Chenyu Xue

As power sources for electric vehicles, lithium-ion batteries (LIBs) have many advantages, such as high energy density and wide temperature range. In the algorithm design process for LIBs, various battery models with different model structures are needed, among which the electrochemical model is widely used due to its high accuracy. However, the electrochemical model is composed of multiple nonlinear partial differential equations (PDEs) that make the simulating process time-consuming. In this paper, a physics-informed neural network single-particle model (PINN SPM) is proposed to improve the accuracy of the single-particle model (SPM) under high C-rates, while ensuring high solving speed. In PINN SPM, an SPM-Net is designed to solve the distribution of lithium-ion concentration in the electrolyte. In the neural network learning process, a loss function is designed based on the physical constraints brought by the PDEs, which reduces the error of the neural network under dynamic working conditions. Finally, the PINN SPM proposed in this paper can achieve a maximum relative error of up to 1.2% compared with the high-fidelity data generated from the P2D model under various conditions. Additionally, the PINN SPM is 20.8% faster than traditional numerical solution methods with the same computational resources.

In this paper, the efficiency benefits of adopting Silicon–Carbide devices for electric vehicle applications are studied. A hybrid time and frequency domain-based simulation tool is developed for the Silicon–Carbide (SiC) traction inverter modeling. The tool provides steady-state results with comparable accuracy to standard time domain methods and achieves a factor of thousand reductions in time when simulating a large number of operating points. Especially, the impact of temperature-dependent device losses has been considered to ensure the simulation precision. Next, a vehicle-level modeling is developed to evaluate the impact of the inverter efficiency on the endurance mileage increase of vehicles. It is found that, by applying Silicon–Carbide devices, the energy consumption of the inverter can be greatly reduced by 3/4 under WLTC (World light light-duty vehicle test cycle) profile. It can be transformed into a mileage endurance increase of 3–5%. The impact of the drive cycle profile and the vehicle’s drag coefficient on the endurance mileage are evaluated as well. In addition, an economic/cost model is developed for selecting the “optimal” chip paralleling number for Silicon–Carbide power modules. Interestingly, the results indicate that this number should be slightly overdesigned to achieve the most cost saving from the system point of view.