Optimal dual-model controller of solid oxide fuel cell output voltage using imitation distributed deep reinforcement learning

Solid oxide fuel cell (SOFC) is disadvantaged by significant nonlinearity, which makes it difficult to control output voltage of SOFC and satisfy the constraints of fuel utilization simultaneously. In order to solve this problem, a dual-model control framework (DMCF) is proposed. In particular, ther...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of hydrogen energy Jg. 48; H. 37; S. 14053 - 14067
Hauptverfasser: Li, Jiawen, Cui, Haoyang, Jiang, Wei, Yu, Hengwen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 30.04.2023
Schlagworte:
Deep reinforcement learning
Fuel utilization
Imitation distributed deep deterministic policy gradient algorithm (ID3PG)
Optimal control framework
Output voltage control
Solid oxide fuel cell
Deep reinforcement learning
Optimal control framework
Solid oxide fuel cell
Output voltage control
Fuel utilization
Imitation distributed deep deterministic policy gradient algorithm (ID3PG)
ISSN:0360-3199, 1879-3487
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Solid oxide fuel cell (SOFC) is disadvantaged by significant nonlinearity, which makes it difficult to control output voltage of SOFC and satisfy the constraints of fuel utilization simultaneously. In order to solve this problem, a dual-model control framework (DMCF) is proposed. In particular, there are two controllers deployed under this framework, with an PID controller and a supplementary dynamic controller to track the SOFC output voltage. The supplementary dynamic controller is conducive to the stabilization of tracking by adapting to the uncertainties, considering the constraint on fuel utilization. In addition, an imitation distributed deep deterministic policy gradient (ID3PG) algorithm, which integrates imitation learning and distributed deep reinforcement learning to enhance the robustness and adaptive capacity of this framework, is proposed for the supplementary dynamic controller. The simulation results obtained in this work have demonstrated that the proposed framework is effective in imposing control on SOFC output voltage and preventing constraint violations of fuel utilization. •An ID3PG-PID dual-model control framework is proposed.•A new deep reinforcement learning algorithm is proposed.•ID3PG is introduced for enhancing adaptive capacity.•The proposed framework is effective in preventing constraint violations.
ISSN:0360-3199
1879-3487
DOI:10.1016/j.ijhydene.2022.12.194