Rank reduction autoencoders for mechanical design: Learning structured latent manifolds for topology optimization

This work presents a data-driven framework for fast forward and inverse analyses in topology optimization by combining Rank Reduction Autoencoders with neural latent-space mappings. The methodology targets the efficient approximation of the relationship between optimized geometries and their corresponding mechanical responses or quantities of interest with a particular focus on compliance-minimized linear elastic structures. High-dimensional topology optimization results are first compressed using Rank Reduction Autoencoders, which encode the data into low-dimensional manifolds via Singular Value Decomposition, thus extracting the most important (latent) features. Separate Rank Reduction Autoencoder models are trained for geometry and for different types of quantities of interest, including scalar metrics, one-dimensional stress fields, and full two-dimensional von Mises stress distributions. The resulting low-dimensional latent manifolds are then related through multilayer perceptrons to address both direct problems – predicting structural responses from geometry – and inverse problems—recovering geometries from prescribed performance targets. The proposed approach is demonstrated on a half MBB beam and a cantilever beam, with the latter studied under separate and simultaneous variations in volume fraction and load position, using datasets generated via density-based Solid Isotropic Material with Penalization optimization. Numerical results show that the framework enables accurate and computationally efficient surrogate models, with increasing robustness and fidelity as richer quantities of interest are considered. The methodology also shows potential for generative mechanical design through preliminary examples of new geometries and response synthesis via latent-space exploration.

Authors

Institutions

Publication Details

Journal
Computers & Structures
Published
2026-11-13
DOI
https://doi.org/10.1016/j.compstruc.2026.108534
Citations
3
Primary Topic
Topology Optimization in Engineering
Type
article
Field-Weighted Citation Impact
5.66

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Rank reduction autoencoders for mechanical design: Learning structured latent manifolds for topology optimization

Mohammed El Fallaki Idrissi, Jad Mounayer, Sebastian Rodriguez, Ismael Ben-Yelun et al.
3 citations
Computers & Structures
Topology Optimization in Engineering
5.66
article

Rank reduction autoencoders for mechanical design: Learning structured latent manifolds for topology optimization

Mohammed El Fallaki Idrissi, Jad Mounayer, Sebastian Rodriguez, Ismael Ben-Yelun, Francisco Chinesta
article en
3 citations

Abstract

This work presents a data-driven framework for fast forward and inverse analyses in topology optimization by combining Rank Reduction Autoencoders with neural latent-space mappings. The methodology targets the efficient approximation of the relationship between optimized geometries and their corresponding mechanical responses or quantities of interest with a particular focus on compliance-minimized linear elastic structures. High-dimensional topology optimization results are first compressed using Rank Reduction Autoencoders, which encode the data into low-dimensional manifolds via Singular Value Decomposition, thus extracting the most important (latent) features. Separate Rank Reduction Autoencoder models are trained for geometry and for different types of quantities of interest, including scalar metrics, one-dimensional stress fields, and full two-dimensional von Mises stress distributions. The resulting low-dimensional latent manifolds are then related through multilayer perceptrons to address both direct problems – predicting structural responses from geometry – and inverse problems—recovering geometries from prescribed performance targets. The proposed approach is demonstrated on a half MBB beam and a cantilever beam, with the latter studied under separate and simultaneous variations in volume fraction and load position, using datasets generated via density-based Solid Isotropic Material with Penalization optimization. Numerical results show that the framework enables accurate and computationally efficient surrogate models, with increasing robustness and fidelity as richer quantities of interest are considered. The methodology also shows potential for generative mechanical design through preliminary examples of new geometries and response synthesis via latent-space exploration.

Computers & StructuresVol. 334
Centre National de la Recherche Scientifique (FR), Arts et Métiers (FR), Laboratoire Procédés et Ingénierie en Mécanique et Matériaux (FR), Universidad Politécnica de Madrid (ES)
European Commission
Openalex Percentile: Top 6%
Topology Optimization in Engineering
5.66
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon