Transactions of the Korean Society of Machine Tool Engineers (한국공작기계학회논문집)

The Korean Society of Manufacturing Technology Engineers (한국생산제조학회)
권호 표지

Improvement of Thickness Accuracy in Hot-rolling Mill Using Neural Network and Genetic Algorithm

신경회로망과 유전자 알고리즘을 이용한 열연두께 정도 향상

  • 손준식 (목포대학교 대학원 기계공학과) ;
  • 김일수 (목포대학교 기계선박해양공학부) ;
  • 이덕만 (POSCO 기술연구소) ;
  • 권영섭 (POSCO 기술연구소)
  • Published : 2006.10.15
Download PDF
⟨ Previous Next ⟩

Abstract

The automation of hot rolling process requires the developments of several mathematical models for simulation and quantitative description of the industrial operations involved in order to achieve the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties). The mathematical modeling of hot rolling process has long been recognized to be a desirable approach to investigate rolling operating practice and design of mill requirement. To achieve this objectives, a new teaming method with neural network to improve the accuracy of rolling force prediction in hot rolling mill is developed. Also, Genetic Algorithm(GA) is applied to select the optimal structure of the neural network and compared with that of engineers experience. It is shown from this research that both structure selection methods can lead to similar results.

Keywords

References

  1. Portmann, N. F., 1995, 'Application of neural networks in rolling mill automation,' Iron and Steel Engineer, Vol. 72, No. 2, pp. 33-36
  2. Lu, C., Wang, X., Liu, X., Wang, G., Zhao, K. and Yuan, J., 1998, 'Application of ANN in combination with mathematical models in prediction of rolling load of the finishing stands in HSM,' Proceeding of The International Conference on Steel Rolling, Iron and Steel Institute of Japan, pp. 206-209
  3. Son, J. S., Lee, D. M., Kim, I. S. and Choi, S. G., 2004, 'A Study on the Prediction for Rolling Force Using Radial Basis Function Network in Hot Rolling Mill,' Journal of the Korean Society of Machine Tool Engineers, Vol. 13, No. 6, pp. 29-33
  4. Poppe, T., Obradovic, D. and Schlang, M., 1995, 'Neural networks : Reducing energy and raw materials requirements,' Siemens Review-R&D Special, pp. 24-27
  5. Schlang, M., Lang, B., Poppe, T., Runkler, T. and Weinzierl, K., 2001, 'Current and future development in neural computation in steel processing,' Control Engineering Practice, Vol. 9, pp. 975-986 https://doi.org/10.1016/S0967-0661(01)00086-7
  6. Yao, X., 1996, Application of artificial intelligence for quality control at hot strip mills, Ph.D Thesis, The University of Wollongong
  7. Khanna, T., 1990, Foundations of Neural Networks, Addson-Wesley
  8. Hagan, M. T. and Menhaj, M. B., 1994, 'Training feedforward networks with marquardt algorithm,' IEEE Transaction on Neural Networks, Vol. 5, No. 6, pp. 989-993 https://doi.org/10.1109/72.329697
  9. Poliak, E. I., 1998, 'Application of linear regression analysis in accuracy assessment of rolling force calculations,' Metals and Materials, Vol. 4, No. 5, pp. 1047-1056 https://doi.org/10.1007/BF03025975