Energy management of an FC/UC hybrid vehicular power system using a combined neural network-wavelet transform based strategy

An energy management strategy (EMS) is one of the most important issues for the efficiency and performance of a hybrid vehicular system. This paper deals with a neural network and wavelet transform based EMS proposed for a fuel cell/ultra-capacitor hybrid vehicular system. The proposed method combines the capability of wavelet transform to treat transient signals with the ability of auto-associative neural network supervisory mode control. The main originality of the paper is related with the application of neural network instead of another intelligent control method, fuzzy logic, which is presented in the recent publication of the authors, and the combination of neural network-wavelet transform approaches. Then, the effectiveness comparison of both methods considering one of the most important points in a vehicular system, fuel consumption (or hydrogen consumption), is realized. The mathematical and electrical models of the hybrid vehicular system are developed in detail and simulated using MATLAB®, Simulink® and SimPowerSystems® environments.