A Pareto frontier-driven multi-objective energy management control strategy for fuel cell hybrid electric vehicles incorporating driving styles in adaptive cruise control scenarios

Traditional adaptive cruise control (ACC) systems relying on fixed algorithms cannot fulfill the comprehensive demands of fuel cell hybrid electric vehicles in driving safety, energy consumption, and component lifespan as they overlook driver behavior and traffic variability. This study proposes an integrated ACC strategy using a convolutional neural network for driving style recognition, a trip distance adaptive equivalent consumption minimization strategy, and Pareto multi-objective optimization via Non-dominated Sorting Genetic Algorithm-II. Key innovations include dynamic equivalent factor adjustment based on state of charge and driving style, and a multi-objective function balancing tracking performance, hydrogen consumption, and fuel cell degradation. Simulations and hardware-in-the-loop experiments demonstrate a 3.96% improvement in fuel economy, 15.9% reduction in fuel cell degradation, and enhanced tracking accuracy compared to sequential quadratic programming.