The interdisciplinary doctoral program in Computational Science and Engineering ( PhD in CSE + Engineering or Science ) offers students the opportunity to specialize at the doctoral level in a computation-related field of their choice via computationally-oriented coursework and a doctoral thesis with a disciplinary focus related to one of eight participating host departments, namely, Aeronautics and Astronautics; Chemical Engineering; Civil and Environmental Engineering; Earth, Atmospheric and Planetary Sciences; Materials Science and Engineering; Mathematics; Mechanical Engineering; or Nuclear Science and Engineering.
Doctoral thesis fields associated with each department are as follows:
As with the standalone CSE PhD program, the emphasis of thesis research activities is the development of new computational methods and/or the innovative application of state-of-the-art computational techniques to important problems in engineering and science. In contrast to the standalone PhD program, however, this research is expected to have a strong disciplinary component of interest to the host department.
The interdisciplinary CSE PhD program is administered jointly by CCSE and the host departments. Students must submit an application to the CSE PhD program, indicating the department in which they wish to be hosted. To gain admission, CSE program applicants must receive approval from both the host department graduate admission committee and the CSE graduate admission committee. See the website for more information about the application process, requirements, and relevant deadlines .
Once admitted, doctoral degree candidates are expected to complete the host department's degree requirements (including qualifying exam) with some deviations relating to coursework, thesis committee composition, and thesis submission that are specific to the CSE program and are discussed in more detail on the CSE website . The most notable coursework requirement associated with this CSE degree is a course of study comprising five graduate subjects in CSE (below).
Architecting and Engineering Software Systems | 12 | |
Atomistic Modeling and Simulation of Materials and Structures | 12 | |
Topology Optimization of Structures | 12 | |
Computational Methods for Flow in Porous Media | 12 | |
Introduction to Finite Element Methods | 12 | |
Artificial Intelligence and Machine Learning for Engineering Design | 12 | |
Learning Machines | 12 | |
Numerical Fluid Mechanics | 12 | |
Atomistic Computer Modeling of Materials | 12 | |
Computational Structural Design and Optimization | ||
Introduction to Mathematical Programming | 12 | |
Nonlinear Optimization | 12 | |
Algebraic Techniques and Semidefinite Optimization | 12 | |
Introduction to Modeling and Simulation | 12 | |
Algorithms for Inference | 12 | |
Bayesian Modeling and Inference | 12 | |
Machine Learning | 12 | |
Dynamic Programming and Reinforcement Learning | 12 | |
Advances in Computer Vision | 12 | |
Shape Analysis | 12 | |
Modeling with Machine Learning: from Algorithms to Applications | 6 | |
Statistical Learning Theory and Applications | 12 | |
Computational Cognitive Science | 12 | |
Systems Engineering | 9 | |
Modern Control Design | 9 | |
Process Data Analytics | 12 | |
Mixed-integer and Nonconvex Optimization | 12 | |
Computational Chemistry | 12 | |
Data and Models | 12 | |
Computational Geophysical Modeling | 12 | |
Classical Mechanics: A Computational Approach | 12 | |
Computational Data Analysis | 12 | |
Data Analysis in Physical Oceanography | 12 | |
Computational Ocean Modeling | 12 | |
Discrete Probability and Stochastic Processes | 12 | |
Statistical Machine Learning and Data Science | 12 | |
Integer Optimization | 12 | |
The Theory of Operations Management | 12 | |
Optimization Methods | 12 | |
Flight Vehicle Aerodynamics | 12 | |
Computational Mechanics of Materials | 12 | |
Principles of Autonomy and Decision Making | 12 | |
Multidisciplinary Design Optimization | 12 | |
Numerical Methods for Partial Differential Equations | 12 | |
Advanced Topics in Numerical Methods for Partial Differential Equations | 12 | |
Numerical Methods for Stochastic Modeling and Inference | 12 | |
Introduction to Numerical Methods | 12 | |
Fast Methods for Partial Differential and Integral Equations | 12 | |
Parallel Computing and Scientific Machine Learning | 12 | |
Eigenvalues of Random Matrices | 12 | |
Mathematical Methods in Nanophotonics | 12 | |
Quantum Computation | 12 | |
Essential Numerical Methods | 6 | |
Nuclear Reactor Analysis II | 12 | |
Nuclear Reactor Physics III | 12 | |
Applied Computational Fluid Dynamics and Heat Transfer | 12 | |
Experiential Learning in Computational Science and Engineering | ||
Statistics, Computation and Applications | 12 |
Note: Students may not use more than 12 units of credit from a "meets with undergraduate" subject to fulfill the CSE curriculum requirements
, , or . | |
for more information. | |
or as a CSE concentration subject, but not both. | |
Print this page.
The PDF includes all information on this page and its related tabs. Subject (course) information includes any changes approved for the current academic year.
Research area:
Associate Professor
Seth Bonder Collegiate Professor
Assistant Professor
Ph.D. Student
Professor of Practice
Ralph L. Disney Professor, Director of Masters Programs
Arthur F. Thurnau Professor
Clyde W. Johnson Collegiate Professor Emeritus
Stephen M. Pollock Collegiate Professor of Industrial and Operations Engineering
Professor, Associate Chair of Graduate Education
PhD Student
Teaching Professor
PhD Candidate
The Ohio State University
We develop new learning-based theory and algorithms for optimization and control of complex systems under uncertainty, with applications in next-generation biochemical systems.
Our research focuses on improving the quality, efficiency, and sustainability of engineered products and processes through the development of advanced decision-making strategies in the presence of uncertainty.
Professor Paulson specializes in formulating these strategies in terms of stochastic mathematical optimization problems that can be applied to a broad range of applications, with a particular emphasis on chemical and biological systems, as well as developing algorithms that can efficiently solve these problems.
Joel Paulson received his PhD in 2016 from the Massachusetts Institute of Technology (MIT), where he won an NSF Graduate Research Fellowship and multiple awards for research and outstanding teaching and mentoring.
His advisors were Professors Richard Braatz and Michael Strano. After completing his PhD, Dr. Paulson held a postdoctoral research position in Professor Ali Mesbah's group at the University of California, Berkeley.
While at UC Berkeley, he was a finalist for the 2017 International Federation of Automatic Control (IFAC) Conference Best Paper Award.
Professor Paulson has published several book chapters and over a dozen articles in such peer-reviewed journals as ACS Nano , Journal of Physical Chemistry Letters , Organic Process Research & Development , Journal of Process Control , and International Journal of Robust and Nonlinear Control .
University of Texas at Austin :
FAST UNCERTAINTY PROPAGATION AND PARAMETER ESTIMATION IN COMPUTATIONALLY INTENSIVE GENOME-SCALE BIOLOGICAL MODELS USING MACHINE LEARNING
i. Construction and validation of mathematical models is biological systems involving genome-scale molecular networks is a very challenging problem. The task of uncertainty quantification (UQ) represents: (i) calibrating the model with experimental data and (ii) propagating uncertainties through the model to characterize the quality of the model predictions. Although many methods for UQ have been developed, the majority of them are intractable on experiment-to-evaluate computational models. I developed a novel metamodeling approach that can vastly accelerate UQ methods for dynamic genome-scale biological system models in the presence of high-throughput experimental data.
i. Modeling is known to have a big impact on process understanding and optimization; however, unless the accuracy of the model is rigorously understood, then the impact of the model is limited. Thus, the developed method helps to answer this question of accuracy. In particular, most process models are functions of several unknown parameters (such as heat transfer coefficients or rate constants) that must be estimated from data. Once this has been done using the proposed approach, we can easily decide if more experiments are required or even which experiments to perform in the future to gain a better understanding of the process.
ii. We applied the method to infer extracellular kinetic parameters in a batch fermentation reactor consisting of diauxic growth on E. coli on a glucose/xylose mixed media. To the best of our knowledge, due to the complexity of the model, this problem had been unable to be solved in the literature using standard methods. Our novel metamodel enabled this problem to be solved a factor of more than 800 times faster and provided significant physical insights that had previously been unknown (such as the reported data set was insufficient for uniquely estimating all parameters).
Back to top
Current members.
Name | Position | Current |
---|---|---|
Joe Flory | 2021-2023, M.S. | Ph.D. student at University of Wisconsin |
Utkarsh Shah | 2019-2022, Ph.D. (co-advised) | |
Naitik Alkesh Choksi | 2019-2021, M.S. | Pactiv Evergreen Inc. |
Faheem Manzoor | 2022-2023 Visiting Scholar |
2024/04/11 - Lowrie Banquet
2023/09/30 - West Fest
2023/09/03 - BBQ at Dr. Paulson's house
2023/05/06 - Hiking with Bakshi's group @ Cuyahoga Valley Natl Park
2023/03/23 - Lowrie Banquet
July 31, 2024 Collaborating to solve complex sustainability challenges: Paulson, Zhai, and Fan
July 1, 2024 Joel Paulson featured in Chemical Engineering Progress (CEP)
April 18, 2024 Graduate students recognized for teaching and organizational leadership
October 2, 2023 Jain, Paulson honored as trailblazers in AIChE's "35 Under 35"
January 17, 2023 Joel Paulson receives prestigious NSF CAREER Award
May 3, 2022 College celebrates 2022 Distinguished Faculty Award honorees
September 23, 2020 NSF funds additional cutting-edge projects led by Bhavik Bakshi
September 17, 2020 Chemical engineering department wins two high-profile NSF grants in same day
3. E. Harinath, L.C. Foguth, J.A. Paulson, and R.D. Braatz. Model predictive control of polynomial systems. In Handbook of Model Predictive Control , edited by Saša V. Raković and William S. Levine, Birkhäuser, 221-237, 2019.
2. J.A. Paulson, E. Harinath, L.C. Foguth, and R.D. Braatz, Control and systems theory for advanced manufacturing. In Emerging Applications of Control and Systems Theory , edited by R. Tempo, S. Yurkovich, P. Misra, Springer, 63-79, 2018.
1. J.A. Paulson, S. Streif, R. Findeisen, R.D. Braatz, and A. Mesbah. Fast stochastic model predictive control of end-to-end continuous pharmaceutical manufacturing. In Process Systems Engineering for Pharmaceutical Manufacturing , edited by Ravendra Singh and Zhihong Yuan, Elsevier, Amsterdam, Netherlands, Chapter 14, pages 353-378, 2018.
19. A.D. Bonzanini, J.A. Paulson , G. Makrygiorgos, and A. Mesbah. Fast approximate learning-based multistage nonlinear model predictive control using Gaussian processes and deep neural networks. Computers & Chemical Engineering (accepted).
18. A. Mesbah, J.A. Paulson , and R.D. Braatz. An internal model control design method for failure- tolerant control with multiple objectives. Computers & Chemical Engineering , 4:106955, 2020.
17. J.A. Paulson and A. Mesbah. Optimal Bayesian experiment design for nonlinear dynamic systems with chance constraints. Submitted to Journal of Process Control.
16. A. Mesbah, J.A. Paulson , and R. D. Braatz. An internal model control design method for multi-objective failure-tolerant control. Submitted to Journal of Process Control .
15. J.A. Paulson , L. C. Foguth, Y. Peng, A. Mesbah, and R. D. Braatz. Optimization methods for fast model predictive control. Submitted to Control Systems Magazine .
14. J.A. Paulson , T. L. M Santos, and A. Mesbah. Mixed stochastic-deterministic tube MPC for offset-free tracking in the presence of plant-model mismatch. Journal of Process Contro l, 2018 (in press).
13. T. A. N. Heirung, J.A. Paulson , S. Lee, and A. Mesbah. Model predictive control with active learning under model uncertainty: when, why, and how? AIChE Journa l, 64:3071–3081, 2018.
12. D. Gidon, B. Curtis, J.A. Paulson , D. B. Graves, and A. Mesbah. Model-based feedback control of a kHz-excited atmospheric pressure plasma jet. IEEE Transactions on Radiation and Plasma Medical Sciences , 2:129–137, 2018.
11. T. A. N. Heirung, J.A. Paulson , J. O’Leary, and A. Mesbah. Stochastic model predictive control-how does it work? Computers & Chemical Engineering , 114:158–170, 2018.
10. J.A. Paulson and A. Mesbah. An efficient method for stochastic optimal control with joint chance constraints for nonlinear systems. International Journal of Robust and Nonlinear Control , 2017.
9. A. Mesbah, J.A. Paulson , R. Lakerveld, and R. D. Braatz. Model predictive control of an integrated continuous pharmaceutical manufacturing pilot plant. Organic Process Research & Development , 21:844–854, 2017.
8. J.A. Paulson , M. Martin-Casas, and A. Mesbah. Input design for online fault diagnosis of nonlinear systems with stochastic uncertainty. Industrial & Engineering Chemistry Research , 56:9593–9605, 2017.
7. J.A. Paulson , E. A. Buehler, R. D. Braatz, and A. Mesbah. Stochastic model predictive control with joint chance constraints. International Journal of Control , 1–14, 2017.
6. D. O. Bellisario, J.A. Paulson , R. D. Braatz, and M. S. Strano. An analytic solution for exciton generation, reaction, and diffusion in nanotube and nanowire-based solar cells. The Journal of Physical Chemistry Letters , 7:2683–2688, 2016.
5. M. Wang and J.A. Paulson . An adaptive model predictive control strategy for nonlinear distributed parameter systems using the Type-2 Takagai-Sugeno model. International Journal of Fuzzy System s, 18:792–805, 2015.
4. B. Jiang, X. Zhu, D. Huang, J.A. Paulson , and R. D. Braatz. A combined canonical variate analysis and fisher discriminant analysis (CVA–FDA) approach for fault diagnosis. Computers & Chemical Engineering , 77:1–9, 2015.
3. Y. Son, Q. H. Wang, J.A. Paulson , C. Shih, K. Tvrdy, B. AlFeeli, R. D. Braatz, M. S. Strano. Layer number dependence of MoS2 photoconductivity using photocurrent spectral atomic force microscope imaging. ACS Nano , 9:2843–2855, 2015.
2. J.A. Paulson , A. Mesbah, X. Zhu, M. Molaro, and R. D. Braatz. Control of self-assembly in micro- and nano-scale systems. Journal of Process Control , 27:38–49, 2015.
1. D. A. Slanac, A. Lie, J.A. Paulson , K. J. Stevenson, and K. P. Johnston. Bifunctional catalyst for alkaline ORR via promotion of ligand and ensemble effects at Ag/MnOx nanodomains. The Journal of Physical Chemistry C , 116:11032–11039, 2012
Peer Reviewed Proceedings Publications
21. J.A. Paulson , T. A. N. Heirung, and A. Mesbah. Tube-based robust nonlinear model predictive control with guaranteed fault tolerance. Submitted to Proc. of ACC .
20. J.A. Paulson and A. Mesbah. Arbitrary polynomial chaos for quantification of general probabilistic uncertainties: Shaping closed-loop behavior of nonlinear systems. In Proc. of the IEEE Conference on Decision and Control , 2018 (accepted).
19. J.A. Paulson and A. Mesbah. Nonlinear model predictive control with explicit backoffs for stochastic systems under arbitrary uncertainty. In Proc. of the IFAC Conference on Nonlinear Model Predictive Control , pages 622–633, Madison, WI, August 2018.
18. T. L. M. Santos, J.A. Paulson , and A. Mesbah. Offset-free stochastic model predictive control with enlarged feasibility region. In Proc. of the American Control Conference , pages 742–748, Milwaukee, WI June 2018.
17. J.A. Paulson , T. A. N. Heirung, R. D. Braatz, and A. Mesbah. Closed-loop active fault diagnosis for stochastic linear systems. In Proc. of the American Control Conference , pages 735–741, Milwaukee, WI June 2018.
16. J.A. Paulson , E. Buehler, and A. Mesbah. Arbitrary polynomial chaos for uncertainty propagation of correlated random variables in dynamic systems. In Proc. of the IFAC World Congress , pages 3607–3612, Toulouse, France, July 2017.
15. J.A. Paulson , L. Xie, and A. Mesbah. Offset-free robust MPC of systems with mixed stochastic and deterministic uncertainty. In Proc. of the IFAC World Congress , pages 3589–3594, Toulouse, France, July 2017.
14. S. Lucia, J.A. Paulson , R. Findeisen, and R. D. Braatz. On stability of stochastic linear systems via polynomial chaos expansions. In Proc. of the American Control Conference , pages 5089–5094, Seattle, WA, May 2017.
13. E. Harinath, L. C. Foguth, J.A. Paulson , and R. D. Braatz. Nonlinear model predictive control using polynomial optimization methods. In Proc. of the American Control Conference , pages 1–6, Boston, MA, July 2016.
12. E. Buehler, J.A. Paulson , and A. Mesbah. Lyapunov-based stochastic nonlinear model predictive control: Shaping the state probability density functions. In Proc. of the American Control Conference , pages 5389–5394, Boston, MA, July 2016.
11. A. E. Lu, J.A. Paulson , and R. D. Braatz. pH and conductivity control in an integrated biomanufacturing plant. In Proc. of the American Control Conference , pages 1741–1746, Boston, MA, July 2016.
10. T. Muehlpfordt, J.A. Paulson , R. Findeisen, and R. D. Braatz. Output feedback model predictive control with probabilistic uncertainties for linear systems. In Proc. of the American Control Conference , pages 2035–2040, Boston, MA, July 2016.
9. J.A. Paulson , M. C. Molaro, D. O. Bellisario, M. S. Strano, and R. D. Braatz. Mathematical modeling and analysis of carbon nanotube photovoltaic systems. In Proc. of the 11th IFAC Symposium on Dynamics and Control Process Systems , pages 442–447, Trondheim, Norway, June 2016.
8. J.A. Paulson , E. Harinath, L. C. Foguth, and R. D. Braatz. Nonlinear model predictive control of systems with probabilistic time-invariant uncertainties. In Proc. of the 5th IFAC Conference on Nonlinear Model Predictive Control , pages 16–25, Seville, Spain, September 2015.
7. A. E. Lu, J.A. Paulson (co-first author), N. J. Mozdzierz, A. Stockdale, A. N. Ford Versypt, K. R. Love, J. C. Love, and R. D. Braatz. Control systems technology in the advanced manufacturing of biologic drugs. In Proc. of the 2015 IEEE Conference on Control Applications , pages 1505–1515, Sydney, Australia, September 2015.
6. L. C. Foguth, J.A. Paulson , R. D. Braatz, and D. M. Raimondo. Fast robust model predictive control of high-dimensional systems. In Proc. of the European Control Conference , pages 2009–2014, Linz, Austria, July 2015.
5. M. Torchio, N. A. Wolff, D. M. Raimondo, L. Magni, U. Krewer, B. Gopaluni, J.A. Paulson , and R. D. Braatz. Real-time model predictive control for the optimal charging of a Lithium-ion battery. In Proc. of the American Control Conference , pages 4536–4541, Chicago, IL, July 2015.
4. A. Mesbah, J.A. Paulson , R. Lakerveld, and R. D. Braatz. Plant-wide model predictive control for a continuous pharmaceutical process. In Proc. of the American Control Conference , pages 4301–4307, Chicago, IL, July 2015.
3. J.A. Paulson , S. Streif, and A. Mesbah. Stability for receding-horizon stochastic model predictive control with chance constraints. In Proc. of the American Control Conference , pages 937–943 Chicago, IL, July 2015.
2. J.A. Paulson , A. Mesbah, S. Streif, R. Findeisen, and R. D. Braatz. Fast stochastic model predictive control of high-dimensional systems. In Proc. of the 53rd IEEE Conference on Decision and Control , pages 2802–2809, Los Angeles, CA, December 2014.
1. J.A. Paulson , D. M. Raimondo, R. Findeisen, R. D. Braatz, and S. Streif. Guaranteed active fault diagnosis for uncertain nonlinear systems. In Proc. of the European Control Conference , pages 926–931, Strasbourg, France, June 2014.
21. J.A. Paulson, T. A. N. Heirung, and A. Mesbah. Tube-based robust nonlinear model predictive control with guaranteed fault tolerance. Submitted to Proc. of ACC.
20. J.A. Paulson and A. Mesbah. Arbitrary polynomial chaos for quantification of general probabilistic uncertainties: Shaping closed-loop behavior of nonlinear systems. In Proc. of the IEEE Conference on Decision and Control, 2018 (accepted).
19. J.A. Paulson and A. Mesbah. Nonlinear model predictive control with explicit backoffs for stochastic systems under arbitrary uncertainty. In Proc. of the IFAC Conference on Nonlinear Model Predictive Control, pages 622–633, Madison, WI, August 2018.
18. T. L. M. Santos, J.A. Paulson, and A. Mesbah. Offset-free stochastic model predictive control with enlarged feasibility region. In Proc. of the American Control Conference, pages 742–748, Milwaukee, WI June 2018.
17. J.A. Paulson, T. A. N. Heirung, R. D. Braatz, and A. Mesbah. Closed-loop active fault diagnosis for stochastic linear systems. In Proc. of the American Control Conference, pages 735–741, Milwaukee, WI June 2018.
16. J.A. Paulson, E. Buehler, and A. Mesbah. Arbitrary polynomial chaos for uncertainty propagation of correlated random variables in dynamic systems. In Proc. of the IFAC World Congress, pages 3607–3612, Toulouse, France, July 2017.
15. J.A. Paulson, L. Xie, and A. Mesbah. Offset-free robust MPC of systems with mixed stochastic and deterministic uncertainty. In Proc. of the IFAC World Congress, pages 3589–3594, Toulouse, France, July 2017.
14. S. Lucia, J.A. Paulson, R. Findeisen, and R. D. Braatz. On stability of stochastic linear systems via polynomial chaos expansions. In Proc. of the American Control Conference, pages 5089–5094, Seattle, WA, May 2017.
13. E. Harinath, L. C. Foguth, J.A. Paulson, and R. D. Braatz. Nonlinear model predictive control using polynomial optimization methods. In Proc. of the American Control Conference, pages 1–6, Boston, MA, July 2016.
12. E. Buehler, J.A. Paulson, and A. Mesbah. Lyapunov-based stochastic nonlinear model predictive control: Shaping the state probability density functions. In Proc. of the American Control Conference, pages 5389–5394, Boston, MA, July 2016.
11. A. E. Lu, J.A. Paulson, and R. D. Braatz. pH and conductivity control in an integrated biomanufacturing plant. In Proc. of the American Control Conference, pages 1741–1746, Boston, MA, July 2016.
10. T. Muehlpfordt, J.A. Paulson, R. Findeisen, and R. D. Braatz. Output feedback model predictive control with probabilistic uncertainties for linear systems. In Proc. of the American Control Conference, pages 2035–2040, Boston, MA, July 2016.
9. J.A. Paulson, M. C. Molaro, D. O. Bellisario, M. S. Strano, and R. D. Braatz. Mathematical modeling and analysis of carbon nanotube photovoltaic systems. In Proc. of the 11th IFAC Symposium on Dynamics and Control Process Systems, pages 442–447, Trondheim, Norway, June 2016.
8. J.A. Paulson, E. Harinath, L. C. Foguth, and R. D. Braatz. Nonlinear model predictive control of systems with probabilistic time-invariant uncertainties. In Proc. of the 5th IFAC Conference on Nonlinear Model Predictive Control, pages 16–25, Seville, Spain, September 2015.
7. A. E. Lu, J.A. Paulson (co-first author), N. J. Mozdzierz, A. Stockdale, A. N. Ford Versypt, K. R. Love, J. C. Love, and R. D. Braatz. Control systems technology in the advanced manufacturing of biologic drugs. In Proc. of the 2015 IEEE Conference on Control Applications, pages 1505–1515, Sydney, Australia, September 2015.
6. L. C. Foguth, J.A. Paulson, R. D. Braatz, and D. M. Raimondo. Fast robust model predictive control of high-dimensional systems. In Proc. of the European Control Conference, pages 2009–2014, Linz, Austria, July 2015.
5. M. Torchio, N. A. Wolff, D. M. Raimondo, L. Magni, U. Krewer, B. Gopaluni, J.A. Paulson, and R. D. Braatz. Real-time model predictive control for the optimal charging of a Lithium-ion battery. In Proc. of the American Control Conference, pages 4536–4541, Chicago, IL, July 2015.
4. A. Mesbah, J.A. Paulson, R. Lakerveld, and R. D. Braatz. Plant-wide model predictive control for a continuous pharmaceutical process. In Proc. of the American Control Conference, pages 4301–4307, Chicago, IL, July 2015.
3. J.A. Paulson, S. Streif, and A. Mesbah. Stability for receding-horizon stochastic model predictive control with chance constraints. In Proc. of the American Control Conference, pages 937–943 Chicago, IL, July 2015.
2. J.A. Paulson, A. Mesbah, S. Streif, R. Findeisen, and R. D. Braatz. Fast stochastic model predictive control of high-dimensional systems. In Proc. of the 53rd IEEE Conference on Decision and Control, pages 2802–2809, Los Angeles, CA, December 2014.
1. J.A. Paulson, D. M. Raimondo, R. Findeisen, R. D. Braatz, and S. Streif. Guaranteed active fault diagnosis for uncertain nonlinear systems. In Proc. of the European Control Conference, pages 926–931, Strasbourg, France, June 2014.
Home > Theses and Dissertations > 9759
Hybrid machine learning and physics-based modeling approaches for process control and optimization.
Junho Park , Brigham Young University Follow
Transformer neural networks have made a significant impact on natural language processing. The Transformer network self-attention mechanism effectively addresses the vanishing gradient problem that limits a network learning capability, especially when the time series gets longer or the size of the network gets deeper. This dissertation examines the usage of the Transformer model for time-series forecasting and customizes it for a simultaneous multistep-ahead prediction model in a surrogate model predictive control (MPC) application. The proposed method demonstrates enhanced control performance and computation efficiency compared to the Long-short term memory (LSTM)-based MPC and one-step-ahead prediction model structures for both LSTM and Transformer networks. In addition to the Transformer, this research investigates hybrid machine-learning modeling. The machine learning models are known for superior function approximation capability with sufficient data. However, the quantity and quality of data to ensure the prediction precision are usually not readily available. The physics-informed neural network (PINN) is a type of hybrid modeling method using dynamic physics-based equations in training a standard machine learning model as a form of multi-objective optimization. The PINN approach with the state-of-the-art time-series neural networks Transformer is studied in this research providing the standard procedure to develop the Physics-Informed Transformer (PIT) and validating with various case studies. This research also investigates the benefit of nonlinear model-based control and estimation algorithms for managed pressure drilling (MPD). This work presents a new real-time high-fidelity flow model (RT-HFM) for bottom-hole pressure (BHP) regulation in MPD operations. Lastly, this paper presents details of an Arduino microcontroller temperature control lab as a benchmark for modeling and control methods. Standard benchmarks are essential for comparing competing models and control methods, especially when a new method is proposed. A physical benchmark considers real process characteristics such as the requirement to meet a cycle time, discrete sampling intervals, communication overhead with the process, and model mismatch. Novel contributions of this work are (1) a new MPC system built upon a Transformer time-series architecture, (2) a training method for time-series machine learning models that enables multistep-ahead prediction, (3) verification of Transformer MPC solution time performance improvement (15 times) over LSTM networks, (4) physics-informed machine learning to improve extrapolation potential, and (5) two case studies that demonstrate hybrid modeling and benchmark performance criteria.
Ira A. Fulton College of Engineering and Technology; Chemical Engineering
https://lib.byu.edu/about/copyright/
Park, Junho, "Hybrid Machine Learning and Physics-Based Modeling Approaches for Process Control and Optimization" (2022). Theses and Dissertations . 9759. https://scholarsarchive.byu.edu/etd/9759
Document type.
Dissertation
http://hdl.lib.byu.edu/1877/etd12597
transformer neural network architecture, physics informed neural network, process control, optimization
Since December 12, 2022
Engineering Commons
Advanced Search
ScholarsArchive ISSN: 2572-4479
Hosted by the.
Home | About | FAQ | My Account | Accessibility Statement
Privacy Copyright
We're sorry but you will need to enable Javascript to access all of the features of this site.
Introduction to optimization.
MS&E211
Stanford School of Engineering
Note: MS&E211 is not going to be offered through SCPD this academic year AY24-25 .
Optimization holds an important place in both practical and theoretical worlds, as understanding the timing and magnitude of actions to be carried out helps achieve a goal in the best possible way. This course emphasizes data-driven modeling, theory and numerical algorithms for optimization with real variables. Explore the study of maximization and minimization of mathematical functions and the role of prices, duality, optimality conditions, and algorithms in finding and recognizing solutions. Learn about applications in machine learning, operations, marketing, finance and economics.
Topics Include
Before enrolling in your first graduate course, you must complete an online application .
Don’t wait! While you can only enroll in courses during open enrollment periods, you can complete your online application at any time.
Once you have enrolled in a course, your application will be sent to the department for approval. You will receive an email notifying you of the department's decision after the enrollment period closes. You can also check your application status in your my stanford connection account at any time.
Learn more about the graduate application process .
There was a problem with this request. We're working on getting it fixed as soon as we can.
IMAGES
VIDEO
COMMENTS
The work in the Operational Research and Optimization research group is in three main areas: the mathematical and computing aspects of optimization, combinatorial optimization, and energy systems. The core technology in optimization is the solution of large sparse linear and quadratic problems, and we provide world-class expertise in the two ...
The Ph.D. program in Operations Research at Stanford combines the areas of "Systems Modeling and Optimization" and "Probability and Stochastic Systems" in the Department of Management Science and Engineering. Operations Research at Stanford combines the depth and elegance of mathematics with the excitement and practicality of engineering like ...
Optimization focuses on finding the minimum (or maximum) value of an objective function subject to constraints that represent user preferences and/or limitations imposed by the nature of the question at hand. Research in optimization involves the analysis of such mathematical problems and the design of efficient algorithms for solving them.
Course of Study. The basic operations research courses offered include: linear, nonlinear, integer and dynamic programming; graph theory and network optimization; convex optimization and convex analysis; and stochastic models. Each course is taught by a faculty member who is actively pursuing research in the subject area.
Qualifying Process: By the end of a student's first semester at MIT, doctoral students must choose three courses they would like to declare as their Qualifying Courses. Students must choose one approved course from the three different categories (Optimization, Probability, and Machine Learning/Statistics).
PhD students take core courses in optimization and stochastics as well as advanced courses in computer science, game theory, microeconomics, statistics, and other areas tailored to the interests of the student, e.g. Computational Social Science, Operations Management, Environmental Policy, Health Policy, etc. Program and Center Affiliations.
Methodological research in optimization uses techniques of algebra, geometry, analysis and combinatorics to develop and analyze algorithms for fundamental optimization models having broad applicability. Such models are the means by which we can leverage general-purpose optimization software for applications in all areas. For very large scale applications, specially tailored algorithms are ...
View All Courses. Mathematical optimization provides a unifying framework for studying issues of rational decision-making, optimal design, effective resource allocation and economic efficiency. It is therefore a central methodology of many business-related disciplines, including operations research, marketing, accounting, economics, game theory ...
Machine learning assisted optimization techniques for fitting excitonic spin-orbit models to big data. University of Edinburgh School of Physics and Astronomy. A PhD studentship is available in the group of Chris Stock (School of Physics and Astronomy, The University of Edinburgh in collaboration with Russell Ewings (STFC-ISIS) and Bo Liu ...
The Ph.D. program in algorithms, combinatorics, and optimization is intended to fill this gap. It brings together the study of the mathematical structure of discrete objects and the design and analysis of algorithms in areas such as: Network Optimization. Combinatorial Optimization. Integer Programming.
The ISE department at the Ohio State University offers two degree programs (MS and PhD) in OR: Master of Science (MS) in OR builds fundamental OR skills with an emphasis on the application of these skills in practice. Doctor of Philosophy (PhD) in OR is academically rigorous with an emphasis on scholarly research and achievement.
Applications from problem areas in which optimization plays a key role are also introduced. The goal of the course is to provide students with a foundation sufficient to use basic optimization in their own research work and/or to pursue more specialized studies involving optimization theory. The course is designed for entering doctoral students.
The Ph.D program in Algorithms, Combinatorics, and Optimization at Carnegie Mellon is intended to fill this gap. The program brings together the study of the mathematical structure of discrete objects and the design and analysis of algorithms in areas such as graph theory, combinatorial optimization, integer programming, polyhedral theory ...
Optimization is also widely used in signal processing, statistics, and machine learning as a method for fitting parametric models to observed data. Examples include: Languages and solvers for convex optimization, Distributed convex optimization, Robotics, Smart grid algorithms, Learning via low rank models, Approximate dynamic programming ...
interactions can be conducted in the optimization process. Several formulations were investigated. The suggested formulation is able to handle well shut-down, avoid some numerical difficulties, and is computationally efficient. Once formulated, the optimization problem was solved by a sequential quadratic programming (SQP) algorithm.
Algorithms, Combinatorics, and Optimization (Ph.D.) Course Description and Catalog. Focus: furthering the study of discrete structures in the context of computer science, applied mathematics, and operations research.
MIT Sloan PhD Program graduates lead in their fields and are teaching and producing research at the world's most prestigious universities. Rigorous, discipline-based research is the hallmark of the MIT Sloan PhD Program. The program is committed to educating scholars who will lead in their fields of research—those with outstanding ...
CSE.900. Doctoral Seminar in Computational Science and Engineering. 3. Core Area of Study. Choose four 12-unit subjects from these six core CSE areas:1. 48. Discretization and numerical methods for partial differential equations. Optimization methods. Statistics and data-driven modeling.
Advanced Materials, Devices, and Nanotechnology. We develop mathematical theories, AI-based algorithms, and computational simulations across the atomistic, particle, and continuum levels to model chemical engineering processes, with the aims of gaining fundamental scientific knowledge and devising next-generation applications in in-space ...
Brian Denton. Stephen M. Pollock Collegiate Professor of Industrial and Operations Engineering.
Joel Paulson received his PhD in 2016 from the Massachusetts Institute of Technology (MIT), where he won an NSF Graduate Research Fellowship and multiple awards for research and outstanding teaching and mentoring. ... (with highest honors) in 2020. Prior to joining OSU in 2020, he worked on mathematical optimization of process designs in pulp ...
PhD. College and Department. Ira A. Fulton College of Engineering and Technology; Chemical Engineering ... "Hybrid Machine Learning and Physics-Based Modeling Approaches for Process Control and Optimization" (2022). Theses and Dissertations. 9759. https://scholarsarchive.byu.edu/etd/9759 Date Submitted. 2022-12-01. Document Type. Dissertation ...
This course emphasizes data-driven modeling, theory and numerical algorithms for optimization with real variables. Explore the study of maximization and minimization of mathematical functions and the role of prices, duality, optimality conditions, and algorithms in finding and recognizing solutions. Learn about applications in machine learning ...
Currently is in the process of obtaining a PhD in the field of Artificial Intelligence or related field Hands-on experience in deep learning algorithms and techniques, e.g., transformers 3+ years experience with deep learning software libraries such as PyTorch/JAX
Optimization of process parameters for SS304 in wire electrical discharge machining using Taguchi's technique. Mater Today Proc 2018; 5(1): 2877-2883. Crossref. Google Scholar. 8. Kumar CS, Patel SK. Effect of WEDM surface texturing on Al 2 O 3 /TiCN composite ceramic tools in dry cutting of hardened steel.