Journal
JOURNAL OF PROCESS CONTROL
Volume 115, Issue -, Pages 89-99Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.jprocont.2022.05.003
Keywords
Multi-objective; Reinforcement learning; Fed-batch fermentation; Process control
Funding
- National Natural Science Foun-dation of China [61873022]
Ask authors/readers for more resources
Many real-world control problems involve conflicting objectives, and obtaining Pareto optimal solution sets for each objective is necessary. This study proposes a soft proximal policy optimization algorithm combined with a hybrid weight-generation method to find the Pareto front approximation of the fed-batch fermentation process. The algorithm aims to find a single policy for the multi-objective reinforcement learning problem and use a hybrid weight-generation method to find a set of Pareto optimal solutions.
Many real-world control problems involve conflicting objectives. For different objectives, it is necessary to obtain Pareto optimal solution sets for each one. Over recent years, multi-objective reinforcement learning (MORL) has been extensively studied to solve this problem. However, the multi-objective optimization problem of complex continuous control processes still requires exploration. Soft proximal policy optimization algorithms have also been proposed to be combined with a hybrid weightgeneration method for application to find the Pareto front approximation of the fed-batch fermentation process. This algorithm intends to initially find a single policy for the multi-objective reinforcement learning problem. A hybrid weight-generation method is then used to change the weights between different objectives to find a set of Pareto optimal solutions. In addition, we analyzed the mechanism of the fed-batch process, established the kinetic model, and designed the experimental environment based on the OpenAI Gym library. Experimental results showed that the proposed algorithm is effective and efficient in approaching the Pareto front of the fed-batch fermentation problem. (c) 2022 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available