(629h) Continuous Control of a Polymerization System with Deep Reinforcement Learning
- Conference: AIChE Annual Meeting
- Year: 2018
- Proceeding: 2018 AIChE Annual Meeting
- Group: Computing and Systems Technology Division
- Time: Thursday, November 1, 2018 - 10:13am-10:32am
Previous studies have been done in controlling a free-radical polymerization process by following real-time measurement of weight-average molar mass, where the specific molar mass distribution can be achieved by following a trajectory of weight-average molar mass with respect to time. In this work, we developed a deep learning based controller for a free radical poly-acrylamide polymerization system using Deep Deterministic Policy Gradient (DDPG). The DDPG utilizes actor-critic structure that is able to predict actions of infinite dimensions. The controller calculates the control action at, which consists of the monomer flow rate Fm and initiator flow rate Fi to adjust at each time step t, and the system response of the action is recorded as a state st. The network is trained to maximize the cumulative reward r that accounts for the distance between current output and target output for each iteration. The network is trained on an established kinetic model of the polymerization reaction, and the controller gradually learns the policy through exploration of the system. Then convergence is achieved when the average cumulative reward reaches a desired threshold. In our experiment, the controller successfully has learned the control policy to follow the target trajectory of the weight-average molar mass.
Overall the smart controller has shown robust control over a range of operating conditions, which indicates the deep reinforcement learning based approachâs capability in controlling a nonlinear dynamic semi-batch system.
 N. Ghadipasha, W. Zhu, J. A. Romagnoli, T. Mcafee, T. Zekoski, and W. F. Reed, âOnline Optimal Feedback Control of Polymerization Reactors : Application to Polymerization of Acrylamide â Water â Potassium Persulfate ( KPS ) System,â 2017.
 S. P. K. Spielberg, R. B. Gopaluni, and P. D. Loewen, âDeep Reinforcement Learning Approaches for Process Controlâ, 2017
 V. Mnih, D. Silver, and M. Riedmiller, âPlaying Atari with Deep Reinforcement Learning,â pp. 1â9.
 T. P. Lillicrap et al., âContinuous learning control with deep reinforcement learning,â , 2016.
 D. Silver, G. Lever, D. Technologies, G. U. Y. Lever, and U. C. L. Ac, âDeterministic Policy Gradient Algorithms.â
This paper has an Extended Abstract file available; you must purchase the conference proceedings to access it.
Do you already own this?
Log In for instructions on accessing this content.
|AIChE Graduate Student Members||Free|
|AIChE Undergraduate Student Members||Free|