Advancing vehicle energy systems: Optimisation of fuel-cell hybrid electric vehicles using parallel LSTM and CNN

Customers and manufacturers in the automotive sector have been positively affected by hydrogen and fuel cells (FCs) over the last 30 years. Automakers are primarily focused on reducing fuel consumption and exhaust emissions, improving energy efficiency, and maximizing range limits through the adaptation of existing technologies. Vehicles also known as electric vehicles (EVs) are those that are equipped with electric motor systems. Feature selection, preprocessing, and training the model are the three key components. Data reduction and data transformation are the two main components of data processing. Use of Spearman's rank correlation coefficient is a technique in feature selection. The model's accuracy was enhanced during training by utilizing the Parallel CNN-LSTM. The proposed method outperformed state-of-the-art methods like CNN and LSTM with an accuracy rate of 97.12%.