Energy management optimization of hybrid electric vehicles based on deep learning model predictive control.

This article focuses on optimizing energy management in hybrid electric vehicles (HEVs) using a deep learning (DL) model predictive control approach. It details the integration of backpropagation neural networks (BPNN) and convolutional neural networks (CNN) to predict and optimize HEV energy consumption under various driving conditions, supported by empirical data from a questionnaire survey of 1,500 consumers. The proposed DL-based strategy demonstrated higher accuracy in energy consumption prediction and improved performance over traditional control methods in fuel consumption, battery usage, battery life, and CO2 emissions. The study highlights consumer preferences, emphasizing battery life as a key optimization target, and acknowledges limitations such as sample size and driving behavior diversity, suggesting future research to expand experimental scope and explore additional DL algorithms for more comprehensive HEV energy management solutions.