Advertisement

Design and Automation for Manufacturing Processes: An Intelligent Business Modeling Using Adaptive Neuro-Fuzzy Inference Systems

  • Alaa F. Sheta
  • Malik Braik
  • Ertan Öznergiz
  • Aladdin Ayesh
  • Mehedi Masud
Part of the Advanced Information and Knowledge Processing book series (AI&KP)

Abstract

The design and automation of a steel making process is getting more complex as a result of the advances in manufacturing and becoming more demanding in quality requirements. It is essential to have an intelligent business process model which brings consistent and outstanding product quality thus keeping the trust with the business stakeholders. Hence, schemes are highly needed for improving the nonlinear process automation. The empirical mathematical model for steel making process is usually time consuming and may require high processing power. Fuzzy neural approach has recently proved to be very beneficial in the identification of such complex nonlinear systems. In this chapter, we discuss the applicability of an Adaptive Neuro-Fuzzy Inference System (ANFIS) to model the dynamics of the hot rolling industrial process including: roll force, roll torque and slab temperature. The proposed system was developed, tested as well as compared with other existing systems. We have conducted several simulation experiments on real data and the results confirm the effectiveness of the ANFIS based algorithms.

Keywords

Mean Square Error Fuzzy Inference System Minimum Mean Square Error Rolling Process Roll Force 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

Authors would like to thank Prof. Dr. Can Özsoy and the Ereg̃li Iron and Steel Factory for providing the required technical assistant and the data for this developed research work.

References

  1. 1.
    Kwak, W.J., Kim, Y.H., Park, H.D., Lee, J.H., Hwang, S.M.: Fe-based on-line model for the prediction of roll force and roll power in hot strip rolling. ISIJ Int., 40(20), 1013–1018 (2000) CrossRefGoogle Scholar
  2. 2.
    Öznergiz, E., Gülez, K., Ozsoy, C.: Neural network modeling of a plate hot-rolling process and comparision with the conventional techniques. In: International Conference on Control and Automation, vol. 1, pp. 646–651 (2005) Google Scholar
  3. 3.
    Al-Hiary, H., Braik, M., Sheta, A., Ayesh, A.: Identification of a chemical process reactor using soft computing techniques. In: 2008 IEEE International Conference on Fuzzy Systems (FUZZ 2008), pp. 845–853 (2008) Google Scholar
  4. 4.
    Sheta, A., Al-Hiary, H., Braik, M.: Identification of model predictive controller design of the Tennessee Eastman chemical process reactor using ANN. In: International Conference of Artificial Intelligence (ICAI’09), pp. 25–31 (2009) Google Scholar
  5. 5.
    Sheta, A.: Modeling the Tennessee Eastman chemical reactor using fuzzy logic. In: The ISE Book Series on Fuzzy System Engineering-Theory and Practice. Nova Science, New York (2005). ISBN: 3-540-25322-X Google Scholar
  6. 6.
    Sheta, A., Öznergiz, E., Abdelrahman, M.A., Babuška, R.: Modeling of hot rolling industrial process using fuzzy logic. In: CAINE-2009, San Francisco, CA, USA, 4–6 November 2009 (2009) Google Scholar
  7. 7.
    Kirihata, A., Siciliano, F. Jr., Maccagno, T.M., Jonas, J.J.: Mathematical modelling of rolling of multiply-alloyed mean flow stress during medium carbon steels. ISIJ Int. 38(2), 187–195 (1998) CrossRefGoogle Scholar
  8. 8.
    Cowling, P.: A flexible decision support system for steel hot rolling mill scheduling. Comput. Ind. Eng. 45(2), 307–321 (2003) CrossRefGoogle Scholar
  9. 9.
    Feng, X., Liu, Y., Luo, H., Tang, H., Liu, C.: Numerical simulation during expansion for hot rolling sheet strip. In: Proceedings of the First International Workshop on Knowledge Discovery and Data Mining, WKDD ’08, Washington, DC, USA, pp. 310–313. IEEE Comput. Soc., New York (2008) CrossRefGoogle Scholar
  10. 10.
    Cser, L., Gulyás, J., Szücs, L., Horváth, A., Árvai, L., Baross, B.: Different kinds of neural networks in control and monitoring of hot rolling mill. In: Proceedings of the 14th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE ’01, pp. 791–796. Springer, London (2001) Google Scholar
  11. 11.
    Lee, D.M., Lee, Y.: Application of neural-network for improving accuracy of roll force model in hot-rolling mill. Control Eng. Pract. 10(2), 473–478 (2002) CrossRefGoogle Scholar
  12. 12.
    Bouhouche, S., Yahi, M., Hocine, B., Bast, J.: Soft sensor—based artificial neural networks and fuzzy logic: application to quality monitoring in hot rolling. In: Proceedings of the 10th WSEAS International Conference on Automatic Control, Modelling & Simulation, ACMOS’08. World Scientific and Engineering Academy and Society, pp. 149–154. Stevens Point, Wisconsin (2008) Google Scholar
  13. 13.
    Tarokh, M., Seredynski, F.: Roll force estimation in plate rolling. J. Iron Steel Inst. 208, 694 (1970) Google Scholar
  14. 14.
    Özsoy, C., Ruddle, E.D., Crawley, A.F.: Optimal scheduling of a hot rolling process by nonlinear programming. Can. Metall. Q. 3(31), 217–224 (1992) CrossRefGoogle Scholar
  15. 15.
    Mandal, M., Pal, S.K.: Pseudo-bond graph modelling of temperature distribution in a through-process steel rolling. Math. Comput. Simul. 77(1), 81–95 (2008) MathSciNetMATHCrossRefGoogle Scholar
  16. 16.
    Öznergiz, E., Özsoy, C., Delice, I.I., Kural, K.: Comparison of empirical and neural network hot-rolling process model. J. Eng. Manuf. 223, 305–312 (2009) CrossRefGoogle Scholar
  17. 17.
    Jang, J.S.R.: ANFIS, adaptive network based fuzzy inference systems. In: IEEE Transaction on Systems, Man and Cybernetics, vol. 23, pp. 665–684 (1993) Google Scholar
  18. 18.
    Jang, J.S.R., Sun, C.T., Mizutani, E.: Neuro-Fuzzy and Soft Computing. Prentice-Hall, Englewood Cliffs (1997) Google Scholar
  19. 19.
    Takagi, T., Sugeno, M.: Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Syst. Man Cybern. 15(1), 116–132 (1985) MATHCrossRefGoogle Scholar
  20. 20.
    Babuška, R., Roubos, J.A., Verbruggen, H.B.: Identification of MIMO systems by input–output TS fuzzy models. In: Proceedings of Fuzzy—IEEE’98, Anchorage, Alaska (1998) Google Scholar
  21. 21.
    Babuška, R., Verbruggen, H.: Identification of composite linear models via fuzzy clustering. In: Proceedings of European Control Conference, Rome, Italy, pp. 1207–1212 (1995) Google Scholar
  22. 22.
    Babuška, R., Verbruggen, H.B.: Applied fuzzy modelings. In: Proceedings of IFAC Symposium on Artificial Intelligence in Real Time Control, Valencia, Spain, pp. 61–66 (1994) Google Scholar
  23. 23.
    Subudhi, B., Jena, D.: Differential evolution and Levenberg Marquardt trained neural network scheme for nonlinear system identification. Neural Process. Lett. 27(3), 285–296 (2008) CrossRefGoogle Scholar
  24. 24.
    Asadi, S., Hadavandi, E., Mehmanpazir, F., Nakhostin, M.M.: Hybridization of evolutionary Levenberg-Marquardt neural networks and data pre-processing for stock market prediction. Knowl.-Based Syst. 35, 245–258 (2012) CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Alaa F. Sheta
    • 1
  • Malik Braik
    • 2
  • Ertan Öznergiz
    • 3
  • Aladdin Ayesh
    • 4
  • Mehedi Masud
    • 1
  1. 1.Department of Computer Science, College of Computers and Information TechnologyTaif UniversityTaifSaudi Arabia
  2. 2.Electronic, Electrical and Computer Engineering DepartmentUniversity of BirminghamBirminghamUK
  3. 3.Marine Engineering Operations Department, Faculty of Naval Architecture and MaritimeYildiz Technical UniversityIstanbulTurkey
  4. 4.Faculty of TechnologyDe Montfort UniversityLeicesterUK

Personalised recommendations