About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Artificial Intelligence Applications in Integrated Computational Materials Engineering (AI-ICME)
|
| Presentation Title |
Data-Driven Design of Two-Phase Metallic Spinodoids for Thermomechanical Properties |
| Author(s) |
Saltuk Yildiz, Zekeriya Ender Eger, Pinar Acar |
| On-Site Speaker (Planned) |
Zekeriya Ender Eger |
| Abstract Scope |
Spinodoid metamaterials are inspired by the material phase transition phenomenon known as “Spinodal Decomposition”. They exhibit inherently stochastic geometries due to their formulation based on Gaussian Random Fields (GRFs), which emulate the spontaneous characteristic of the decomposition process. Spinodoid structures are shown to achieve increased performance compared to conventional materials as a result of their novel architectures and highly tunable design spaces. In this study, a convolutional neural network (CNN) model is developed to solve a multi-objective optimization problem for metal-metal spinodoid composites considering thermal and mechanical objectives. Finite element simulations are performed to create the data used to train the deep learning model. This model is integrated into a gradient-free optimization algorithm to optimize composite spinodoids to enhance thermal and mechanical performance. To the best of our knowledge, this is the first study investigating the design of composite spinodoids for both mechanical and thermal properties. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Mechanical Properties, Computational Materials Science & Engineering |