The development of electric vehicles (EVs) and their power source systems (PSS) is a rapidly growing field of technology. However, the EV's travel distance (range between charging stations) depends on the agility of the PSS, or battery capacity system. EV driving range and battery capacity are the two most significant technical challenges in commercializing EVs. This study aims to propose an integrated model that identifies the optimal energy factor orientation, enabling EVs to cover the maximum travel distance and reach the charging station for their next trip. Additionally, the artificial intelligence (AI) and statistical models were integrated and applied to predict, validate, and explain how energy factors affect the driving range of EVs. The developed models and validations revealed that maintaining precise assimilation of battery power factors can vary the EV's travel distance from 60 to 610 km. In this case, we have identified 77.5 kWh battery capacity and 14.5 kW charging capacity as the optimum power source factors. After 5.5 h of charging, various adjustments to power source factors allow for optimum battery performance. We have also proposed the central composite factorial design (CCFD) to compute the impact of energy factors on travel distance. The study used the response surface methodology (RSM) and an in-house-developed AI-based algorithm to achieve the research results. The alignment percentage between model-predicted data and real-time outputs showed an extremely high precision of over 95 % and confidence in the findings' reliability.
Read full abstract