Fuel cell hybrid electric vehicles (FCHEVs) are gaining prominence as eco-friendly alternatives to conventional vehicles due to their lower emissions and higher energy efficiency. Effective energy management is crucial for maximising FCHEV performance. Compared with the available literatures in the relevant field, this study proposes a machine leaning (ML) framework, combining artificial neural networks (ANN) and genetic algorithms (GA) to develop an intelligent energy management strategy. The ANN component leverages its predictive and pattern recognition capabilities, while GA optimises network parameters such as weights, biases, and structural hyper parameters to enhance model performance. Additionally, while investigating the real-world driving data, the hybrid ANN-GA model dynamically predicts optimal power distribution between the fuel cell and battery efficiently. Furthermore, the results achieved through different observations confirm that the proposed method outperforms conventional strategies, delivering significant gains in energy efficiency and system responsiveness. Finally, the outcome of the findings demonstrates the superiority of the ANN-GA hybrid model in terms of optimal energy distribution paving the way for more sustainable and efficient transportation systems.
Chatterjee et al. (2026) studied this question.