Work

Variational rank reduction autoencoders for generative thermal design

Year: 2025

Type: article

Abstract: • Application of Variational Rank Reduction Autoencoders (VRRAE) to obtain continuous manifolds for design exploration via linear interpolation. • Use of physics-informed neural networks, particularly DeepONets, for thermal problems based on the interpretable latent variables of the VRRAE. • Design exploration in manifold for generative applications based on physics response outperforming black-box convolutional neural networks. Generative thermal design for complex geometries is fundamental in many areas of engineering, yet it faces two main challenges: the high computational cost of high-fidelity simulations and the limitations of conventional generative models. Approaches such as autoencoders (AEs) and variational autoencoders (VAEs) often produce unstructured latent spaces with discontinuities, which restricts their capacity to explore designs and generate physically consistent solutions. To address these limitations, we propose a hybrid framework that combines Variational Rank-Reduction Autoencoders (VRRAEs) with Deep Operator Networks (DeepONets). The VRRAE introduces a truncated SVD within the latent space, leading to continuous, interpretable, and well-structured representations that mitigate posterior collapse and improve geometric reconstruction. The DeepONet then exploits this compact latent encoding in its branch network, together with spatial coordinates in the trunk network, to predict temperature gradients efficiently and accurately. This hybrid approach not only enhances the quality of generated geometries and the accuracy of gradient prediction, but also provides a substantial advantage in inference efficiency compared to traditional numerical solvers. Overall, the study underscores the importance of structured latent representations for operator learning and highlights the potential of combining generative models and operator networks in thermal design and broader engineering applications.

Source: Results in Engineering

DOI: 10.1016/j.rineng.2025.108418

Authors: Alicia Tierz, Jad Mounayer, Beatriz Moya, Francisco Chinesta

Institutions: Universidad de Zaragoza, Instituto de Investigación en Ingeniería de Aragón, Arts et Métiers, Laboratoire Procédés et Ingénierie en Mécanique et Matériaux, CNRS@CREATE Ltd (Singapore)

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

SDG: Affordable and clean energy

Open Access status: gold

Estimated APC paid: $1,940