Search

• TIP-EMS enhances EV energy efficiency by integrated prediction and energy management. • Significant driving economy boost; 1.6%-4.2% better than state-of-the-art PEMS. • TIP-EMS shows robust performance with varying prediction weight adjustments. To enhance the energy efficiency of electrified vehicles (EVs), developing effective energy management strategies (EMS) for hybrid storage systems is essential. Predictive EMS (PEMS) that foresee future vehicle speeds have demonstrated substantial potential in boosting EMS performance. However, traditional PEMS models, employing a sequential approach of speed prediction followed by energy allocation, are hampered by cumulative errors. These errors from the initial speed predss this issue, this paper introduces a novel solution: the trainable integrated preiction negatively impact the efficiency of subsequent energy management. To addrediction and energy management strategy (TIP-EMS). Contrasting with conventional sequential PEMS, TIP-EMS features a dual-branch, integrated neural network, which is fully trainable. This network processes driving status inputs via attention layers, with one branch dedicated to energy management objectives using a reinforcement learning (RL) algorithm, and the other to vehicle speed prediction. Both branches are trained simultaneously, but post-training, only the RL branch is activated for energy management. Implemented with a soft actor-critic RL algorithm, TIP-EMS is applied to a fuel cell EV for optimized energy management. The validation involved training TIP-EMS using 27 driving profiles, which developed its prediction and energy management capabilities, followed by tests in untrained scenarios. The results show that TIP-EMS surpasses conventional sequential PEMS by up to 4.2% in scenarios where prediction accuracies are comparable, highlighting the efficacy of the trainable integrated mechanism. In addition, TIP-EMS exhibits superior energy conservation compared to non-predictive RL strategies. Lastly, TIP-EMS exhibits robustness to adjustments in the weight given to the prediction objective, further confirming its practical applicability. [ABSTRACT FROM AUTHOR]

• An experimentally validated system-level model of a fuel cell electric vehicle. • Fuel cell electric vehicle is simulated with a coupled multi-domain model. • Model comprises multiple scales from intra-fuel cell phenomena to the vehicle level. • Model comprises a fuel cell and battery aging model. • Model enables multi-objective optimisation of component sizing and control strategy. One of the key challenges in the design of fuel cell vehicles arises from the need for the simultaneous optimisation of their efficiency and lifetime, which is, in particular, challenging when operating under transient operating conditions; further, the minimisation of costs and the use of critical materials should be considered. To enable a more detailed virtual exploration of the design space, this paper presents a high-fidelity multi-domain and multi-scale model of a fuel cell electric vehicle that is capable of modelling the coupled phenomena from the vehicle level to intra-fuel cell level with a mechanistically based fuel cell model. The high-fidelity multi-domain and multi-scale model of a fuel cell electric vehicle is based on consistent coupling of different domains, that is, mechanical, electrical, electrochemical, gas flow, thermal, and control, which are modelled with mechanistic governing equations coupled to empirical degradation models of electrochemical devices and solved with multirate solvers ensuring flux conservations and synchronization of time steps. Establishing a consistent model based causal interactions between different domains and the significantly different scales associated with the phenomena in these domains, which more consistently virtually replicates the phenomena in a real fuel cell electric vehicle, is crucial for evaluating the impact of the parameters from high scales on intra-fuel cell spatio-temporal characteristics impacting fuel cell degradation. The results demonstrate that the application of an experimentally validated multi-domain and multi-scale model of a fuel cell electric vehicle enables the virtual exploration of interactions considering the scale of vehicle characteristics and its driving pattern to the scale of intra-fuel cell spatio-temporal characteristics and its degradation early in the development stages of the fuel cell electric vehicle. Therefore, the proposed approach represents a valuable contribution to the virtualisation of the system-level design of powertrains of fuel cell electric vehicles and supports front loading in the development process. [ABSTRACT FROM AUTHOR]