Toward self‐driving processes: A deep reinforcement learning approach to control

S Spielberg, A Tulsyan, NP Lawrence… - AIChE …, 2019 - Wiley Online Library
Advanced model‐based controllers are well established in process industries. However,
such controllers require regular maintenance to maintain acceptable performance. It is a …

Deep reinforcement learning for process control: A primer for beginners

S Spielberg, A Tulsyan, NP Lawrence… - arxiv preprint arxiv …, 2020 - arxiv.org
Advanced model-based controllers are well established in process industries. However,
such controllers require regular maintenance to maintain acceptable performance. It is a …

[HTML][HTML] Sequential Experiment Design for Parameter Estimation of Nonlinear Systems using a Neural Network Approximator

R Ramakrishna, Y Shao, G Dán, N Kringos - European Journal of Control, 2023 - Elsevier
We consider the problem of sequential parameter estimation of a nonlinear function under
the Bayesian setting. The designer can choose inputs for a sequence of experiments to …

Bayesian identification of non-linear state-space models: Part II-Error Analysis

A Tulsyan, B Huang, RB Gopaluni, JF Forbes - IFAC Proceedings Volumes, 2013 - Elsevier
In the last two decades, several methods based on sequential Monte Carlo (SMC) and
Markov chain Monte Carlo (MCMC) have been proposed for Bayesian identification of …

Process Proportional-Integral PI Control with Deep Reinforcement Learning

T Tiong, I Saad, KTK Teo… - 2023 IEEE 13th Annual …, 2023 - ieeexplore.ieee.org
Advanced model-based controllers in process industries require regular maintenance to
maintain acceptable performance. Controller performance is continuously monitored and …

A data-driven digital twin approach to optimize continuous production environment with deep reinforcement learning

AH Sivri - 2023 - open.metu.edu.tr
Today, the world mainly strives to minimize carbon emissions and maximize efficiency in
energy production to lower energy costs and greenhouse effect. Therefore, optimizing …

Recalculation of initial conditions for the observable canonical form of state-space representation

M Garan, I Kovalenko - Proceedings of the 5th International Conference …, 2016 - dl.acm.org
This paper provides the technique for recalculation of initial conditions for state vector in
observable canonical form of state-space representation for linear dynamical systems …

Error analysis in Bayesian identification of non-linear state-space models

A Tulsyan, B Huang, RB Gopaluni… - arxiv preprint arxiv …, 2013 - arxiv.org
In the last two decades, several methods based on sequential Monte Carlo (SMC) and
Markov chain Monte Carlo (MCMC) have been proposed for Bayesian identification of …