Daniel Beahr

Augmentation and Hybridization of Conventional Forms of Process Control with Advanced Control Methods

The goals of my research is to broadly integrate novel advanced control methods into the field of process control. This is largely focused on the implementation of reinforcement learning. New advanced computational techniques have allowed the use of RL in conjunction with continuous systems, but developments have failed to accommodate the often stringent learning and performance requirements necessary for control of a plant environment. This work seeks to bridge that gap, establishing RL as a viable control method while also ensuring the safety and performance expected of any conventional process control. 

1. Beahr D, Saini V, Bhattacharyya D, Seachman S, Boohaker C, "Estimation-based Model Predictive Control with Objective Prioritization for Mutually Exclusive Objectives: Application to a Power Plant", 141, 103268, Journal of Process Control, 2024

2. Beahr D, Bhattaharyya D, Allan D A, Zitney S E, "Development of Algorithms for Augmenting and Replacing Conventional Process Control using Reinforcement Learning", 190, 108826, Computers & Chemical Engineering, 2024

• Beahr D, Bhattacharyya D, Saini V, Hedrick E, Hong S M C, “Estimation-Based Model Predictive Control with State-Dependent Objective Prioritization; An Application to a Natural Gas Combined Cycle Power Plant”, Paper 689c, AIChE Annual Meeting, Phoenix, AZ, November 13-18, 2022

• Beahr D, Alastanos M, Hedrick E, Bhattacharyya D, “Development of Algorithms for Augmenting and Replacing Conventional Process Control Using Reinforcement Learning”, Paper 106g, AIChE Annual Meeting, Phoenix, AZ, November 13-18, 2022