Determining the Condition of the Batteries in Electric Vehicles and Calculating Rural Driving Range Applications using Machine Learning

By putting forward Machine learning technique method to forecast the driving range and Battery State of Charge (SOC) ) of electric cars (EVs) in rural settings, this work seeks to fill the gap in the literature. The suggested method takes into account the trio main groups of elements that affect Vehicle SOC and EV range specifications, driver conduct and the atmosphere of exploitation. This is in contrast to the literature, which found a deficiency of a complete model that takes into account all significant aspects influencing EV range prediction. An OBD (On-Board Diagnostics) gadget that is linked to the driver's car supplied the driving cycle (RDC) data from the actual world that was used in this investigation The outcome of our investigation display Considering The suggested educational by machine method could forecast the state of charge (SOC) of lithium-ion batteries with a 95% accuracy rate on average. Despite the notable variations in RDC information as well as the presence of measurement sound, this loud level of precision was achieved. Using a mean inaccuracy of under 2 percent, the recommended learning by machine method was furthermore successful in properly predicting using the expected SOC values, calculate EVs' residual driving range (RDR).