About this Abstract |
Meeting |
Advances in Welding and Additive Manufacturing Research 2022
|
Symposium
|
Advances in Welding and Additive Manufacturing Research 2022
|
Presentation Title |
Accelerated Design of Chromium Carbide Overlays via Design of Experiment and Machine Learning |
Author(s) |
Jing Li, Bing Cao, Haohan Chen, Leijun Li |
On-Site Speaker (Planned) |
Jing Li |
Abstract Scope |
Chromium carbide overlays with MC-type primary carbides have shown a significantly lower cracking susceptibility during overlay welding. However, optimizing the composition and improving the wear-resistant properties of complex alloys have always been difficult by traditional one-variable-at-a-time development methods. Here we propose a method using design of experiments and machine learning through a simple generalized linear model strategy to design new chromium carbide overlays, with a targeted hardness, containing MC-type primary carbides and eutectic matrix with various Nb, Ti, and V combinations. Using this method, a closed-loop alloy design process was developed to enable improvements of the model by collecting data for self-driving laboratories. The efficacy of this method is demonstrated by predicting the simultaneous effects of the carbide formers on overlay hardness, which highlights the possibilities of using machine learning in the alloy design of chromium carbide overlay systems. |
Proceedings Inclusion? |
Undecided |