Sustainable Metallurgy
Lithium-Ion Battery Optimisation with AI and Machine Learning
Project Lead: Nima Emami
In this project, we are developing a framework using data-driven and machine learning methods to optimize and design new recycling processes. We also aim to develop a new sustainability metric for the evaluation of recycling processes.
Partner(s): Rodrigo Serna Guerrero, Department of Chemical and Metallurgical Eng, Aalto, Finland
RL-driven Optimisation for Sustainable Recycling Design
Project Lead: Masoud Jalayer
Relative Statistical Entropy (RSE) of a recycling process measures how efficiently the procedure separates individual materials from waste. We combine reinforcement learning (RL) with process simulations to re-formulate recycling. We seek to balance material separation, material quality, process cost, time, and energy efficiency for next-generation recycling of Li-ion batteries.
Partner(s): Rodrigo Serna Guerrero, Department of Chemical and Metallurgical Eng, Aalto, Finland
Identifying Critical Energy Materials from Microscopy Images of Battery Waste
Project Lead: Reza Amrollaheian
Scanning electron microscopy (SEM) images of crushed battery waste reveal the raw materials within. We combine computer vision with machine learning to analyze the composition of black mass. This information can be used to improve the separation and recovery of critical materials in battery recycling.
Partner(s): Rodrigo Serna Guerrero, Department of Chemical and Metallurgical Eng, Aalto, Finland