Physics-informed MTA-UNet: Prediction of Thermal Stress and Thermal Deformation of Satellites

TL;DR

This paper introduces a physics-informed Multi-Task Attention UNet model for real-time satellite thermal stress and deformation prediction, integrating PDEs into training to enhance accuracy especially on small datasets.

Contribution

The paper presents a novel neural network architecture combining multi-task learning, attention mechanisms, and physics-informed training for satellite thermal analysis.

Findings

Improved prediction accuracy over single-task models.

Physics-informed training reduces errors, especially with limited data.

Effective multi-task learning for thermal stress and deformation prediction.

Abstract

The rapid analysis of thermal stress and deformation plays a pivotal role in the thermal control measures and optimization of the structural design of satellites. For achieving real-time thermal stress and thermal deformation analysis of satellite motherboards, this paper proposes a novel Multi-Task Attention UNet (MTA-UNet) neural network which combines the advantages of both Multi-Task Learning (MTL) and U-Net with attention mechanism. Besides, a physics-informed strategy is used in the training process, where partial differential equations (PDEs) are integrated into the loss functions as residual terms. Finally, an uncertainty-based loss balancing approach is applied to weight different loss functions of multiple training tasks. Experimental results show that the proposed MTA-UNet effectively improves the prediction accuracy of multiple physics tasks compared with Single-Task Learning (STL) models. In addition, the physics-informed method brings less error in the prediction of each task, especially on small data sets. The code can be downloaded at: \url{https://github.com/KomorebiTso/MTA-UNet}.