What question did this study set out to answer?

This research aims to develop a rapid co-simulation framework for predicting thermal and mechanical fields in power modules.

July 10, 2026Microelectronics ReliabilityOpen Access

Accelerated electro-thermo-mechanical co-simulation of power modules using reduced-order modeling and neural network-based field reconstruction

View Full Paper

Ask AI

Bookmark

Authors

COCélestin Ott GPGaëtan Perez PPPierre Perichon

Discussion

Member takes

Overview

Randomized trial demonstrates enhanced efficiency in thermal and mechanical field predictions for SiC power modules, suggesting improved real-time monitoring capabilities.

Key Points

This research aims to develop a rapid co-simulation framework for predicting thermal and mechanical fields in power modules.
Proposed a multi-physics reduced-order framework integrating TAPLM, a Foster network, and a neural network.
Validated framework on a 12-die SiC power module under variable operating conditions.
Achieved maximum field reconstruction errors below ± 1.3 % with over 95% speedup compared to traditional methods.
Successfully achieved full 2D thermal and mechanical fields without any FEM call at inference time.
Field reconstruction errors were maintained below ± 1.3 % across multiple operating conditions.
Demonstrated a 95% computational speedup relative to the traditional SPICE/FEM reference workflow.

Cite This Study

Ott et al. (2026) studied this question.

synapsesocial.com/papers/6a508ea56eeac72a437a15c0 https://doi.org/10.1016/j.microrel.2026.116232

View Full Paper

Ask AI

Bookmark

July 10, 2026Microelectronics ReliabilityOpen Access

Accelerated electro-thermo-mechanical co-simulation of power modules using reduced-order modeling and neural network-based field reconstruction

View Full Paper

Ask AI

Bookmark

Authors

COCélestin Ott GPGaëtan Perez PPPierre Perichon

Discussion

Member takes

Overview

Randomized trial demonstrates enhanced efficiency in thermal and mechanical field predictions for SiC power modules, suggesting improved real-time monitoring capabilities.

Key Points

This research aims to develop a rapid co-simulation framework for predicting thermal and mechanical fields in power modules.
Proposed a multi-physics reduced-order framework integrating TAPLM, a Foster network, and a neural network.
Validated framework on a 12-die SiC power module under variable operating conditions.
Achieved maximum field reconstruction errors below ± 1.3 % with over 95% speedup compared to traditional methods.
Successfully achieved full 2D thermal and mechanical fields without any FEM call at inference time.
Field reconstruction errors were maintained below ± 1.3 % across multiple operating conditions.
Demonstrated a 95% computational speedup relative to the traditional SPICE/FEM reference workflow.

Cite This Study

Ott et al. (2026) studied this question.

synapsesocial.com/papers/6a508ea56eeac72a437a15c0 https://doi.org/10.1016/j.microrel.2026.116232

Also Consider

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

View Full Paper

Ask AI

Bookmark