A Multi-Criteria Decision Making Procedure Based on Neural Networks for Kanban Allocation

  • Özlem Uzun Araz
  • Özgür Eski
  • Ceyhun Araz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


In this study, we proposed a methodology for determining optimal number of kanbans for each station in a JIT manufacturing system. In this methodology, a backpropagation neural network is used in order to generate simulation meta-models, and a multi-criteria decision making technique (TOPSIS) is employed in order to evaluate kanban combinations with respect to the relative importance of the performance measures. The proposed methodology is applied to a case problem and the results are presented. The results show that the methodology can solve this type of problems effectively and efficiently.


Kanban System Kanban Withdrawal Production Kanban 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ramanan, G.V., Rajendran, C.: Scheduling in Kanban-Controlled Flowshops to Minimise the Makespan of Containers. Int. J. Adv. Manuf. Technol. 21, 348–354 (2003)CrossRefGoogle Scholar
  2. 2.
    Bard, J.F., Golony, B.: Determining the Number of Kanbans in a Multiproduct, Multistage Production System. Int. J. of Production Research 29, 881–895 (1991)CrossRefGoogle Scholar
  3. 3.
    Mitwasi, M.G., Askin, R.G.: Production Planning for A Multi-item, Multi-stage Kanban System. Int. J. of Production Research 32, 1173–1195 (1994)MATHCrossRefGoogle Scholar
  4. 4.
    Wang, H., Wang, H.P.: Determining the Number of Kanbans: A Step toward Non-Stock-Production. Int. J. of Production Research 28, 2101–2115 (1990)CrossRefGoogle Scholar
  5. 5.
    Askin, R.G., Mitwasi, M.G., Goldberg, J.B.: Determining the Number of Kanbans in Multi-Item Just-In-Time Systems. IIE Transactions 25, 89–97 (1993)CrossRefGoogle Scholar
  6. 6.
    Gupta, Y.P., Gupta, M.C.: A System Dynamics Model for A Multi-Stage, Multi-Line Dual-Card JIT-Kanban System. Int. J. of Production Research 27, 309–352 (1989)CrossRefGoogle Scholar
  7. 7.
    Savsar, M.: Effects of Kanban Withdrawal Policies and Other Factors on the Performance of JIT Systems: A Simulation Study. Int. J. of Production Research 34, 205–214 (1996)Google Scholar
  8. 8.
    Aytug, H., Dogan, C.A., Bezmez, G.: Determining the Number of Kanbans: A Simulation Metamodeling Approach. Simulation 67, 23–32 (1996)CrossRefGoogle Scholar
  9. 9.
    Hurrion, R.D.: An Example of Simulation Optimization Using A Neural Network Metamodel: Finding the Optimum Number of Kanbans in Manufacturing System. Journal of the Operation Research Society 48, 1105–1112 (1997)MATHGoogle Scholar
  10. 10.
    Savsar, M., Choueiki, M.H.: A Neural Network Procedure for Kanban Allocation in JIT Production Control Systems. Int. J. of Production Research 38, 3247–3265 (2000)MATHCrossRefGoogle Scholar
  11. 11.
    Hwang, C.L., Yoon, K.: Multiple Attribute Decision Making: Methods and Applications, A State-of-the-Art Survey. Springer, Berlin (1981)MATHGoogle Scholar
  12. 12.
    Pomerol, J.C., Romero, S.B.: Multicriterion Decision in Management: Principles and Practice. Kluwer Academic Publishers, USA (2000)MATHGoogle Scholar
  13. 13.
    Triantaphyllou, E., Lin, C.T.: Development and evaluation of five fuzzy multi-attribute decision making methods. Int. J. of Approximate Reasoning 14, 281–310 (1996)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Özlem Uzun Araz
    • 1
  • Özgür Eski
    • 1
  • Ceyhun Araz
    • 1
  1. 1.Faculty of Engineering, Industrial Engineering Dept.Dokuz Eylul UniversityBornova-IzmirTurkey

Personalised recommendations