AI-Based Real-Time Site-Wide Optimization for Process Manufacturing
Jayant Kalagnanam (),
Dzung T. Phan (),
Pavankumar Murali (),
Lam M. Nguyen (),
Nianjun Zhou (),
Dharmashankar Subramanian (),
Raju Pavuluri (),
Xiang Ma (),
Crystal Lui () and
Giovane Cesar da Silva ()
Additional contact information
Jayant Kalagnanam: IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598
Dzung T. Phan: IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598
Pavankumar Murali: IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598
Lam M. Nguyen: IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598
Nianjun Zhou: IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598
Dharmashankar Subramanian: IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598
Raju Pavuluri: IBM Thomas J. Watson Research Center, Yorktown Heights, New York 10598
Xiang Ma: IBM Global Business Services, Calgary, Alberta T2R1R9, Canada
Crystal Lui: IBM Global Business Services, Calgary, Alberta T2R1R9, Canada
Giovane Cesar da Silva: IBM Global Business Services, Calgary, Alberta T2R1R9, Canada
Interfaces, 2022, vol. 52, issue 4, 363-378
Abstract:
In this paper, we propose a site-wide lead advisor, which is an artificial intelligence–based prediction and set-point recommendation engine, by combining the use of machine learning with optimization techniques. It provides operational set-point recommendations to continuously improve site-wide operations for throughput measured in additional barrels of oil produced per day. A key contribution and differentiator is the utilization of sensor data to continuously learn the behavior of all the subsystems of an oil-producing plant and use this within an optimization framework to provide advisory control in near real time. This is novel in that it does not require a model of the plant to be provided as input. The predictive model is learned automatically and continuously from data. This work required the development of a new prediction-optimization modeling framework that optimizes throughput while staying in the vicinity of the historical process behavior and employing the model’s structure in designing algorithms to solve it. This solution has been deployed at Suncor Energy, an oil-sands company, since January 2019 and is estimated to generate business value in the order of tens of millions of dollars per year. The generalized approach of this framework lends it the ability to be applied to any processing or manufacturing plant.
Keywords: Industry 4.0; process manufacturing; real-time prediction-optimization; machine learning; deep learning; mixed-integer linear program; primal-dual algorithm (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)
Downloads: (external link)
http://dx.doi.org/10.1287/inte.2022.1121 (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:inm:orinte:v:52:y:2022:i:4:p:363-378
Access Statistics for this article
More articles in Interfaces from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().