Optimal power split control strategy for plug-in biofuel-electric hybrid vehicle using improvised adaptive ECMS control algorithm

Hybrid electric powertrains are the most suitable and optimal option to solve the incessant increase in pollution by automotive vehicles. Even, when it is operated with renewable fuels, they are further support for the energy crisis. In this aspect, this research work is performed using a brushless direct current electric motor and bio-fuel-powered diesel engine-incorporated plug-in hybrid electric vehicle. Here the aim is to incorporate intelligent control with the adaptive equivalent consumption minimization strategy (A-ECMS) to improve the optimal power split, so that the proposed intelligent module dynamically estimates the appropriate equivalence factor (EF) required in the ECMS algorithm for any unknown drive cycle. The intelligent approaches which have been incorporated here are the fuzzy logic and genetic algorithmically optimized adaptive neuro-fuzzy inference system (ANFIS) controller and employed the three hybrid standard driving cycles for training the fuzzy inference system and for complete performance validation. Based on the obtained results the variance at the terminal SOC of fuzzy-PI is higher than the ANFIS; this shows the stable control of EF corresponding to battery SOC feedback is performed in the ANFIS. The suggested ANFIS-ECMS achieves closer to desired terminal SOC of 30%. The driving cycle (D1) is 29.41%, driving cycle (D2) is 28.22%, and the driving cycle (D3) is 28.37%. Also, the ANFIS-A-ECMS achieves a terminal SOC of 27.53% and a fuel efficiency of 33.37 km/l in real-time validation for the self-developed real-world driving cycle which is 34.69% and 24.52% higher than the rule-based and conventional A-ECMS. The overall findings of this work demonstrate that the suggested approach delivers considerable advancements in battery and energy usage operation as well as emissions reductions when compared to rule-based, conventional fixed PI ECMS and fuzzy-PI-based ECMS.