An Improved Sparrow Search Algorithm-optimized fuzzy energy management strategy for fuel cell vehicles considering energy source health

Fuel cell hybrid electric vehicles (FCHEVs) face significant barriers to large-scale adoption due to high manufacturing and operating costs. This study proposes a fuzzy control-based energy management strategy (EMS) that incorporates the health states of multiple energy sources and is optimized using an Improved Sparrow Search Algorithm (ISSA). A complete vehicle model and simulation platform are established, and ISSA optimizes the fuzzy membership functions. The algorithm integrates Chebyshev chaotic mapping, an adaptive convergence factor, cosine annealing, bubble-net attacking, and spiral foraging to enhance global and local search capabilities, targeting reduced hydrogen consumption and improved component durability. Compared with the power-following strategy, the proposed EMS reduces hydrogen consumption by 5.9% and 3.46% under the New European Driving Cycle (NEDC) and Worldwide Harmonized Light Vehicles Test Cycle (WLTC), respectively, and by 2.97% and 1.38% compared with conventional fuzzy control. SOC fluctuations decrease from 0.745 to 0.028 under NEDC and from 1.091 to 0.150 under WLTC, while fuel cell degradation rates are reduced by 20.41% and 32.18%, respectively. The proposed strategy improves energy efficiency and extends the service life of FCHEVs.