Основные понятия
A novel neural network architecture, Transport-Embedded Neural Network (TENN), shows promise in simulating fluid mechanics problems by embedding physical transport laws directly into its structure, leading to improved accuracy and stability compared to traditional Physics-Informed Neural Networks (PINNs).
Статистика
The relative error of TENN in predicting the Taylor-Green vortex dynamics was approximately 4% for relatively high Reynolds numbers.
The maximum error in TENN's predictions occurred at half the domain period, where the vorticity magnitude was minimal.