Search NASA⌕ Search

Engineering topics

Castonguay, Stephen

Publications and source records attributed to Castonguay, Stephen.

PhyML

Python scripts for physics informed machine learning for time-dependent problems. The code implements hard constrained sequential physics-informed neural networks (HCSPINNs) using JAX library. The details of the method and implementation can be found in the following paper: Roy, P., & Castonguay, S. (2024). Exact Enforcement of Temporal Continuity in Sequential Physics- Informed Neural Networks. arXiv preprint arXiv:2403.03223. (https://arxiv.org/abs/2403.03223)

Roy, Pratanu↗

Water sorption equilibrium and dynamics on Epon 828-Epikure 3125

Epon 828-Epikure 3125 absorbs a significant amount of water (up to 4 weight percent), but diffusion of water into the material is slow. A one cm thick open slab may take 80 days to reach equilibrium at 70 °C and five years at 20 °C.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗