Slime Mould Algorithm (SMA) and Adaptive Neuro-Fuzzy Inference (ANFIS)-Based Energy Management of FCHEV Under Uncertainty.

This manuscript proposes a hybrid technique for optimal energy management (EM) of fuel cell (FC) and ultra-capacitor (UC) hybrid electric vehicles (FCHEVs) under uncertainty. The proposed method is a joint execution of the Slime Mould Algorithm (SMA) and the Adaptive Neuro-fuzzy Inference System (ANFIS), otherwise called the SMA-ANFIS system. The main aim of the proposed system is to achieve and regulate the steady state of DC bus voltage with minimal steady-state error (SSE) under different load conditions by using the proposed SMA-ANFIS technique. FC supplies power during vehicular operation and it is used to regulate DC bus voltage to the chosen value and recharge, and UC supplies current optimally through the proposed technique. The optimal EMS performs and controls the power flows through the associated power converters to accomplish some power allocation and energy efficiency levels. Finally, the proposed method is done in the MATLAB platform, and the performance is compared with other methods. [ABSTRACT FROM AUTHOR]