Refrigerant substitution is an urgent need in the context of reducing carbon emissions and slowing global warming. CO₂ is now being proposed as a promising solution based on its excellent properties and system performance, especially in low-temperature environments. This paper presents an overview of recent advances in system configuration and operation characteristics to improve the performance of transcritical CO₂ heat pump and refrigeration systems. The paper first introduces the basic research background, system cycle, and thermodynamic characteristics. Secondly, CO₂ cycle improvements with single modifications and modification combinations are reviewed. Then, some important operation characteristics and control methods are discussed. Additionally, the paper provides a detailed description of the development of transcritical CO₂ heat pump and refrigeration systems in the vehicle field. At the end of this review, conclusions and opportunities for future work in this field are presented.

The facial air temperature has a significant impact on the driver’s thermal comfort. Machine Learning models have been proved to be evidently effective in temperature predicting. In this study, three models are employed to predict the drivers’ facial temperature in a certain series of vehicles, which are Support Vector Regression (SVR), Artificial Neural Network (ANN), and Gated Recurrent Unit (GRU) respectively. We conduct an electric vehicle air-conditioning system experiment to collect the datasets of drivers’ head temperature and 6 input features for model training. And we divide the training and testing datasets in two different ways. In these two ways, the testing datasets are the last 20% of datasets in each condition, and the datasets in the last condition respectively. The evaluation of these models’ performance is exerted with Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R2). The MAE of these three models are SVR: 0.8096, ANN: 0.4984, GRU: 0.7289 in the trained working conditions, and SVR: 1.0946, ANN: 0.7878, GRU: 0.7837 in the untrained working conditions. The results of MAE show that the performance of the ANN is the best among the three models when tested with the trained and untrained test datasets, and the same conclusion can be got from the R2 and RMSE. Moreover, the accuracies of these models are lower when the tested dataset is collected in new working conditions. According to the results above, ANN may be the preferred method for vehicle drivers’ facial air temperature prediction.

Frost formation on heat exchanger outside of heat pump air conditioning system will decrease the heat exchange efficiency, thus heating capacity and COP of the system fall with the range of EV. It's necessary to apply a practicable defrost strategy with high efficiency for a normal operating heat pump system. This study presents a review of frost formation's impacts, influence factors, main defrosting manners and the determinant condition of defrosting. It's suggested that defrosting determination from several aspects can improve accuracy and reduce energy consumption.