arXiv subjects

Pierluigi D'Acunto

Publications and source records attributed to Pierluigi D'Acunto.

4 recordsLinked to original sources

arXiv2026

Text2Structure3D: Graph-Based Generative Modeling of Equilibrium Structures with Diffusion Transformers

This paper presents Text2Structure3D, a graph-based Machine Learning (ML) model that generates equilibrium structures from natural language prompts. Text2Structure3D is designed to support new intuitive ways of design exploration and iteration in the conceptual structural design process. The approach combines latent diffusion with a Variational Graph Auto-Encoder (VGAE) and graph transformers to generate structural graphs that are close to an equilibrium state. Text2Structure3D integrates a residual force optimization post-processing step that ensures generated structures fully satisfy static equilibrium. The model was trained and validated using a cross-typological dataset of funicular form-found and statically determinate bridge structures, paired with text descriptions that capture the formal and structural features of each bridge. Results demonstrate that Text2Structure3D generates equilibrium structures with strong adherence to text-based specifications and greatly improves generalization capabilities compared to parametric model-based approaches. Text2Structure3D represents an early step toward a general-purpose foundation model for structural design, enabling the integration of generative AI into conceptual design workflows.

cs.CE↗

arXiv2025

BridgeNet: A Dataset of Graph-based Bridge Structural Models for Machine Learning Applications

Machine learning (ML) is increasingly used in structural engineering and design, yet its broader adoption is hampered by the lack of openly accessible datasets of structural systems. We introduce BridgeNet, a publicly available graph-based dataset of 20,000 form-found bridge structures aimed at enabling Graph ML and multi-modal learning in the context of conceptual structural design. Each datapoint consists of (i) a pin-jointed equilibrium wireframe model generated with the Combinatorial Equilibrium Modeling (CEM) form-finding method, (ii) a volumetric 3D mesh obtained through force-informed materialization, and (iii) rendered images from two canonical camera angles. The resulting dataset is modality-rich and application-agnostic, supporting tasks such as CEM-specific edge classification and parameter inference, surrogate modeling of form-finding, cross-modal reconstruction between graphs, meshes and images, and generative structural design. BridgeNet addresses a key bottleneck in data-driven applications for structural engineering and design by providing a dataset that facilitates the development of new ML-based approaches for equilibrium bridge structures.

cs.CE↗

arXiv2023

Two-scale analysis and design of spaceframes with complex additive manufactured nodes

The advancements in additive manufacturing (AM) technology have allowed for the production of geometrically complex parts with customizable designs. This versatility benefits large-scale space-frame structures, as the individual design of each structural node can be tailored to meet specific mechanical and other functional requirements. To this end, however, the design and analysis of such space-frames with distinct structural nodes needs to be highly automated. A critical aspect in this context is automated integration of the local 3D features into the 1D large-scale models. In the present work, a two-scale modeling approach is developed to improve the design and linear-elastic analysis of space frames with complex additively manufactured nodes. The mechanical characteristics of the 3D nodes are numerically reduced through an automated dimensional reduction process based on the Finite Cell Method (FCM) and substructuring. The reduced stiffness quantities are assembled in the large-scale 1D model which, in turn, enables efficient structural analysis. The response of the 1D model is passed on to the local model, enabling fully resolved 3D linear-elastic analysis. The proposed approach is numerically verified on a simplified beam example. Furthermore, the workflow is demonstrated on a tree canopy structure with additively manufactured nodes with bolted connections. The form of the large-scale structure is found based on the Combinatorial Equilibrium Modeling framework, and the different designs of the local structural nodes are based on generative exploration of the design space. It is demonstrated that the proposed methodology effectively automates the design and analysis of space-frame structures with complex, distinct structural nodes.

cs.CE↗

arXiv2022

Constrained Form-Finding of Tension-Compression Structures using Automatic Differentiation

This paper proposes a computational approach to form-find pin-jointed, bar structures subjected to combinations of tension and compression forces. The generated equilibrium states can meet force and geometric constraints via gradient-based optimization. We achieve this by extending the combinatorial equilibrium modeling (CEM) framework in three important ways. First, we introduce a new topological object, the auxiliary trail, to expand the range of structures that can be form-found with the framework. Then, we leverage automatic differentiation (AD) to obtain an exact value of the gradient of the sequential and iterative calculations of the CEM form-finding algorithm, instead of a numerical approximation. Finally, we encapsulate our research developments into an open-source design tool written in Python that is usable across different CAD platforms and operating systems. After studying four different structures -- a self-stressed planar tensegrity, a tree canopy, a curved bridge, and a spiral staircase -- we demonstrate that our approach enables the solution of constrained form-finding problems on a diverse range of structures more efficiently than in previous work.

cs.CE↗