The specificities of temperature-dependent electrochemical modelling strategies of 18650 Li-ion batteries were investigated in pseudo-2D, 2D and 3D domains using finite element analysis. Emphasis was placed on exploring the challenges associated with the geometric representation of the batteries in each domain, as well as analysing the performance of coupled thermal-electrochemical models. The results of the simulations were compared with real reference measurements, where temperature data were collected using temperature sensors and a thermal camera. It was highlighted that the spiral geometry provides the most realistic results in terms of the temperature distribution, as its layered structure allows for a detailed realisation of the radial heat transfer within the cell. On the other hand, the 3D-lumped thermal model is able to recover the temperature distribution in the axial direction of the cell and to reveal the influence of the cell cap and the cell wall on the thermal behaviour of the cell. The effect of cooling is an important factor that can be introduced in the models as a boundary condition by heat convection or heat flux. It has been shown that both regulated and unregulated (i.e., natural) cooling conditions can be achieved using an appropriate choice of the rate and type of cooling applied.

On account of intense technological advances regarding Electric Vehicles, the state evaluation and prediction issues of Li-ion cells have become increasingly important for ensuring the competitiveness in terms of feasible performance and range. Albeit the wide investigation of various standard modelling and estimation techniques, only limited researches focus on their precision and applicability under heavy transient working conditions. This paper is concerned with Li-ion battery terminal voltage and State-of-Charge (SoC) prediction for two types of dynamic loads. Attention is focused on the investigation of the applicability of direct multi-step forecasting strategy in combination with Machine Learning. Beside that, a feature bank is composed of discharge profiles obtained at different C-rates. The set of discharge curves is proposed to complement the feature extraction, i.e. the additional historical data is considered for model building. Special care is devoted for the design of appropriate training data. Hence, a battery cell model is built for simulating intensive dynamic load scenarios in addition to the experimental setup. The cell model is validated by using measurement data. Results have demonstrated, that in case of WLTP-type discharge load of 0.3C-rate the forecasting performance is highly efficient on measurement data. Under dynamic loads of 1C-rate, or when small historical data is available, the application of feature bank improves the performance. We have obtained comprehensive results proving that the application of direct multi-step forecasting strategy using XGBoost represents a viable alternative to capture real-time the cell dynamics and predict the terminal voltage and SoC of Li-ion batteries exposed to dynamic loads.