Neural Network Based Online Eco-Driving Strategy for Plug-In Hybrid Electric Bus

An online eco-driving strategy (EDS) for a plug-in hybrid electric bus (PHEB) is proposed focusing on fuel economy improvement. This EDS achieves the optimization objective via adjusting demand power within acceptable boundaries based on the driver behavior and the vehicle state. Two procedures are included in the EDS namely offline optimization and online implementation. First, dynamic programming (DP) is applied to optimize power profile using global optimization state of charge (SOC) profile as a benchmark to simplify three dimensions DP, therefore reducing the heavy computational duty caused by the structure characteristics of PHEB. Then neural network with four input variables of accelerator pedal position, vehicle velocity, battery SOC, vehicle acceleration and one output variable of power adjustment value produces an online control strategy based on offline optimization results. Simulation using untrained driving cycle data indicates 2.72\% fuel consumption reduction compared to the strategy without eco- driving.

[1]  Yong Huang,et al.  A length ratio based neural network energy management strategy for online control of plug-in hybrid electric city bus , 2016 .

[2]  Zheng Chen,et al.  Energy Management for a Power-Split Plug-in Hybrid Electric Vehicle Based on Dynamic Programming and Neural Networks , 2014, IEEE Transactions on Vehicular Technology.

[3]  Randall Guensler,et al.  Eco-driving for transit: An effective strategy to conserve fuel and emissions , 2017 .

[4]  Dimitar Filev,et al.  Adaptive real-time advisory system for fuel economy improvement in a hybrid electric vehicle , 2009, NAFIPS 2009 - 2009 Annual Meeting of the North American Fuzzy Information Processing Society.

[5]  Eva Ericsson,et al.  Independent driving pattern factors and their influence on fuel-use and exhaust emission factors , 2001 .

[6]  Bo Cheng,et al.  Fuel-Saving Servo-Loop Control for an Adaptive Cruise Control System of Road Vehicles With Step-Gear Transmission , 2017, IEEE Transactions on Vehicular Technology.

[7]  Bedatri Moulik,et al.  Optimized Powermanagement for Human Driver-HEV Using Online Identification of Velocity Patterns , 2015, 2015 IEEE Vehicle Power and Propulsion Conference (VPPC).

[8]  Rochdi Trigui,et al.  Eco-Driving Rules Extraction from a Model Based Optimization for a New Generation EV , 2015, 2015 IEEE Vehicle Power and Propulsion Conference (VPPC).

[9]  Hao Ying,et al.  Real time Advisory System for Fuel Economy Improvement in a Hybrid Electric Vehicle , 2008, NAFIPS 2008 - 2008 Annual Meeting of the North American Fuzzy Information Processing Society.