A novel vanadium redox flow battery modelling method using honey badger optimization assisted CNN-BiLSTM

• Published in: Journal of power sources Vol. 558; p. 232610
• Main Authors: Liu, Yulin, Li, Ran, Xiong, Binyu, Zhang, Shaofeng, Zhang, Xinan, Iu, Herbert, Fernando, Tyrone
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 28.02.2023
• Subjects: Battery modelling; CNN-BiLSTM; Honey badger optimization; Learning-based; Vanadium redox flow battery; CNN-BiLSTM; Vanadium redox flow battery; Learning-based; Honey badger optimization; Battery modelling
• DOI: 10.1016/j.jpowsour.2022.232610
• ISSN: 0378-7753

This research proposes a highly accurate data-driven vanadium redox flow battery (VRB) modelling approach for power engineering applications. The proposed approach addresses the common problem of excessive model dependency in the existing electrochemical principle or equivalent circuit based VRB modelling methods. Furthermore, a honey badger algorithm optimized CNN-BiLSTM is applied to directly learn the behavioural relationship between VRB current, flow rate, state-of-charge, and voltage with excellent accuracy, avoiding the usage of model parameters that are subject to variations. Besides, an outstanding modelling accuracy is obtained under variable current and flow rate. Once trained, the honey badger algorithm optimized CNN-BiLSTM neural network becomes mathematically very simple and thus, can be easily implemented in simulation studies. This contributes to substantially simplify the analysis of electrical systems with VRB. The validity of the proposed approach is verified experimentally. •People without any background in electrochemistry can use it.•It does not require any knowledge of VRB system dynamics.•It further considers the influences of variable flow rate and current.•It has superior accuracy and avoids tedious hyperparameter tuning process.