Groundbreaking Battery Research Poised for Revolutionary Impact
New research into using artificial intelligence (AI) to optimise lithium battery recycling could see major environmental and economic benefits. Scientists from the University of East London (UEL), the University of Lincoln and NEX Power have developed a framework for using AI which promises to make it easier to reuse lithium, meaning less waste and greater efficiency.
The framework serves as a valuable guide for researchers and practitioners looking to integrate machine learning into this field. The research focused on three key areas. One was AI’s potential in predicting battery recycling viability and optimizing recycling processes. Another examined how machine learning can address engineering challenges within recycling. The final area of research looked at how to use the framework itself to apply AI to make lithium battery recycling more efficient.
One of the researchers involved in the project, UEL Senior Lecturer in Computer Science and Digital Technologies, Dr Mohammad Hossein Amirhosseini, said the work was a major step forward,
The results of this study are very significant for the industry as battery recycling for lithium batteries offers economic and environmental challenges and lithium sources are limited.”
The growing use of lithium batteries in electric vehicles, laptops, phones and tablets has led to rapidly growing demand for the metal. The World Economic Forum forecasts that demand for it will increase sixfold by 2030, making recycling even more important. But traditional recycling methods face significant challenges in terms of greenhouse gas emissions, economic viability and the recovery of valuable materials. To address these challenges, there is a need to develop efficient and scalable recycling processes.
Dr Amirhosseini thinks this is where AI can help. He said, “Artificial intelligence has the potential to revolutionise the approach for reusing vital minerals and battery metals such as lithium, steering us toward an economy that is greener, more sustainable, and more efficient.”
The newly developed framework provides significant advantages compared to previous models. By providing more details on the pre-processing, feature engineering and evaluation phases, it enables researchers with low technical skills to apply machine learning models in their analysis and product development.
The research was carried out by Dr Amirhosseini in collaboration with Dr Alireza Valizadeh of NEX Power and Dr Yousef Ghorbani from the University of Lincoln. Their paper, Predictive Precision in Battery Recycling: Unveiling Lithium Battery Recycling Potential through Machine Learning was published in the journal Computers & Chemical Engineering.