Study on the Optimal Double-Layer Electrode for a Non-Aqueous Vanadium-Iron Redox Flow Battery Using a Machine Learning Model Coupled with Genetic Algorithm

To boost the operational performance of a non-aqueous DES electrolyte-based vanadium-iron redox flow battery (RFB), our previous work proposed double-layer porous electrode spliced by carbon paper and graphite felt. However, this electrode’s architecture still needs to be further optimized under different conditions. Hence, proposes multi-layer artificial neural network (ANN) model predict relationship between RFB’s structural characteristics. A training dataset ANN is generated three-dimensional finite-element numerical simulations galvanostatic discharging process. In addition, genetic algorithm (GA) coupled an regression process for optimizing parameters elevate accuracy prediction. The novelty lies in modified optimal method RFB driven machine learning (ML) with GA. comparative result shows that ML reaches satisfactory predictive accuracy, mean square error lower than other popular models. Based on known region operating conditions, obtained results prove well-trained can used estimate whether should applied determine appropriate thickness ratio electrode.