Journal of Renewable and Sustainable Energy, Год журнала: 2023, Номер 15(6)

Опубликована: Ноя. 1, 2023

CO2 heat pump air conditioning (HPAC) systems for electric vehicles (EVs) have received widespread attention their excellent low-temperature heating capabilities. However, the range of EVs is limited by battery energy storage, which makes demand system affect use efficiency drive battery. In order to measure thermal economy (AC) in terms heating, index coefficient performance (COP) often used. Accurate COP prediction can help optimize HPAC avoid wastage and thus improve vehicle. this study, we a backpropagation (BP) neural network combined with particle swarm optimization (PSO) algorithm predict EVs. First, model was established, consider variety influencing factors, key parameters affecting AC were obtained through experiments. Second, BP used system, overcome shortcomings network, slow prone fall into minimum value, PSO introduced weights biases so as accuracy stability prediction. Through combine achieve accurate an EV, provides strong support improvement efficiency. considered such outdoor temperature, compressor speed, EV status, made more applicable. Finally, method proposed study validated on real dataset, using 65.8%.

Язык: Английский