Lithium-Ion Battery Classification and Detection Using an Optimal Machine Learning Algorithm

Abstract

In today's civilization, lithium-ion batteries (LIBs) are essential energy storage technologies. In terms of energy density, power density, cycle life, safety, etc., the performance and cost are still unsatisfactory. Traditional "trial-and-error" procedures necessitate a large number of time-consuming trials to further enhance battery performance. The End-of-life (EOL) LIBs come in a variety of shapes and sizes, which makes it difficult to automate a few unit processes (such cell-level disassembly) of the recycling process. Meanwhile, LIBs contain dangerous and combustible components, posing serious risks to human exposure. In this paper, we anticipate the various crystal system types based on the system's LIB using an optimal machine learning (OML) approach.