Kanban sistemlerinde yapay zeka tabanlı optimizasyon uygulama teknikleri: literatür incelemesi ve metodolojik yaklaşımlar

Abstract

Bu çalışmada, Teknolojik gelişmeler, yalın üretim süreçlerinde kullanılan yöntem ve araçlarda köklü dönüşümlere yol açmıştır. Çekme sistemlerinin temel araçlarından biri olan Kanban kartları da bu dönüşüm sürecinde yalnızca fiziksel bir işaretleme aracı olmaktan çıkarak dijital ve yapay zekâ tabanlı çözümlerle yeniden şekillenmiştir. Özellikle karmaşık ve dinamik üretim ortamlarında karar verme süreçlerinin hızlanması, stok seviyelerinin dengelenmesi ve üretim akışının optimize edilmesi için yapay zekâ tabanlı optimizasyon tekniklerinin Kanban sistemlerine entegrasyonu giderek önem kazanmaktadır. Bu çalışma, Kanban sistemlerinde yapay zekâ tabanlı optimizasyon uygulamalarını ele alan literatürü sistematik biçimde incelemektedir. Çalışma kapsamında, genetik algoritmalar, tabu arama, benzetilmiş tavlama, karınca kolonisi optimizasyonu ve parçacık sürü optimizasyonu gibi yöntemlerin kullanım alanları, ele aldıkları problem türleri ve sundukları katkılar değerlendirilmiştir. Analiz sonucunda, bu tekniklerin özellikle değişken üretim koşullarında karar verme süreçlerini hızlandırma ve sistemin adaptasyon kapasitesini güçlendirmede etkili olduğu belirlenmiştir. Bilindiği kadarıyla bu çalışma, Kanban sistemlerinde yapay zekâ tabanlı optimizasyon yöntemlerini bütüncül bir bakış açısıyla inceleyen literatürdeki ilk sistematik çalışma olma özelliğini taşımaktadır. Böylece hem akademik hem de endüstriyel uygulamalar için gelecekteki araştırmalara yön verecek kapsamlı bir çerçeve sunulmaktadır.

Keywords

• Kanban
• yalın üretim
• yapay zeka
• optimizasyon teknikleri

Artificial intelligence-based optimization applications techniques in Kanban Systems: Literature review and methodological approaches

Abstract

In this study, technological advancements have led to fundamental transformations in the methods and tools used in lean production processes. Kanban cards, one of the primary tools of pull systems, have evolved in this transformation process from being merely a physical signaling tool to being reshaped with digital and artificial intelligence-based solutions. Especially in complex and dynamic production environments, the integration of AI-based optimization techniques into Kanban systems is increasingly important for accelerating decision-making processes, balancing inventory levels, and optimizing production flow. This study systematically reviews the literature on AI-based optimization applications in Kanban systems. Within the scope of the study, the use, problem types addressed, and contributions of methods such as genetic algorithms, tabu search, simulated annealing, ant colony optimization, and particle swarm optimization were evaluated. The analysis revealed that these techniques are particularly effective in accelerating decision-making processes and enhancing the adaptive capacity of the system under variable production conditions. To the best of our knowledge, this study represents the first systematic review in the literature to examine AI-based optimization methods in Kanban systems from a comprehensive perspective. Consequently, it provides a broad framework that will guide future research for both academic and industrial applications.

Keywords

• Kanban
• lean production
• artificial intelligence
• optimization methods

References

1. Four Principles Management Consulting, Marrying’ Artificial Intelligence and Lean Management in Manufacturing, (2018). Accessed: Aug. 08, 2025. [Online]. Available: www.fourprinciples.com
2. Ohno, T., Evolution of Toyota Production System. (2017).
3. Becker, M. and Szczerbicka H., Modeling and Optimization of Kanban Controlled Manufacturing Systems with GSPN Including QN. California: IEEE, (1998).
4. Szczerbicka, H., Becker, M., and Syrjakow, M., Genetic algorithms: A tool for modelling, simulation, and optimization of complex systems, Cybernetics and Systems Analysis, vol. 29, no. 7, 639–659, (1998). doi: 10.1080/019697298125461.
5. Koulouriotis, D. E., Xanthopoulos, A. S. and Tourassis, V. D., Simulation optimisation of pull control policies for serial manufacturing lines and assembly manufacturing systems using genetic algorithms, International Journal of Production Research, vol. 48, no. 10, 2887–2912, (2010). doi: 10.1080/00207540802603759.
6. Azadeh, A., Ebrahimipour, V., and Bavar, P., A hybrid GA-simulation approach to improve JIT systems, International Journal of Production Research, vol. 48, no. 8, 2323–2344, (2010). doi: 10.1080/00207540802676441.
7. Azadeh, A., Layegh, J., and Pourankooh, P., Optimal Model for Supply Chain System Controlled by Kanban under JIT Philosophy by Integration of Computer Simulation and Genetic Algorithm, Australian Journal of Basic Applied Sciences, vol. 4, no. 3, 370–378, (2010).
8. Hou, T. H. and Hu, W. C., An integrated MOGA approach to determine the Pareto-optimal kanban number and size for a JIT system, Expert Systems with Applications, vol. 38, no. 5, 5912–5918, (2011). doi: 10.1016/j.eswa.2010.11.032.

9. Huang, L., Multi-Product Kanban System Based on Modified Genetic Algorithm, Proceedings of the International Conference on Information Engineering and Applications (IEA), Z. Zhong, Ed., 817–824, (2012).
10. Smew, W., Young, P., and Geraghty, J., Supply chain analysis using simulation, gaussian process modelling and optimisation, International Journal of Simulation Modelling, vol. 12, no. 3, 178–189, (2013). doi: 10.2507/IJSIMM12(3)4.239.
11. Xanthopoulos, A. S., Koulouriotis, D. E., and Botsaris, P. N., Single-stage Kanban system with deterioration failures and condition-based preventive maintenance, Reliability Engineering&System Safety, vol. 142, 111–122, (2015). doi: 10.1016/j.ress.2015.05.008.
12. Belisário, L. S. and Pierreval, H., Using genetic programming and simulation to learn how to dynamically adapt the number of cards in reactive pull systems, Expert Systems with Applications, vol. 42, no. 6, 3129–3141, (2015). doi: 10.1016/j.eswa.2014.11.052.
13. Al-Hawari, T., Qasem, A. G., and Smadi, H., Development and evaluation of a Basestock-CONWIP pull production control strategy in balanced assembly systems, Simulation Modelling Practice and Theory, vol. 84, 83–105, (2018). doi: 10.1016/j.simpat.2018.01.008.
14. Azouz, N., Silva Belisário, L., Ammar, A., and Pierreval, H., Addressing over-correction in adaptive card-based pull control systems, International Journal of Computer Integrated Manufacturing, vol. 31, no. 12, 1189–1204, (2018). doi: 10.1080/0951192X.2018.1509132.
15. Nugroho, W. A. and Suroso, J. S., Optimizing Kanban Configuration in High Mix, Low Volume Environmentes by Applying Multi Objective Genetic Algorithm, Journal of Theoretical Applied Information Technology, vol. 15, no. 1, (2023).
16. Alabas, C., Altiparmak, F., and Dengiz, B., A comparison of the performance of artificial intelligence techniques for optimizing the number of kanbans, Journal of the Operational Research Society, vol. 53, no. 8, 907–914, (2002). doi: 10.1057/palgrave.jors.2601395.
17. Martin, A. D., Chang, T.-M., Yih, Y., and Kincaid, R. K., Using tabu search to determine the number of kanbans and lotsizes in a generic kanban system, Annals of Operations Research, vol.78,201-217, (1998).
18. Alabas, C., Altiparmak, F., and Dengiz, B., The Optimization of Number of Kanbans with Genetic Algorithms, Simulated Annealing and Tabu Search, Proceedings of the 2000 Congress on Evolutionary Computation, (2000).
19. Lee, I., A Comparison of Different Solution Approaches to Simultaneous Manufacturing Kanban Design and Scheduling, (2003). [Online]. Available: www.irma-international.org/chapter/ischools-promoting-information-science-and-technology-ist-domain-towards-
20. Lee, I., Evaluating artificial intelligence heuristics for a flexible Kanban system: Simultaneous Kanban controlling and scheduling, International Journal of Production Research, vol. 45, no. 13, 2859–2873, (2007). doi: 10.1080/00207540600806505.
21. Dengiz, B., Alabas-Uslu, C., and Dengiz, O., Optimization of manufacturing systems using a neural network metamodel with a new training approach, Journal of the Operational Research Society, vol. 60, no. 9, 1191–1197, (2009). doi: 10.1057/palgrave.jors.2602620.
22. Sivakumar, G. D. and Shahabudeen, P., Algorithms for the design of a multi-stage adaptive kanban system, International Journal of Production Research, vol. 47, no. 23, 6707–6738, (2009). doi: 10.1080/00207540802302071.
23. Chang, T. M. and Yih ,Y., Determining the number of kanbans and lotsizes in a generic kanban system: A simulated annealing approach, International Journal of Production Research, vol. 32, no. 8, 1991–2004, (1994). doi: 10.1080/00207549408957054.
24. Chang, T. M. and Yih, Y., A fuzzy rule-based approach for dynamic control of kanbans in a generic kanban system, International Journal of Production Research, vol. 36, no. 8, 2247–2257, (1998). doi: 10.1080/002075498192878.
25. Shahabudeen, P., Gopinath, R., and Krishnaiah, K., Design of bi-criteria kanban system using simulated annealing technique, Computers&Industrial Engineering, vol 41,355-370, (2002).
26. Shahabudeen, P., Krishnaiah, K., and Narayanan, M. T., Design of a Two-Card Dynamic Kanban System Using a Simulated Annealing Algorithm, The International Journal of Advanced Manufacturing Technology, vol.21, 754-759, (2003).
27. Ramanan, G. V. and Rajendran C., Scheduling in Kanban-Controlled Flowshops to Minimise the Makespan of Containers, The International Journal of Advanced Manufacturing Technology, vol.21, 348-354, (2003).
28. Shahabudeen, P. and Sivakumar, G. D., Algorithm for the design of single-stage adaptive kanban system, Computers&Industrial Engineering, vol. 54, no. 4, 800–820, (2008). doi: 10.1016/j.cie.2007.10.017.
29. Liang, H., Yuan, G., Feng, Q., Suzhou, T., and Delun, W., Design of a Multi-product Kanban System Based on Bottleneck Analysis. IEEE, (2010).
30. Widyadana, G. A., Wee, H. M., and Chang, J. Y., Determining the optimal number of Kanban in multi-products supply chain system, International Journal of Systems Science, vol. 41, no. 2, 189–201, (2010). doi: 10.1080/00207720903042996.
31. Wang, H., The electronic Kanban system for mixed-model assembly based on simulated annealing algorithm, Advanced Materials Research, 4355–4359, (2012). doi: 10.4028/www.scientific.net/AMR.403-408.4355.
32. Manavizadeh, N., Hosseini, N. S., Rabbani, M., and Jolai, F., A Simulated Annealing algorithm for a mixed model assembly U-line balancing type-I problem considering human efficiency and Just-In-Time approach, Computers & Industrial Engineering, vol. 64, no. 2, 669–685, (2013). doi: 10.1016/j.cie.2012.11.010.
33. Arani M., Dastmard, M., Momenitabar, M., and Liu, X., Unrelated Parallel Machine Scheduling Problem Subject to Inventory Limitations and Resource Constraints, Communications in Computer and Information Science, Springer Science and Business Media Deutschland GmbH, 238–254, (2021). doi: 10.1007/978-3-030-89743-7_13.
34. Chen, Z. and Sarker, B. R., Optimisation of multi-stage JIT production-pricing decision: Centralised and decentralised models and algorithms, International Journal Production Research, vol. 53, no. 20, pp. 6210–6230, (2015). doi: 10.1080/00207543.2015.1038369.
35. Becker, M. and Szczerbicka, H., Parameters Influencing the Performance of Ant Algorithms Applied to Optimisation of Buffer Size in Manufacturing, Industrial Engineering & Management Systems, (2005).
36. Krishnaiyer, K., Chen F. F., and Bouzary, H., Cloud Kanban Framework for Service Operations Management, Procedia Manufacturing, Elsevier B.V., 531–538. (2018).doi: 10.1016/j.promfg.2018.10.093.
37. Marialuisa, M., Matteo M, S., and Muhammad, S., Optimizing milk-run system and IT-based Kanban with artificial intelligence: an empirical study on multi-lines assembly shop floor, Production&Manufacturing Research, vol. 11, no. 1, (2023). doi: 10.1080/21693277.2023.2179123.
38. Aghajani, M., Keramati, A., and Javadi, B., Determination of number of kanban in a cellular manufacturing system with considering rework process, International Journal of Advanced Manufacturing Technology, vol. 63, no. 9–12,1177–1189, (2012). doi: 10.1007/s00170-012-3973-y.
39. Cao, Z. and Li, H., Multi-objective optimization of material collaborative delivery for mixed model automotive assembly process, 6th International Conference on Business Intelligence and Financial Engineering (BIFE), Institute of Electrical and Electronics Engineers Inc., 405–409, (2014). doi: 10.1109/BIFE.2013.85.
40. Aghajani, M., Keramati, A., Moghadam, R. T., and Mirjavadi, S. S., A mathematical programming model for cellular manufacturing system controlled by kanban with rework consideration, International Journal of Advanced Manufacturing Technology, vol. 83, no. 5–8, pp. 1377–1394, (2016). doi: 10.1007/s00170-015-7635-8.
41. Simić, D., Svirčević, V., Corchado, E., Calvo-Rolle, J. L., Simić, S. D., and Simić, S., Modelling material flow using the Milk run and Kanban systems in the automotive industry, Expert Systems, Blackwell Publishing Ltd, (2021). doi: 10.1111/exsy.12546.
42. Castro, R. F., Godinho-Filho, M., and Tavares-Neto, R. F., Dispatching method based on particle swarm optimization for make-to-availability, Journal Intelligent Manufacturing, vol. 33, no. 4, 1021–1030, (2022). doi: 10.1007/s10845-020-01707-6.
43. Elloumi, K., Ammar, A., and Benaissa, M., Particle swarm optimization algorithm for design of an adaptive Kanban system based on optimization via simulation, Journal of Industrial and Production Engineering, (2025). doi: 10.1080/21681015.2025.2474082.