Machine Learning-Based Current Density Simulation for Direct Borohydride Fuel Cell

Recent studies on fuel cell design have showed that the use of simulation tools is beneficial in terms saving time and money. Current density management still a key research problem for several technologies, including Direct Borohydride Fuel Cell (DBFC). This paper describes systematic machine learning technique estimating current DBFC as function various input factors. Artificial Neural Networks (ANN) Decision Tree Regressor (DTR) are two popular models were trained evaluated using conducted experiments presented previous research. The ANN model performed better than DTR simulation, with mean absolute error 3.00015 training 5.57614 testing. exhibits very small values, indicating suggested approaches accurately mirror real-world process.