About Us
Grad Studies
Jump To Topic...
Theme Topic
Optimization and Control of Batch Process Systems using Data-Driven Models

Data-driven models provide a useful alternative for the control of complex systems where computation time and numerical solution robustness pose challenges to the use of detailed first-principles models. In this research, we are exploring and analyzing different types of data-driven models for the optimization and control of complex industrial processes such as electric arc furnace operation in the steel industry.

Dr. Chris L. E. Swartz
Professor and Director, MACC
Dr. Prashant Mhaskar
Professor and Canada Research Chair in Nonlinear and Fault-Tolerant Control
Dr. Abhinav Garg
Postdoctoral Fellow
Mudassir Rashid
Ph.D. recipient
Model predictive control of uni-axial rotational molding process
Garg, A., Felipe P.C. Gomes, Mhaskar, P., Micheal R. Thompson
Computers & Chemical Engineering, 121 306-316 (2019)  -  [ Publisher Version ]
Data-Driven Advanced in Manufacturing for Batch Polymer Processing Using Multivariate Nondestructive Monitoring
Felipe P.C. Gomes, Garg, A.Mhaskar, P., Michael R. Thompson
Industrial and Engineering Chemistry Research, 23 (58) 9940-9951 (2019)  -  [ Publisher Version ]
Modeling and Control of Batch Processes: Theory and Applications
Springer International Publishing (2019)  -  [ Publisher Version ]
Utilizing Big Data for Batch Process Modeling and Control
Computers and Chemical Engineering (2018)  -  [ Publisher Version ]
Handling multi‐rate and missing data in variable duration economic model predictive control of batch processes
AIChE Journal, 63 (7) 2705-2718 (2017)  -  [ Publisher Version ]
Subspace identification and predictive control of batch particulate processes
American Control Conference, 505-510 (2017)  -  [ Publisher Version ]
Handling multi-rate and missing data in system identification
American Control Conference, 839-844 (2017)  -  [ Publisher Version ]
Development of a high fidelity and subspace identification model of a hydrogen plant startup dynamics
Garg, A.Corbett, B.Mhaskar, P., Hu, G., Flores-Cerrillo, J.
American Control Conference, 2857-2862 (2017)  -  [ Publisher Version ]
Subspace-based model identification of a hydrogen plant startup dynamics
Garg, A.Corbett, B.Mhaskar, P., Hu, G., Flores-Cerrillo, J.
Computers & Chemical Engineering, 106 183-190 (2017)  -  [ Publisher Version ]
Subspace Identification-Based Modeling and Control of Batch Particulate Processes
Industrial & Engineering Chemistry Research, 56 (26) 7491-7502 (2017)  -  [ Publisher Version ]