Maximizing Efficiency in Fuel Cell Electric Bicycles: The Role of Deep Learning in Performance Optimization

The purpose of this work is to maximize the energy consumption and performance of fuel cell electric bicycles (FCEBs) using particular key input parameters. The paper used an integrated strategy that included an artificial neural network (ANN) and a genetic algorithm (GA) to predict and determine the optimal performance and energy consumption of FCEBs. The FCEB simulation model is established and simulated in the MATLAB-Simulink environment to generate 1000 data points that are used for training, validating, and testing the artificial neural network (ANN), which consists of five input neurons, two hidden neurons, and two output neurons. Furthermore, the GA is used to determine the optimal performance and energy usage after the ANN has been precisely trained. To evaluate and verify the simulated results, the experimental approach method was performed under the identical conditions.