A machine learning approach for implementing data-driven production control policies

ABSTRACT

Given the extensive data being collected in manufacturing systems, there is a need for developing a systematic method to implement data-driven production control policies. For an effective implementation, first, the relevant information sources must be selected. Then, a control policy that uses the real-time signals collected from these sources must be implemented. We analyse the production control policy implementation problem in three levels: choosing the information sources, forming clusters of information signals to be used by the policy and determining the optimal policy parameters. Due to the search-space size, a machine-learning-based framework is proposed. Using machine learning speeds up optimisation and allows utilising the collected data with simulation. Through two experiments, we show the effectiveness of this approach. In the first experiment, the problem of selecting the right machines and buffers for controlling the release of materials in a production/inventory system is considered. In the second experiment, the best dispatching policy based on the selected information sources is identified. We show that selecting the right information sources and controlling a production system based on the real-time signals from the selected sources with the right policy improve the system performance significantly. Furthermore, the proposed machine learning framework facilitates this task effectively.

Keywords:

• Production control
• stochastic models
• machine learning
• real-time control
• discrete event simulation

Acknowledgments

Research leading to these results has received funding from the EU ECSEL Joint Undertaking under grant agreement no. 737459 (project Productive4.0) and from TUBITAK (217M145).

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by Electronic Components and Systems for European Leadership [737459 (project Productive4.0)] and Scientific and Technological Research Council of Turkey [27M145].

Notes on contributors

Siamak Khayyati

Siamak Khayyati is Postdoctoral Fellow at Koç University. He received a BS degree in Industrial Engineering from Sharif University of Technology and PhD degree in Industrial Engineering and Operations Management from Koç University. His research interests are in design and control of production systems and artificial intelligence applications in manufacturing.

Barış Tan

Barış Tan is Professor of Operations Management and Industrial Engineering at Koç University, Istanbul, Turkey. His areas of expertise are in design and control of production systems, supply chain management, and stochastic modelling. He received a BS degree in Electrical&Electronics Engineering from Bogazici University, and ME in Industrial and Systems Engineering, MSE in Manufacturing Systems, and PhD in Operations Research from the University of Florida.