Reinforcement learning for online adaptation of model predictive controllers: Application to a selective catalytic reduction unit

Hedrick, Elijah; Hedrick, Katherine; Bhattacharyya, Debangsu; Zitney, Stephen E.; Omell, Benjamin

doi:10.1016/j.compchemeng.2022.107727

Cited by 16 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, recent reinforcement control strategies aimed to batch control can be found elsewhere (Ma et al, Kim et al, Yoo et al, Joshi et al, and Mowbray et al). Additional recent applications of reinforcement learning are in the Ph control of wastewater plants (Goulart and Pereira), in hydraulic fracturing (Bangi and Kwon), in catalytic reduction units (Hedrick et al), and in downstream separation in biopharmaceutical processes (Hwangbo and Sin).…”

Section: Reinforcement Learning Algorithmsmentioning

confidence: 99%

Machine Learning Algorithms Used in PSE Environments: A Didactic Approach and Critical Perspective

Fuentes-Cortés

Flores‐Tlacuahuac

Nigam

2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

This work addresses recent developments for solving problems in process systems engineering based on machine learning algorithms. A general description of most popular supervised and unsupervised learning algorithms is presented, as well as the applications addressed in the current literature. Because of their wide usage and potential applications, support vector machines and neural networks are addressed as special cases. The approach used is fundamentally didactic. Therefore, several of the references included are recommendations for novice readers interested in entering the area of machine learning and data science. The applications were selected considering simplicity, popularity of the application, and accessibility for inexperienced readers, but with knowledge of the process systems engineering area. Finally, a critical perspective for future development and applications is provided. Epistemological issues and modeling limitations are discussed in order to analyze the real significance of data-driven strategies as well as a questioning of academic marketing in recent years.

show abstract

Section: Reinforcement Learning Algorithmsmentioning

confidence: 99%

Machine Learning Algorithms Used in PSE Environments: A Didactic Approach and Critical Perspective

Fuentes-Cortés

Flores‐Tlacuahuac

Nigam

2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…This approach also allows for continuous learning to deal with uncertain environments. In addition, RL‐based approaches are developed for online tuning of the MPC controller 42 . While RL‐based controllers show promising results, these works also highlight the challenges that presently exist in developing RL in practice (the need for large online training data and safe explorations).…”

Section: Introductionmentioning

confidence: 99%

A practically implementable reinforcement learning‐based process controller design

Hassanpour,

Wang,

Corbett

et al. 2023

AIChE Journal

View full text Add to dashboard Cite

The present article enables reinforcement learning (RL)‐based controllers for process control applications. Existing instances of RL‐based solutions have significant challenges for online implementation since the training process of an RL agent (controller) presently requires practically impossible number of online interactions between the agent and the environment (process). To address this challenge, we propose an implementable model‐free RL method developed by leveraging industrially implemented model predictive control (MPC) calculations (often designed using a simple linear model identified via step tests). In the first step, MPC calculations are used to pretrain an RL agent that can mimic the MPC performance. Specifically, the MPC calculations are used to pretrain the actor, and the objective function is used to pretrain the critic(s). The pretrained RL agent is then employed within a model‐free RL framework to control the process in a way that initially imitates MPC behavior (thus not compromising process performance and safety), but also continuously learns and improve its performance over the nominal linear MPC. The effectiveness of the proposed approach is illustrated through simulations on a chemical reactor example.

show abstract

“…The key to SCR denitrification system lies in the control of ammonia injection amount. The precise measurement of NOx is the foundation for achieving precise ammonia injection [3,4].…”

Section: Introductionmentioning

confidence: 99%

NOx emissions estimation of boiler based on mutual information feature reconstruction and optimization of extreme learning machine

Jiang

Dong

Sun

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

The measurement of NOx emissions in the selective catalytic reduction (SCR) system of boiler has problems with poor real-time performance and abnormal measurement during purging. It is necessary to accurately estimate NOx emissions. For this reason, the NOx emissions prediction method of boiler based on mutual information feature reconstruction and optimization of extreme learning machine (ELM) is proposed: Firstly, delay estimation and data space reconstruction of input features are performed based on mutual information; Then the conditional mutual information based on greedy selection strategy is adopted to rank and choose the input features; Finally, the hybrid quantum sparrow search algorithm (QSSA) was proposed by combining Lévy flight strategy and quantum strategy in the sparrow search algorithm (SSA), and QSSA is used to optimize the weights and biases of the ELM. Taking the operation data of the SCR system of a 1000MW thermal power unit as an example for verification. The results show that the proposed method can effectively improve the accuracy and generalization ability of the ELM, and provide a new method for NOx emissions estimation of boiler.

show abstract

Reinforcement learning for online adaptation of model predictive controllers: Application to a selective catalytic reduction unit

Cited by 16 publications

References 34 publications

Machine Learning Algorithms Used in PSE Environments: A Didactic Approach and Critical Perspective

Machine Learning Algorithms Used in PSE Environments: A Didactic Approach and Critical Perspective

A practically implementable reinforcement learning‐based process controller design

NOx emissions estimation of boiler based on mutual information feature reconstruction and optimization of extreme learning machine

Contact Info

Product

Resources

About