About this Abstract |
Meeting |
MS&T23: Materials Science & Technology
|
Symposium
|
Materials Processing and Fundamental Understanding Based on Machine Learning and Data Informatics
|
Presentation Title |
Process Cycle Modeling with AI |
Author(s) |
Vyacheslav Romanov |
On-Site Speaker (Planned) |
Vyacheslav Romanov |
Abstract Scope |
Modeling the process‐structure‐property‐performance relationships hidden in materials data can be accelerated without loss of interpretability, with artificial intelligence tools that mimic the salient features of the process and process-structure relations. Here a convoluted process model-filtering technique is presented that can build and successfully train the structural property artifacts of materials after multiple heat treatment cycles. The artifacts were pre-trained on Fe-based alloy data to filter out deep models that did not reflect the domain knowledge. The Graph based approach facilitated development of the microstructure evolution models with reduced overfitting to limited datasets. |