Digital Twins for Lithium-Ion Battery Health Monitoring with Linked Clustering Model using VGG 16 for Enhanced Security Levels

Abstract

Digital Twin (DT) has only been widely used since the early 2000s. The concept of DT refers to the act of creating a computerized replica of a physical item or physical process. There is the physical world, the cyber world, a bridge between them, and a portal from the cyber world to the physical world. The goal of DT is to create an accurate digital replica of a previously existent physical object by combining AI, IoT, deep learning, and data analytics. Using the virtual copy in real time, DTs attempt to describe the actions of the physical object. Battery based DT's viability as a solution to the industry's growing problems of degradation evaluation, usage optimization, manufacturing irregularities, and possible second-life applications, among others, are of fundamental importance. Through the integration of real-time checking and DT elaboration, data can be collected that could be used to determine which sensors/data used in a batteries to analyze their performance. This research proposes a Linked Clustering Model using VGG 16 for Lithium-ion batteries health condition monitoring (LCM-VGG-Li-ion-BHM). This work explored the use of deep learning to extract battery information by selecting the most important features gathered from the sensors. Data from a digital twin analyzed using deep learning allowed us to anticipate both typical and abnormal conditions, as well as those that required closer attention. The proposed model when contrasted with the existing models performs better in health condition monitoring.