Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-Model-Based Conceptual Design of Pedestrian Bridges

被引：5

作者：

Balmer, Vera ^{[1
,2
]}

Kuhn, Sophia V. ^{[1
,2
]}

Bischof, Rafael ^{[2
,3
]}

Salamanca, Luis ^{[2
,3
]}

Kaufmann, Walter ^{[1
,2
]}

Perez-Cruz, Fernando ^{[3
,4
]}

Kraus, Michael A. ^{[1
,2
]}

机构：

[1] Swiss Fed Inst Technol, Inst Struct Engn, Stefano Franscini Pl 5, CH-8093 Zurich, Switzerland

[2] Swiss Fed Inst Technol, Ctr Augmented Computat Design Architecture Engn &, Wolfgang Pauli Str 27, CH-8093 Zurich, Switzerland

[3] Swiss Data Sci Ctr SDSC, Andreasstr 5, CH-8092 Zurich, Switzerland

[4] Univ Str 6, CH-8006 Zurich, Switzerland

来源：

AUTOMATION IN CONSTRUCTION | 2024年 / 163卷

关键词：

Computational design; Design space exploration; Generative AI; Conditional Variational Autoencoder; Explainable AI; Pedestrian bridge; PARAMETRIC DESIGN; OPTIMIZATION;

D O I：

10.1016/j.autcon.2024.105411

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

Today, engineers rely on conventional iterative (often manual) techniques for conceptual design. Emerging parametric models facilitate design space exploration based on quantifiable performance metrics, yet remain time-consuming and computationally expensive, leaving room for improvement. This paper provides a design exploration and explanation framework to augment the designer via a Conditional Variational Autoencoder (CVAE), which serves as a forward performance predictor as well as an inverse design generator conditioned on a set of performance requests. Hence, the CVAE overcomes the limitations of traditional iterative techniques by learning a differentiable mapping for a highly nonlinear design space, thus enabling sensitivity analysis. These methods allow for informing designers about (i) relations of the model between features and performances and (ii) structural improvements under user-defined objectives. The framework is tested on a case-study and proves its potential to serve as a future co-pilot for conceptual design studies of diverse civil structures and beyond.

引用

页数：38