Digital Twin Modeling for Smart Car Battery

Abstract

The electric car’s (EC) performance depends on its battery condition, recharging, and useful life. Therefore, it is imperative to design a model to effectively manage the battery life cycle to achieve efficient and reliable EC. This can be achieved through the application of the Digital Twin (DT) model. Absorbent glass mat (AGM) lead-acid batteries of 12 volts, 150 Ah, Internet of things (IoT), sensors, cloud computing technologies, etc. are used for this study. Though, there is sufficient literature on smart car battery management and prediction only a few studies have been able to address the variable characteristics of the battery. This experimental study seeks to model EC battery management by using DT. The application of DT in smart manufacturing has shown that DT can model variable battery conditions. An experimental study was carried out on EC in three main areas which include performance evaluation, real-life data generation, and battery prediction. This study provides a platform for EC users to monitor EC performance in real life. This is achieved by assembling the right set of sensors, RFID via IoT to enable the EC operations by digital data transmission and processing through cloud computing. The results recorded during the performance evaluation are stored in the cloud, and the real data generated are used to stimulate the EC battery performance by using algorithms and Artificial intelligence (AI). Also, the EC battery prediction is used to determine the EC speed in km/h, Frequency of rotation in RPM, and battery remaining useful life in real-time. This study provides the stakeholders with the assurance to adequately estimate the distance EC can cover before the battery is recharged, and helps to estimate the useful life of the battery.