Nonintrusive parameter adaptation of chemical process models with reinforcement learning

Model-based control is one of the most prevalent techniques for designing and controlling engineering systems. However, many of these systems are complex and characterized by changing dynamics. Hence, online system identification is required to achieve optimum adaptive control performance for such complex systems. This work proposes an algorithm for nonintrusive, online, nonlinear parameter estimation of physical models using deep reinforcement learning (RL). The problem of training a neural network for parameter estimation is formulated as a reinforcement learning problem. The RL-based parameter estimation policy is tested on a simulation of the selective hydrogenation of acetylene, which is a highly nonlinear system. The learned model estimation policy is able to correctly predict the states of the system with a prediction error of less than 1% in various conditions, such as in the presence of measurement noise and structural differences in models.(c) 2023 Elsevier Ltd. All rights reserved.

Automated summary

Model-based control is a prevalent technique for engineering systems, but complex systems with changing dynamics require online system identification. This study proposes an algorithm for nonintrusive, online, nonlinear parameter estimation using deep reinforcement learning. The RL-based parameter estimation policy accurately predicts system states with less than 1% error in various conditions. The algorithm is tested on a simulation of selective hydrogenation of acetylene, a highly nonlinear system. (c) 2023 Elsevier Ltd. All rights reserved.