APPLICATION OF ONLINE LEARNING FOR THE DYNAMIC CONFIGURATION OF KANBAN SYSTEMS

Kanban systems constitute a widely used pull control for inventory management in production systems. As a result of an increasingly volatile and individualized customer demand, Kanban systems have to be reconfigured dynamically to achieve minimal inventory levels while maintaining a stable production. This paper investigates the application of an incremental online learning platform called XELOPRO to optimize inventory levels using the current state of the production system, while including contextual information, e.g., time-related information. As the platform uses an incremental support vector machine to update its models during runtime without the need to store and reevaluate large amounts of historical data, it constitutes a suitable tool for a decentralized inventory management. Results show a good performance with drastic decreases in inventory levels compared to static configurations and a higher reliability compared to a dynamic application of standard Kanban rules.

[1]  H. Bungartz,et al.  Sparse grids , 2004, Acta Numerica.

[2]  Osamu Kimura,et al.  Desiǵn and analysis of Pull System, a method of multi-staǵe production control , 1981 .

[3]  P. Shahabudeen,et al.  Design of Multi-stage Adaptive Kanban System using Simulated Annealing algorithm , 2009, Int. J. Manuf. Res..

[4]  Roger Fletcher,et al.  Practical methods of optimization; (2nd ed.) , 1987 .

[5]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[6]  Zhiping Wang,et al.  The Study and Development of E-kanban Management in MES for Hardware Plastics Production Workshop , 2015, ICIS 2015.

[7]  Takeshi Yoshikawa,et al.  Adaptive Kanban control systems for two-stage production lines , 2010, Int. J. Manuf. Technol. Manag..

[8]  Loren Paul Rees,et al.  Dynamically Adjusting the Number of Kanbans in a Just-in-Time Production System Using Estimated Values of Leadtime , 1987 .

[9]  P. Shahabudeen,et al.  Design of a Two-Card Dynamic Kanban System Using a Simulated Annealing Algorithm , 2003 .

[10]  Lean Production Development in SMEs: A Case Study , 2017 .

[11]  D. Shepherd,et al.  Advanced manufacturing technology , 2000 .

[12]  Valerie Tardif,et al.  An adaptive approach to controlling kanban systems , 2001, Eur. J. Oper. Res..

[13]  Andre Thomas,et al.  The relevance study of adaptive kanban in a multicriteria constraints context using data-driven simulation method , 2013, Proceedings of 2013 International Conference on Industrial Engineering and Systems Management (IESM).

[14]  David L. Woodruff,et al.  CONWIP: a pull alternative to kanban , 1990 .

[15]  Samir Lamouri,et al.  The ConWip production control system: a systematic review and classification , 2018 .

[16]  P. Shahabudeen,et al.  Design of multi-stage adaptive kanban system , 2008 .

[17]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[18]  Henri Pierreval,et al.  Using genetic programming and simulation to learn how to dynamically adapt the number of cards in reactive pull systems , 2015, Expert Syst. Appl..

[19]  Jose M. Framinan,et al.  Dynamic card controlling in a Conwip system , 2006 .

[20]  Surendra M. Gupta,et al.  An adaptive CONWIP mechanism for hybrid production systems , 2014 .

[21]  Surendra M. Gupta,et al.  An algorithm to dynamically adjust the number of Kanbans in stochastic processing times and variable demand environment , 1997 .