Towards Self-learning Energy Management for Optimal PHEV Operation Around Zero Emission Zones

To meet increasingly strict CO2 and pollutant emission targets, development time and costs of vehicle control systems are exploding. This is mainly driven by growing system complexity and the need for optimal performance under real-world operating conditions. As a result, control development is facing a turning point, so there is an urgent need for new, innovative methods. Self-learning control is a promising concept. Based on available information of the actual and predicted system state and its changing environment, the control settings are adapted on-line. Also, this avoids time and cost efficient control calibration. The potential of this concept is demonstrated for energy management in Plug-in Hybrid Electric Vehicles (PHEV). These vehicles are of great interest for the transport sector, since they combine high fuel efficiency with last mile full-electric driving. We focus on a specific use case: PHEV operation through future Zero Emission zones of cities. Compared to earlier work, we introduce a novel, modular energy and emission management (MEEM) strategy that deals with varying constraints and system uncertainty. This optimal control strategy is based on Pontryagin’s Minimum Principle and maximizes overall energy efficiency. The constraints are directly related to sufficient battery energy for full electric driving and to meet real-world tailpipe NOx emissions. For a given mission, the control parameters in MEEM are numerically optimized. Simulations are done using a validated hybrid truck model with Diesel engine and urea-based SCR aftertreatment. To demonstrate the self-learning capabilities, we study the effect of battery aging and changing route (i.e. detour due to unexpected traffic jam). For the specified mission, the performance of the optimal MEEM is compared with a standard MEEM strategy without information on system or environment state. Based on the results of this work, an outlook is given on a self-learning energy management concept.