Ceramic nanocomposites are important for various structural and energy storage applications. The investigation of the mechanical properties of such materials requires the combination of novel experimental microscale testing combined with labor/time-intensive finite element computations. In this talk, a new approach for ceramic nanocomposite materials characterization based on composite neural networks will be introduced. The capabilities of composite neural networks to significantly accelerate fracture toughness investigations at small scales, without the need for large finite element-generated datasets will be discussed. The accuracy of the proposed approach will be accessed by direct comparisons with single-fidelity machine learning.


Accelerating mechanical characterization of ceramic nanocomposites via composite neural networks

The Virtual Technical Meeting of the Society of Engineering Science 2020 is the first fully virtual meeting of the SES community to envision and connect during the hiatus created by Covid-19, providing a platform for the exchange of ideas, and to showcase the latest research in the field of engineering science.

[Visit the Programme](https://drive.google.com/file/d/1BoCPBzrr1IQFANuzQI8a-paXCJoOcCkB/view?usp=sharing) | [Visit the Prerecorded Video/Poster List](https://drive.google.com/file/d/1XHLeEXJxEFjCSsNScuLDfMwy1X7oy7oJ/view?usp=sharing) | [View the Session Grid](https://drive.google.com/file/d/1VeDOC-Ev5m_ymYjXnjaXSZHR3_DARiLt/view?usp=sharing)