on data-driven methods is studied. Based on the mechanism analysis of the warping defects, the process parameters affecting the warping defects were sorted out and used as the original input parameters of the defect diagnosis model. Firstly, a diagnostic model that combines the deep belief network and contribution plots of each dimensionality reduction layer is proposed. The deep belief network that integrates each dimensionality reduction layer can predict product defects more accurately and stably than the traditional deep belief network. Meanwhile, on the basis of the pre-judgment model, the method of contribution plot is further introduced to trace the defects, and the comprehensive diagnosis function of model pre-judgment and traceability is realized. Finally, collected the production data from a hot rolling production line for a period of time. Tested the model and predicted a hit rate of 85%. The main influencing factors of edge surface warping defects were determined that the rate of defect decrease with the increase of furnace temperature. When the heating temperature of the second stage of the heating furnace is higher than 1160°C, the incidence of defects is significantly reduced. Defect rate is relatively low within 240min of total furnace time. With the first and third pass phosphorus removal equipment turned on, the incidence of defects was relatively low.


Corresponding author

*Corresponding author (


Hide All
1.Xu, H. W., Yu, Y.Origination Mechanism of the Edge Shell Defect on the Hot-Rolled IF Steel Strip”. Iron and Steel, 47(9):53-56 (2012).
2.Liu, J. Q., Zhang, G.C., Tang, Q.Cause Analysis and Control Measures of Edge Shell Defect of Hot-Rolled Strip”. Steel Rolling, 33(6):77-80 (2016).
3.Luo, Y. Z., Jiao, H. L., Pang, Z. G.Effect of Hot-Rolled Technology on Slag Entrapment and Surface Sliver Defects for Ultralow Carbon IF Steel”. Iron and Steel, 50(5):44-48 (2015).
4.Pang, Q. H., Tang, D., Zhao, A. M.Formation Mechanism of the Scar Defect on the Surface of Hot Rolled Plate and Its Control Measures”. Steel Rolling, 31(6):9-11 (2014).
5.Zhou, X., Xia, Y. F., Wang, J. G.Study on Control Method for Edge Scar Defect of Hot Rolled Strip in Ferrite Region”. Steel Rolling, 35(6):24-27 (2018).
6.Pesin, A., Pustovoytov, D.Research of edge defect formation in plate rolling by finite element method”. Journal of Materials Processing Technology, 220:96106 (2015).
7.Li, X. A., Ding, J. G., Zeng, Q. L.Width Control Methods Based on Racial Correlation Technique in Plate Mill”. Steel Rolling, 28(1):58-60 (2011).
8.Wang, X. C., Yang, Q., Sun, Y. Z.Research on Comprehensive Optimization of Tandem Cold Rolling Setting Control System”. Journal of Mechanical Engineering, 50(6):39-47 (2014).
9.Yang, L. P., Zhang, Z., Wang, D. C.Mechanism-Intelligent Coordination Shape Control Model of Cold Strip”. Iron and Steel, 52(7):52-57 (2017).
10.Zhang, D. H., Liu, J. W., Wang, J. S.Self-Learning Model of Cold-Strip Mill Based on the Actuator Efficiency Factor of Shape Control”. Iron and Steel, 45(3):52-56 (2010).
11.Ren, X. W., Du, F. S., Huang, H. G.Application of Fuzzy Immune PID Controller Based on Gray Prediction in Gauge Control System”. Iron and Steel, 45(11):62-67 (2010).
12.Yang, J. M., Sun, X. N., Che, H. J.Neural Network Based on Ant Colony Algorithm for Rolling Force Prediction on Tandem Cold Rolling Mill”. Iron and Steel, 44(3):52-55 (2009).
13.Mahdi, B., Hosein, B.Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process”. Applied Mathematical Modelling, 37:4593-4607 (2013).
14.Li, Z. F., Ma, Y. L., Feng, Y.Applications of Neutral Network in Surface Hardness Prediction for Cold Rolling 301S Stainless Steel Thin Strip”. Iron and Steel, 49(5):63-67 (2014).
15.Bai, Z. H.Development and application of high-grade strip surface quality control technology”. World Metals, 12.B04, 1-6 (2014).
16.Li, R., Zhang, Q. D., Zhang, X. F.Control method for steel strip roughness in two-stand temper mill rolling”. Chinese Journal of Mechanical Engineering, 28(3):573-579 (2015).
17.Zhang, Q. D., Zhang, B. Y., Li, R.Advances in Theory and Technology for Microscopic Surface Quality Control of Steel Strip”. Journal of Mechanical Engineering, 52(10):32-45 (2016).
18.Chen, C. C., Shao, J., He, R. A.Research on Online Calculation Methods of Temperature Field of Hot Strip”. Chinese Journal of Mechanical Engineering, 50(14): 135-142 (2014).
19.Zhang, J., Li, N., Cao, J. G.Research Method and Measure Analysis of Transverse Temperature in Hot Rolling Strip”. Journal of University of Science and Technology Beijing, 29(2):140-143 (2007).
20.Hinton, G. E., Salakhutdinov, R. R.Reducing thedimensionality of data with neural networks”. Science, 313(5786): 504-507 (2006).
21.Yang, H., Yong, Y.Learning Restricted Boltzmann Machines using Mode-Hopping MCMC”. The 4th Int Conf on Machine Learning and Computing. Xi’an, 20:105-110 (2012).


Research on Edge Surface Warping Defect Diagnosis Based on Fusion Dimension Reduction Layer DBN and Contribution Plot Method

  • Sun Jianliang (a1), Sun Mengqian (a1), Guo Hesong (a1), Peng Yan (a1), Ji Jiang (a2) and Xu Lipu (a2)...


Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed.