Jingyuan Tang

PhD thesis: TBC

Research interests:

1. Mechanical behaviour of materials
2. Data driven mechanics
3. Public Policy
4. Machine Learning

My PhD project aims to establish a new framework for material characterization by combining advanced 3D imaging with data-driven modelling. Instead of relying on numerous traditional tests, I will develop methods to capture complete stress and strain fields from a single specimen using Flux Enhanced Tomography Correlation and Energy Dispersive X-ray Diffraction. These high-fidelity datasets will then be integrated with modern machine learning tools, particularly recurrent neural networks, to directly derive accurate constitutive laws and design new materials with fully tunable mechanical properties. This approach not only streamlines the testing process but also creates a direct link between experiments and predictive models, paving the way for faster and more reliable design of next-generation structural materials.

Who or what inspired you to pursue your research interests?

I am inspired by the vision of transforming how materials are studied and designed. Traditional testing is often slow and fragmented, while modern imaging and machine learning open the possibility of seeing the entire picture of material behaviour in 3D. The idea that we can capture detailed experimental data and immediately turn it into predictive models for designing new materials motivates me. I am particularly driven by the opportunity to create approaches that accelerate innovation in material characterization and design, ultimately supporting technological progress across multiple industries.