1 code implementation • 23 Apr 2024 • Nathan P. Lawrence, Philip D. Loewen, Shuyuan Wang, Michael G. Forbes, R. Bhushan Gopaluni
Willems' fundamental lemma enables a trajectory-based characterization of linear systems through data-based Hankel matrices.
no code implementations • 24 Jan 2024 • Nathan P. Lawrence, Seshu Kumar Damarla, Jong Woo Kim, Aditya Tulsyan, Faraz Amjad, Kai Wang, Benoit Chachuat, Jong Min Lee, Biao Huang, R. Bhushan Gopaluni
Soft sensing contains a wealth of industrial applications of statistical and machine learning methods.
1 code implementation • 21 Oct 2023 • Nathan P. Lawrence, Philip D. Loewen, Shuyuan Wang, Michael G. Forbes, R. Bhushan Gopaluni
For the training of reinforcement learning agents, the set of all stable linear operators is given explicitly through a matrix factorization approach.
no code implementations • 26 Apr 2023 • Shuyuan Wang, Philip D. Loewen, Nathan P. Lawrence, Michael G. Forbes, R. Bhushan Gopaluni
We adapt reinforcement learning (RL) methods for continuous control to bridge the gap between complete ignorance and perfect knowledge of the environment.
no code implementations • 7 Apr 2023 • Nathan P. Lawrence, Philip D. Loewen, Shuyuan Wang, Michael G. Forbes, R. Bhushan Gopaluni
We propose a framework for the design of feedback controllers that combines the optimization-driven and model-free advantages of deep reinforcement learning with the stability guarantees provided by using the Youla-Kucera parameterization to define the search domain.
no code implementations • 18 Jan 2023 • Tobi Michael Alabi, Nathan P. Lawrence, Lin Lu, Zaiyue Yang, R. Bhushan Gopaluni
However, the adoption of CDRT is not economically viable at the current carbon price.
no code implementations • 11 Nov 2022 • Lim C. Siang, Shams Elnawawi, Lee D. Rippon, Daniel L. O'Connor, R. Bhushan Gopaluni
A significant portion of the effort involved in advanced process control, process analytics, and machine learning involves acquiring and preparing data.
no code implementations • 22 Sep 2022 • R. Bhushan Gopaluni, Aditya Tulsyan, Benoit Chachuat, Biao Huang, Jong Min Lee, Faraz Amjad, Seshu Kumar Damarla, Jong Woo Kim, Nathan P. Lawrence
Over the last ten years, we have seen a significant increase in industrial data, tremendous improvement in computational power, and major theoretical advances in machine learning.
no code implementations • 19 Sep 2022 • Daniel G. McClement, Nathan P. Lawrence, Michael G. Forbes, Philip D. Loewen, Johan U. Backström, R. Bhushan Gopaluni
In this work, we briefly reintroduce our methodology and demonstrate how it can be extended to proportional-integral-derivative controllers and second order systems.
no code implementations • 17 Mar 2022 • Daniel G. McClement, Nathan P. Lawrence, Johan U. Backstrom, Philip D. Loewen, Michael G. Forbes, R. Bhushan Gopaluni
In tests reported here, the meta-RL agent was trained entirely offline on first order plus time delay systems, and produced excellent results on novel systems drawn from the same distribution of process dynamics used for training.
no code implementations • 13 Nov 2021 • Nathan P. Lawrence, Michael G. Forbes, Philip D. Loewen, Daniel G. McClement, Johan U. Backstrom, R. Bhushan Gopaluni
In addition to its simplicity, this approach has several appealing features: No additional hardware needs to be added to the control system, since a PID controller can easily be implemented through a standard programmable logic controller; the control law can easily be initialized in a "safe'' region of the parameter space; and the final product -- a well-tuned PID controller -- has a form that practitioners can reason about and deploy with confidence.
1 code implementation • 26 Mar 2021 • Nathan P. Lawrence, Philip D. Loewen, Michael G. Forbes, Johan U. Backström, R. Bhushan Gopaluni
We introduce a method for learning provably stable deep neural network based dynamic models from observed data.
no code implementations • 25 Mar 2021 • Daniel G. McClement, Nathan P. Lawrence, Philip D. Loewen, Michael G. Forbes, Johan U. Backström, R. Bhushan Gopaluni
Meta-learning is appealing for process control applications because the perturbations to a process required to train an AI controller can be costly and unsafe.
no code implementations • 10 May 2020 • Nathan P. Lawrence, Gregory E. Stewart, Philip D. Loewen, Michael G. Forbes, Johan U. Backstrom, R. Bhushan Gopaluni
Reinforcement learning has been successfully applied to the problem of tuning PID controllers in several applications.
no code implementations • 10 May 2020 • Nathan P. Lawrence, Gregory E. Stewart, Philip D. Loewen, Michael G. Forbes, Johan U. Backstrom, R. Bhushan Gopaluni
In this work, we focus on the interpretability of DRL control methods.
no code implementations • 12 Jul 2013 • Aditya Tulsyan, Biao Huang, R. Bhushan Gopaluni, J. Fraser Forbes
The simultaneous estimation is performed by filtering an extended vector of states and parameters using an adaptive sequential-importance-resampling (SIR) filter with a kernel density estimation method.