Background
Aluminium is crucial for the green transition and has been classified by the EU as a critical material. Using recycled aluminium is a big win for sustainability. However, recycling aluminium can introduce various impurities that can affect its quality.
This project aims to use advanced machine learning to better understand the structure and properties of recycled aluminium. The goal is to predict how well large components made from recycled aluminium will perform.
Research question
A recent disruptive manufacturing technology in large-scale high pressure die casting – commonly known as mega-casting, promises the wide adoption of recycled aluminium in high-value applications. However, the interplay of numerous tramp elements and diverse thermomechanical parameters creates a high dimensional space that is challenging to fully explore using traditional experimental and computational methods.
Aim
In this project, the aim is to develop advanced machine learning frameworks to gain a fundamental understanding of the microstructure and mechanical properties of cast recycled aluminium, as well as to accurately predict the performance of large components made of recycled aluminium.
Synergy and Team
To address the aforementioned scientific challenges in materials science related to introducing recycled aluminium in megacasting, a multidisciplinary team of experienced researchers with complementary expertise have been formed. Throughout the project, machine learning will be leveraged as a tool to enhance both information extraction and computational speed, which raises exciting additional research challenges in data science.
All involved research groups are based on the Johanneberg campus of Chalmers University of Technology. This close proximity fosters both formal and informal interactions and strengthens collaboration and teamwork.
Sustainability aspects
The project aims to enable an increased industrial application of recycled (secondary) aluminium alloys. By leveraging machine learning to enhance both material modelling and high throughput microstructure analysis we will provide the tools necessary to understand the impact of tramp elements and thermomechanical parameters on the microstructure and mechanical behavior of such alloys.
Having such tools available will significantly accelerate the discovery of optimised alloy compositions and processing conditions for recycled aluminium.
Contact Main PI
Fang Liu, fang.liu@chalmers.se
Fredrik Kahl, fredrik.kahl@chalmers.se
