Benoit Jordan
Papers
1
Total Citations
145
H-Index
1
About
Benoit Jordan is a leading figure in the computational mechanics of polymers, with a core focus on developing physics-informed neural network models to predict complex material behaviors. His most influential work, a 2020 paper with 145 citations, introduced a neural network framework that accurately captures the temperature- and rate-dependent stress-strain response of polypropylene—a breakthrough for designing durable polymer components under real-world loading conditions. By integrating experimental data with machine learning, Jordan’s model bypasses traditional constitutive equations, offering a scalable approach for predicting nonlinear viscoelastic and plastic deformation. This contribution has been widely adopted in automotive and aerospace industries for fatigue and crashworthiness simulations. Beyond this landmark study, Jordan has advanced hybrid modeling techniques that merge physical laws with data-driven methods, enabling robust predictions even with sparse datasets. His work bridges the gap between classical solid mechanics and modern AI, earning him recognition as a pioneer in the emerging field of mechano-informatics. For students and researchers, Jordan’s research exemplifies how neural networks can transform the simulation of rate- and temperature-sensitive materials, opening new avenues for virtual material design and digital twins.
Research Focus
Key Achievements
Top Papers
- 1