Adaptive Energy Management Strategy for PEMFC Electric Vehicles Based on SVM-FLC

In response to the adaptive energy management issue of the Proton Exchange Membrane Fuel Cell (PEMFC) and lithium-ion battery hybrid energy storage system under complex and variable driving conditions, an adaptive fuzzy logic energy management strategy based on Support Vector Machine (SVM) driving pattern recognition is proposed. First, seven principal components that represent different driving condition categories are established using Principal Component Analysis (PCA). K-means clustering analysis is then employed to classify the driving cycles into low-speed, medium-speed, and high-speed categories. Subsequently, SVM is utilized to recognize the real-time driving mode based on the principal components of the driving conditions. Finally, the adaptive fuzzy logic controller activates three different fuzzy control rules according to the classification results of the SVM, thereby achieving adaptive energy management for the hybrid energy storage system. Simulation results indicate that the proposed method effectively enhances the adaptability of the hybrid energy storage system to complex driving conditions and can efficiently balance the power output of the PEMFC and lithium-ion battery.