Adaptive neuro fuzzy inference system-based energy management controller for optimal battery charge sustaining in biofuel powered non-plugin hybrid electric vehicle

Abstract

In the hybrid electric vehicle, better performance can be acquired by implementing an optimized energy management strategy. The purpose of this work is to improve the efficiency of the energy management strategy for a biofuel-powered hybrid electric vehicle (HEV). The energy management system opted for this work is adaptive equivalent consumption minimization strategy (AECMS) with PI, fuzzy and adaptive neuro-fuzzy logic-based equivalence factor (EF) value adjustment. The appropriate selection of equivalence factor value in AECMS decides the optimal performance of an energy management. This entire work uses three standard combined driving cycles for training the intelligent controller and has been tested using a real-time driving cycle. The proposed adaptive neuro-fuzzy controller implemented in the AECMS energy management strategy provides the best results in terms of charging and discharging within defined operating limit of 40%-70% state of charge, delivers lower fuel economy and emissions compared to rule-based and fuzzy-PI AECMS. Adaptive neuro-fuzzy AECMS improves the fuel economy by 3% compared to 25.3 km/l of fuzzy-PI AECMS for the standard combined driving cycle (D1). Whereas for the D2 and D3 driving cycles 0.5–1% improvement has occurred. This work strives to prove that the proposed adaptive neuro-fuzzy AECMS controller is efficient and provide better fuel economy and lesser emissions.