Application of machine learning to guide efficient metal leaching from spent lithium-ion batteries and comprehensively reveal the process parameter influences

Abstract

Recycling spent lithium-ion batteries (LIBs) has been a global hot spot due to the increasing scrap amount and enriching valuable resources. Acid leaching is the crucial step of hydrometallurgy recycling metals from spent LIB. However, the uncontrollable components cause many trials for obtaining the optimal leaching parameters, which increases the recycling cost and environmental risk. Herein, this study applied machine learning (ML) to guide metal leaching from spent LIBs and could quickly obtain the leaching results without the vast leaching experiments. After referring to the relative studies between 2005 and 2022, a total of 17,588 data points were collected as the dataset for ML. The process parameter influences of metal leaching were comprehensively revealed through the ML analysis of 20 input features and 4 output metal leaching efficiency. Then, a convenient graphical user interface (GUI) was developed to guide efficient metal leaching from spent LIBs, only measuring the particle size and composition of waste and avoiding extensive leaching experiments. Finally, some experiments verified the GUI reliability. This study can significantly reduce the experiment cost and environmental risk, which trailblazes the smart and efficient recycling of spent LIBs.