Integration and Usage of Artificial Intelligence Systems in Parametric Generation / an Experiment

This article presents the development process of a parametric application for design and architecture, designed to generate customizable three-dimensional structures through a modular, spiral, and deformable logic.The software tool enables the creation of complex spatial forms by controlling geometric parameters and applying spatial transformations within an intuitive graphical interface.The application was developed in Python [1], using essential opensource libraries: PyQt5 for the graphical interface, Trimesh for geometry generation, and Open3d for real-time interactive visualization.The project began with the procedural generation of spiral-stacked cubic modules and gradually evolved to include various geometric primitives, advanced deformation techniques, and scaling in real physical units.Additional features, such as wireframe visualization and .OBJ export, ensure compatibility with external 3D design workflows [2] (e.g., Blender, Rhino).This experimental project, with an applied research component, demonstrates how parametric thinking and accessible computational tools can be integrated into a unique generative framework, enabling real-time exploration of architectural form and beyond.The resulting application provides both pedagogical value and professional applicability in the field of computational design and digital prototyping, up to a physical development stage including 3D printing.The experiment illustrates the applicability of artificial intelligence programs and thus becomes a potential starting point for integrating and using these new technologies in future applications that can generate or analyze structures from the conceptualization process of forms. Introduction.In recent years, procedural generation of threedimensional forms has gained increased interest in architecture, engineering, product design and the visual arts.Software applications that enable parametric modeling of structures offer high levels of flexibility, efficiency and creativity, being essential for rapid prototyping, form studies, spatial simulations and computer-aided manufacturing.These tools are no longer just a technical support, but become co-authors of the design process, allowing fast exploration of variants and alternative scenarios (Jaechang Ko, John Ajibefun, Wei Yan, 2025, Generative AI-powered parametric modeling and BIM for architectural design and visualization).The present project aims to develop a parametric 3D application dedicated to generating deformable spiral structures and, in a more advanced stage, volumetric fractal networks that grow along the same trajectory.The user controls the real physical dimensions of the modules (width, height, depth), deformation (twist and noise), global curvature (bend on the X

Authors

Institutions

Publication Details

Published
2026-11-17
DOI
https://doi.org/10.54508/archex.2.04
Primary Topic
Architecture and Computational Design
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Integration and Usage of Artificial Intelligence Systems in Parametric Generation / an Experiment

Roland Edgar Vasiliu
2 links
Architecture and Computational Design
article

Integration and Usage of Artificial Intelligence Systems in Parametric Generation / an Experiment

Roland Edgar Vasiliu
article en

Abstract

This article presents the development process of a parametric application for design and architecture, designed to generate customizable three-dimensional structures through a modular, spiral, and deformable logic.The software tool enables the creation of complex spatial forms by controlling geometric parameters and applying spatial transformations within an intuitive graphical interface.The application was developed in Python [1], using essential opensource libraries: PyQt5 for the graphical interface, Trimesh for geometry generation, and Open3d for real-time interactive visualization.The project began with the procedural generation of spiral-stacked cubic modules and gradually evolved to include various geometric primitives, advanced deformation techniques, and scaling in real physical units.Additional features, such as wireframe visualization and .OBJ export, ensure compatibility with external 3D design workflows [2] (e.g., Blender, Rhino).This experimental project, with an applied research component, demonstrates how parametric thinking and accessible computational tools can be integrated into a unique generative framework, enabling real-time exploration of architectural form and beyond.The resulting application provides both pedagogical value and professional applicability in the field of computational design and digital prototyping, up to a physical development stage including 3D printing.The experiment illustrates the applicability of artificial intelligence programs and thus becomes a potential starting point for integrating and using these new technologies in future applications that can generate or analyze structures from the conceptualization process of forms. Introduction.In recent years, procedural generation of threedimensional forms has gained increased interest in architecture, engineering, product design and the visual arts.Software applications that enable parametric modeling of structures offer high levels of flexibility, efficiency and creativity, being essential for rapid prototyping, form studies, spatial simulations and computer-aided manufacturing.These tools are no longer just a technical support, but become co-authors of the design process, allowing fast exploration of variants and alternative scenarios (Jaechang Ko, John Ajibefun, Wei Yan, 2025, Generative AI-powered parametric modeling and BIM for architectural design and visualization).The present project aims to develop a parametric 3D application dedicated to generating deformable spiral structures and, in a more advanced stage, volumetric fractal networks that grow along the same trajectory.The user controls the real physical dimensions of the modules (width, height, depth), deformation (twist and noise), global curvature (bend on the X

Vol. 2
Ion Mincu University of Architecture and Urbanism (RO)
Architecture and Computational Design
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