Learning to Simulate and Design for Structural Engineering

Kai-Hung Chang, Chin-Yi Cheng
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:1426-1436, 2020.

Abstract

The structural design process for buildings is time-consuming and laborious. To automate this process, structural engineers combine optimization methods with simulation tools to find an optimal design with minimal building mass subject to building regulations. However, structural engineers in practice often avoid optimization and compromise on a suboptimal design for the majority of buildings, due to the large size of the design space, the iterative nature of the optimization methods, and the slow simulation tools. In this work, we formulate the building structures as graphs and create an end-to-end pipeline that can learn to propose the optimal cross-sections of columns and beams by training together with a pre-trained differentiable structural simulator. The performance of the proposed structural designs is comparable to the ones optimized by genetic algorithm (GA), with all the constraints satisfied. The optimal structural design with the reduced the building mass can not only lower the material cost, but also decrease the carbon footprint.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-chang20a, title = {Learning to Simulate and Design for Structural Engineering}, author = {Chang, Kai-Hung and Cheng, Chin-Yi}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {1426--1436}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/chang20a/chang20a.pdf}, url = {http://proceedings.mlr.press/v119/chang20a.html}, abstract = {The structural design process for buildings is time-consuming and laborious. To automate this process, structural engineers combine optimization methods with simulation tools to find an optimal design with minimal building mass subject to building regulations. However, structural engineers in practice often avoid optimization and compromise on a suboptimal design for the majority of buildings, due to the large size of the design space, the iterative nature of the optimization methods, and the slow simulation tools. In this work, we formulate the building structures as graphs and create an end-to-end pipeline that can learn to propose the optimal cross-sections of columns and beams by training together with a pre-trained differentiable structural simulator. The performance of the proposed structural designs is comparable to the ones optimized by genetic algorithm (GA), with all the constraints satisfied. The optimal structural design with the reduced the building mass can not only lower the material cost, but also decrease the carbon footprint.} }
Endnote
%0 Conference Paper %T Learning to Simulate and Design for Structural Engineering %A Kai-Hung Chang %A Chin-Yi Cheng %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-chang20a %I PMLR %P 1426--1436 %U http://proceedings.mlr.press/v119/chang20a.html %V 119 %X The structural design process for buildings is time-consuming and laborious. To automate this process, structural engineers combine optimization methods with simulation tools to find an optimal design with minimal building mass subject to building regulations. However, structural engineers in practice often avoid optimization and compromise on a suboptimal design for the majority of buildings, due to the large size of the design space, the iterative nature of the optimization methods, and the slow simulation tools. In this work, we formulate the building structures as graphs and create an end-to-end pipeline that can learn to propose the optimal cross-sections of columns and beams by training together with a pre-trained differentiable structural simulator. The performance of the proposed structural designs is comparable to the ones optimized by genetic algorithm (GA), with all the constraints satisfied. The optimal structural design with the reduced the building mass can not only lower the material cost, but also decrease the carbon footprint.
APA
Chang, K. & Cheng, C.. (2020). Learning to Simulate and Design for Structural Engineering. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:1426-1436 Available from http://proceedings.mlr.press/v119/chang20a.html.

Related Material