A length ratio based neural network energy management strategy for online control of plug-in hybrid electric city bus

•Neural network was applied to interpret mechanisms of optimal control commands.•Length ratio was chosen as the neural network module input variable to represent trip information.•The simplified neural network module structure can reduce calculation time and memory usage of micro-controller.•Neural network based energy management strategy can be used online effectively.•The proposed strategy can be regarded as an approximated global optimal energy management strategy. Because of the limited resources of micro-controller, rule-based energy management strategies are still very popular for online control of plug-in hybrid electric vehicles, however, the control results may deviate from the optimal control results. Since the city bus routes are predetermined, the speed profiles of the certain bus route do not make much difference, this indeed creates an opportunity to design a novel energy management strategy that can reduce the micro-controller resources usage and achieve close to optimal control performance. To accomplish these goals, the single parameter of length ratio was introduced to represent trip information, and a novel efficient neural network module structure was designed to reduce the calculation time and memory usage of micro-controller. Finally, the length ratio based neural network energy management strategy was proposed for online control of plug-in hybrid electric city bus. Simulation results show that the proposed strategy can greatly decrease the total cost compared with the charge-depleting and charge-sustaining control strategy and can be regarded as an approximated global optimal energy management strategy.