A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Performance-Based Generative Design for Parametric Modeling of Engineering Structures Using Deep Conditional Generative Models
https://orcid.org/0000-0002-5254-6131
https://orcid.org/0000-0002-5000-2923
https://orcid.org/0000-0003-3722-8132
https://orcid.org/0000-0002-1015-4770
Abstract Parametric Modeling, Generative Design, and Performance-Based Design have gained increasing attention in the AEC field as a way to create a wide range of design variants while focusing on performance attributes rather than building codes. However, the relationships between design parameters and performance attributes are often very complex, resulting in a highly iterative and unguided process. In this paper, we argue that a more goal-oriented design process is enabled by an inverse formulation that starts with performance attributes instead of design parameters. A Deep Conditional Generative Design workflow is proposed that takes a set of performance attributes and partially defined design features as input and produces a complete set of design parameters as output. A model architecture based on a Conditional Variational Autoencoder is presented along with different approximate posteriors, and evaluated on four different case studies. Compared to Genetic Algorithms, our method proves superior when utilizing a pre-trained model.
Highlights Complex 2D/3D models hinder understanding of relationships in Generative Design. Deep Conditional Generative Design learns joint distribution for targeted designs. Inverse formulation enables precise control for Performance-Based Generative Design. Our Conditional Variational Autoencoder is evaluated against Genetic Algorithms. Expressive posterior improves performance; partial conditioning shows promise.
Performance-Based Generative Design for Parametric Modeling of Engineering Structures Using Deep Conditional Generative Models
https://orcid.org/0000-0002-5254-6131
https://orcid.org/0000-0002-5000-2923
https://orcid.org/0000-0003-3722-8132
https://orcid.org/0000-0002-1015-4770
Abstract Parametric Modeling, Generative Design, and Performance-Based Design have gained increasing attention in the AEC field as a way to create a wide range of design variants while focusing on performance attributes rather than building codes. However, the relationships between design parameters and performance attributes are often very complex, resulting in a highly iterative and unguided process. In this paper, we argue that a more goal-oriented design process is enabled by an inverse formulation that starts with performance attributes instead of design parameters. A Deep Conditional Generative Design workflow is proposed that takes a set of performance attributes and partially defined design features as input and produces a complete set of design parameters as output. A model architecture based on a Conditional Variational Autoencoder is presented along with different approximate posteriors, and evaluated on four different case studies. Compared to Genetic Algorithms, our method proves superior when utilizing a pre-trained model.
Highlights Complex 2D/3D models hinder understanding of relationships in Generative Design. Deep Conditional Generative Design learns joint distribution for targeted designs. Inverse formulation enables precise control for Performance-Based Generative Design. Our Conditional Variational Autoencoder is evaluated against Genetic Algorithms. Expressive posterior improves performance; partial conditioning shows promise.
Performance-Based Generative Design for Parametric Modeling of Engineering Structures Using Deep Conditional Generative Models
https://orcid.org/0000-0002-5254-6131
https://orcid.org/0000-0002-5000-2923
https://orcid.org/0000-0003-3722-8132
https://orcid.org/0000-0002-1015-4770
Abstract Parametric Modeling, Generative Design, and Performance-Based Design have gained increasing attention in the AEC field as a way to create a wide range of design variants while focusing on performance attributes rather than building codes. However, the relationships between design parameters and performance attributes are often very complex, resulting in a highly iterative and unguided process. In this paper, we argue that a more goal-oriented design process is enabled by an inverse formulation that starts with performance attributes instead of design parameters. A Deep Conditional Generative Design workflow is proposed that takes a set of performance attributes and partially defined design features as input and produces a complete set of design parameters as output. A model architecture based on a Conditional Variational Autoencoder is presented along with different approximate posteriors, and evaluated on four different case studies. Compared to Genetic Algorithms, our method proves superior when utilizing a pre-trained model.
Highlights Complex 2D/3D models hinder understanding of relationships in Generative Design. Deep Conditional Generative Design learns joint distribution for targeted designs. Inverse formulation enables precise control for Performance-Based Generative Design. Our Conditional Variational Autoencoder is evaluated against Genetic Algorithms. Expressive posterior improves performance; partial conditioning shows promise.
Performance-Based Generative Design for Parametric Modeling of Engineering Structures Using Deep Conditional Generative Models
Bucher, Martin Juan José (author) / Kraus, Michael Anton (author) / Rust, Romana (author) / Tang, Siyu (author)
2023-10-10
Article (Journal)
Electronic Resource
English
Early-Phase Performance-Driven Design Using Generative Models
| British Library Conference Proceedings | 2022
Application of Deep Generative Models in the Design of Buildings and Structures
| Springer Verlag | 2024