| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Late News Poster Session
|
| Presentation Title |
N-25: Machine Learning for Joint Quality Performance-A Comparative Study of the Relationship between Process Parameters and Joint Performance of Al/Steel Resistance Spot Welds |
| Author(s) |
Moses Obiri, Alejandro Ojeda, Deb Fagan |
| On-Site Speaker (Planned) |
Moses Obiri |
| Abstract Scope |
10% vehicle weight loss improves fuel economy by 6-8%. Aluminum's strength-to-weight ratio reduces vehicle mass, but it binds poorly with other metals. Spot welding uses electric current and pressure to connect aluminum and low carbon steel. Spot weld quality depends on joint performance and processing parameters. Traditional statistical methodologies don't provide a thorough understanding of welding process evolution due to data structure and variable number. To overcome this gap, supervised and unsupervised machine learning algorithms were used to identify the main elements that determine aluminum and steel joint features and performance and to predict the process parameters required to make joints with preset performance. The results and comparisons between two aluminum types are utilized to create uniform designs to examine the parametric space of the best performing joints and give exploratory recommendations. |
| Proceedings Inclusion? |
Undecided |
| Keywords |
Aluminum, Computational Materials Science & Engineering, Characterization |