What question did this study set out to answer?

This research aims to develop a computational method to solve the inverse heat conduction problem in complex materials.

Using Neural Networks to Solve the Inverse Problem of Heat Conduction in Complex Bodies

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved recovery of thermophysical parameters in complex bodies, suggesting enhanced heat management strategies.

This research aims to develop a computational method to solve the inverse heat conduction problem in complex materials.
Coupled a finite volume solver with a multilayer perceptron for parameter recovery.
Used large datasets from steady-state heat conduction solutions for training.
Validated on twisted-geometry fuel rod configurations using an unstructured mesh.
MLP achieved prediction errors below 0.034% for single-parameter recovery.
Simultaneous recovery with a three-layer network reduced maximum errors to below 0.02%.
Anisotropic materials showed maximum errors of 0.15% for diagonal conductivity tensor recovery.

Молчанов et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial demonstrates improved recovery of thermophysical parameters in complex bodies, suggesting enhanced heat management strategies.