-
[ December 14, 2018]
Data-Driven Control of a Production System by Using Marking-Dependent Threshold Policy
-
- Speaker:
- Baris Tan
- Date:
- Dec. 14, 2018
- Time:
- 10:00am
- Location:
- Room 805, Wangkezhen Building
- Host:
- Leyuan Shi
- Abstract
-
This study is motivated by the need of developing effective data-driven control methods for production systems. Our aim is answering the following research questions: How can we control production by using partial information (markings) obtained from a production system?; How can the control parameters be determined by using the real-time data? How well does the data-driven control policy perform?; and How can the markings be selected for a given system?
In order to analyze the performance of a production system controlled with partial information, we introduce the Marked Markov Arrival Process (MMAP) framework to model a system that generates different signals, referred as markings, based on the system status. We then propose a marking-dependent threshold policy to control the system. An analytical method that is based on a matrix analytical approach is developed to analyze a production/inventory system with MMAP information and demand arrivals and a partially observable production time process modeled as a MMAP. A mathematical programming formulation is used to determine the optimal thresholds of the control policy based on the matrix geometric model of the system. We then present a joint simulation and optimization (JSO) approach to determine the parameters of the threshold policy by using the shop-floor data collected from the system.
We test these methods on two production systems.
We show that using a marking-dependent control policy together with a JSO approach that determines the policy parameters works effectively as a data-driven control method for manufacturing.
- Biography
-
Baris Tan is a Professor of Operations Management and Industrial Engineering and the Vice President for Academic Affairs and at Koç University, Istanbul, Turkey.
His areas of expertise are in design and control of production systems, supply chain management, and stochastic modelling. He is the author of many publications including two edited books and serves as the manufacturing area editor of Flexible Services and Manufacturing Journal and Design and Manufacturing area editor of IISE Transactions.
Barış Tan is the recipient of Turkish Academy of Sciences Distinguished Young Scholar Award, TUBITAK fellowship, NATO Science Fellowship, the Rockefeller Foundation Residency Award at Bellagio Center, and best paper awards for his publications.
He received a BS degree in Electrical 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. He previously served as the Dean of College of Administrative Sciences and Economics and the Director of the Graduate School of Business. He held visiting positions at Harvard University Division of Engineering and Applied Sciences, MIT Operations Research Center, MIT Laboratory for Manufacturing and Productivity, University of Cambridge Judge Business School, and University College London School of Management.
Professor Tan is a member of the international advisory boards of EM Lyon (France) and Nottingham Business School (UK), the chairman of the ISM University of Management and Economics Senate (Lithuania), a member of the European Foundation for Management Development EQUIS Awarding Body, and independent board member of Anadolu Efes. He served on the boards of CEMS Global Alliance in Management Education, European Foundation for Management Development, Turkish Quality Association, and Turkish Operations Research Society, and on the Education and Research Industry Strategy Council of Oracle and Research Analytics Advisory Board of Thomson Reuters.