2

Structural design through reinforcement learning
The paper introduces SOgym, an open-source reinforcement learning environment for topology optimization.
Thomas Rochefort-Beaudoin, Aurelian Vadean, Niels Aage, Sofiane Achiche
PDF Cite Code Source Document DOI
Structural design through reinforcement learning
From density to geometry: Instance segmentation for reverse engineering of optimized structures
This paper presents YOLOv8-TO, a novel method using a custom YOLOv8 model to automate the reverse engineering of topology-optimized structures into parametric forms, significantly outperforming traditional skeletonization methods in accuracy and efficiency.
Thomas Rochefort-Beaudoin, Aurelian Vadean, Sofiane Achiche, Niels Aage
PDF Cite Code Dataset Source Document DOI Try it out!
From density to geometry: Instance segmentation for reverse engineering of optimized structures
Complexity-driven layout exploration for aircraft structures
The study presents complexity-driven layout exploration for aircraft structures (CD-LEAS), a novel process for efficient topology optimization. Case studies confirm CD-LEAS’s ability to produce simple, light, stiff, and buckling-resistant layouts.
Jean-François Gamache, Aurelian Vadean, Mario Capo, Thomas Rochefort-Beaudoin, Nicolas Dodane, Sofiane Achiche
PDF Cite Source Document
Complexity-driven layout exploration for aircraft structures
Supervised deep learning for the moving morphable components topology optimization framework
This research leverages a deep learning model to improve scalability in topology optimization, with a new approach that reduces computation time by 36.84% and maintains mechanical performance.
Thomas Rochefort-Beaudoin, Aurelian Vadean, Jean-François Gamache, Sofiane Achiche
Cite Source Document DOI
Supervised deep learning for the moving morphable components topology optimization framework