| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Late News Poster Session
|
| Presentation Title |
Machine Learning for Joint Quality Performance-A Comparison Study of the Relationship between Process Parameters and Weld Microstructure of Al/Steel Resistance Spot Welds |
| Author(s) |
Alejandro Ojeda, Moses Obiri |
| On-Site Speaker (Planned) |
Alejandro Ojeda |
| Abstract Scope |
The qualities of resistance spot welding (RSW) of aluminum to steel are being explored in order to reduce vehicle weight and hence boost fuel efficiency. Resistance spot welding of Al and steel results in a layer of brittle intermetallic compounds along the Al and steel sheets' contact. Previous research has described the parameters of microstructure variables (fracture mode, hardness, and thickness) in the intermetallic layer formed by RSW of Al - steel welds. In contrast, the role of weld process parameters in the weld intermetallic layer has yet to be well studied. For two Al types, we employ supervised machine learning algorithms to determine essential welding parameters that result in excellent weld microstructure and intermetallic layer characteristics. The results are compared between the two different types of aluminum, and they are utilized to plan intelligent experiment design in a subset of the parameter space, which ultimately leads to production optimization. |
| Proceedings Inclusion? |
Undecided |
| Keywords |
Machine Learning, Aluminum, |