What question did this study set out to answer?

The aim is to enhance the accuracy of solving nonlinear heat conduction problems using a new PINN framework.

An enhanced physics-informed deep learning framework for solving variable-coefficient heat conduction problems with temperature-dependent thermal conductivity and nonlinear source terms

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved accuracy in solving heat conduction challenges, indicating practical benefits for complex boundary conditions.

The aim is to enhance the accuracy of solving nonlinear heat conduction problems using a new PINN framework.
Developed a variable-coefficient PINN framework for transient nonlinear heat conduction problems.
Conducted numerical experiments to compare the proposed method against standard PINNs, finite difference and finite element methods.
Assessed accuracy using L2 and L∞ error metrics and maximum error reports.
Achieved L2 and L∞ errors as low as 10−6 and mean squared errors reaching 10−8.
Reduced maximum error for discontinuous coefficients down to approximately 10−6, improving over previous studies.
Showed improved accuracy and stability compared to standard PINNs and traditional numerical methods.

Tessema et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved accuracy in solving heat conduction challenges, indicating practical benefits for complex boundary conditions.

The aim is to enhance the accuracy of solving nonlinear heat conduction problems using a new PINN framework.
Developed a variable-coefficient PINN framework for transient nonlinear heat conduction problems.
Conducted numerical experiments to compare the proposed method against standard PINNs, finite difference and finite element methods.
Assessed accuracy using L2 and L∞ error metrics and maximum error reports.
Achieved L2 and L∞ errors as low as 10−6 and mean squared errors reaching 10−8.
Reduced maximum error for discontinuous coefficients down to approximately 10−6, improving over previous studies.
Showed improved accuracy and stability compared to standard PINNs and traditional numerical methods.

Tessema et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark