What type of study is this?

September 10, 2025Physics of Fluids

Mixed convection physical-informed neural networks for flow reconstruction with sparse thermal data and partial physics in a lid-driven cavity

View Full Paper

Ask AI

Bookmark

Authors

Novel mixed convection physics-informed neural networks enhance flow reconstruction using sparse thermal data, indicating improved efficiency.

The MC-PINN accurately reconstructs velocity fields with R2 > 99% using only 0.1% sparse thermal measurements.
By employing Fourier feature embeddings and an augmented Lagrangian method, the MC-PINN captures complex multi-scale flow features.
Bayesian inference is utilized for hyperparameter optimization, significantly improving model accuracy in mixed convection heat transfer problems.
With a training efficiency improvement of 57%–58.4% over traditional PINNs, the model demonstrates robustness against data noise.

Zhang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

September 10, 2025Physics of Fluids

View Full Paper

Ask AI

Bookmark

Authors

Novel mixed convection physics-informed neural networks enhance flow reconstruction using sparse thermal data, indicating improved efficiency.

The MC-PINN accurately reconstructs velocity fields with R2 > 99% using only 0.1% sparse thermal measurements.
By employing Fourier feature embeddings and an augmented Lagrangian method, the MC-PINN captures complex multi-scale flow features.
Bayesian inference is utilized for hyperparameter optimization, significantly improving model accuracy in mixed convection heat transfer problems.
With a training efficiency improvement of 57%–58.4% over traditional PINNs, the model demonstrates robustness against data noise.

Zhang et al. (2025) studied this question.

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark