Skip to content Skip to main navigation Report an accessibility issue

A Learning-based Optimization Framework for Production Planning and Scheduling

Dr. Zhongshun “Tony” Shi
Research Associate
Industrial & Systems Engineering
The University of Tennessee
Friday, February 7, 2020
2:30-3:30 pm   Tickle 410


Today’s manufacturing encounters more customization, higher standard and shorter response time from the market and customers. Automation and digitalization provide a big improvement of operations level, but also significantly increase the difficulties and challenges of the real-time decision of daily operations. As such, traditional optimization approaches based on limited data information and simplified models, are struggling in providing the efficient real-time decision support. This talk focuses on the production planning and scheduling problems in modern manufacturing operations. A learning-based optimization framework is proposed to enhance the real-time decision-making for daily operations by utilizing the digital twin production systems and industrial big data. In this framework, we develop a novel deep programming method, as a plug-in optimization solver, to automatically generating the efficient real-time optimization algorithms via an off-line learning manner. Convergence analysis and computational budget allocation issues are discussed. Numerical results show the superiority of the proposed framework and its potential to enable the intelligent decision-making technology for the modern manufacturing operations management.



Dr. Zhongshun Shi is currently a Research Associate at the University of Tennessee Space Institute and will be an Assistant Professor in the Department of Industrial and Systems Engineering at the University of Tennessee starting on August 1, 2020. Prior to joining UT in 2019, he was a Research Associate in the Department of Industrial and Systems Engineering at the University of Wisconsin-Madison from 2017 to 2019. He received the B.S. degree in Applied Mathematics from China University of Geosciences, Beijing, in 2011, and the Ph.D. degree in Management Science and Engineering from Peking University, China, in 2017. His papers have been published in journals such as Automatica, IEEE Transactions on Automatic Control, Naval Research Logistics, IEEE Transactions on Automation Science and Engineering, and International Journal of Production Research. His research interests include complex systems optimization, discrete optimization, approximation algorithm, simulation optimization, artificial intelligence and their applications in smart manufacturing, planning and scheduling, agriculture, logistics and supply chain management.