A Data-Driven Workflow for Modelling Self-Shaping Wood Bilayer, Utilizing Natural Material Variations with Machine Vision and Machine Learning
Z. Akbar, D. Wood, L. Kiesewetter, A. Menges, and T. Wortmann. Post Carbon - Proceedings of the 27th International Conference on Computer-Aided Architectural Design Research in Asia, 1, page 393-402. The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong, CAADRIA, (2022)
DOI: 10.52842/conf.caadria.2022.1.393
Abstract
This paper develops a workflow to train machine learning (ML) models with a small dataset from physical samples to predict the curvatures of self-shaping wood bilayers based on local variations in the grain. In contrast to state-of-the-art predictive models, specifically 1.) a 2D Timoshenko model and 2.) a 3D numerical model with a rheological model, our method accounts for natural and unavoidable material variations. In this paper, we only focus on local grain variations as the main driver for curvatures in small-scale material samples. We extracted a feature matrix from grain images of active and passive layers as a Grey Level Co-Occurrence Matrix and used it as the input for our ML models. We also analysed the impact of grain variations on the feature matrix. We trained and tested several tree-based regression models with different features. The models achieved very accurate predictions for curvatures in each sample (R²>0.9) and extend the range of parameters that is incalculable by a Timoshenko model. This research contributes to the material-efficient design of weather-responsive shape-changing wood structures by further leveraging the use of natural material features and explainable data-driven modelling and extends the topic in ML for material behaviour-driven design among the CAADRIA community.
%0 Conference Paper
%1 Akbar_2022
%A Akbar, Zuardin
%A Wood, Dylan
%A Kiesewetter, Laura
%A Menges, Achim
%A Wortmann, Thomas
%B Post Carbon - Proceedings of the 27th International Conference on Computer-Aided Architectural Design Research in Asia
%D 2022
%E van Ameijde, Jeroen
%E Gardner, Nicole
%E Hyun, Kyung Hoon
%E Dan, Luo
%E Sheth, Urvi
%I CAADRIA
%K P266 ai from:zuardinakbar matpro myown peer
%P 393-402
%R 10.52842/conf.caadria.2022.1.393
%T A Data-Driven Workflow for Modelling Self-Shaping Wood Bilayer, Utilizing Natural Material Variations with Machine Vision and Machine Learning
%U https://doi.org/10.52842%2Fconf.caadria.2022.1.393
%V 1
%X This paper develops a workflow to train machine learning (ML) models with a small dataset from physical samples to predict the curvatures of self-shaping wood bilayers based on local variations in the grain. In contrast to state-of-the-art predictive models, specifically 1.) a 2D Timoshenko model and 2.) a 3D numerical model with a rheological model, our method accounts for natural and unavoidable material variations. In this paper, we only focus on local grain variations as the main driver for curvatures in small-scale material samples. We extracted a feature matrix from grain images of active and passive layers as a Grey Level Co-Occurrence Matrix and used it as the input for our ML models. We also analysed the impact of grain variations on the feature matrix. We trained and tested several tree-based regression models with different features. The models achieved very accurate predictions for curvatures in each sample (R²>0.9) and extend the range of parameters that is incalculable by a Timoshenko model. This research contributes to the material-efficient design of weather-responsive shape-changing wood structures by further leveraging the use of natural material features and explainable data-driven modelling and extends the topic in ML for material behaviour-driven design among the CAADRIA community.
%@ 978-988-78917-7-2
@inproceedings{Akbar_2022,
abstract = {This paper develops a workflow to train machine learning (ML) models with a small dataset from physical samples to predict the curvatures of self-shaping wood bilayers based on local variations in the grain. In contrast to state-of-the-art predictive models, specifically 1.) a 2D Timoshenko model and 2.) a 3D numerical model with a rheological model, our method accounts for natural and unavoidable material variations. In this paper, we only focus on local grain variations as the main driver for curvatures in small-scale material samples. We extracted a feature matrix from grain images of active and passive layers as a Grey Level Co-Occurrence Matrix and used it as the input for our ML models. We also analysed the impact of grain variations on the feature matrix. We trained and tested several tree-based regression models with different features. The models achieved very accurate predictions for curvatures in each sample (R²>0.9) and extend the range of parameters that is incalculable by a Timoshenko model. This research contributes to the material-efficient design of weather-responsive shape-changing wood structures by further leveraging the use of natural material features and explainable data-driven modelling and extends the topic in ML for material behaviour-driven design among the CAADRIA community.},
added-at = {2023-01-16T14:38:26.000+0100},
author = {Akbar, Zuardin and Wood, Dylan and Kiesewetter, Laura and Menges, Achim and Wortmann, Thomas},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2aa2298e7d59ec644844f9e5ee6afc366/icd},
booktitle = {Post Carbon - Proceedings of the 27th International Conference on Computer-Aided Architectural Design Research in Asia},
doi = {10.52842/conf.caadria.2022.1.393},
editor = {van Ameijde, Jeroen and Gardner, Nicole and Hyun, Kyung Hoon and Dan, Luo and Sheth, Urvi},
eventdate = {9-15 April 2022},
interhash = {0a074ddf73e648573166e2d3e23500ac},
intrahash = {aa2298e7d59ec644844f9e5ee6afc366},
isbn = {978-988-78917-7-2},
issn = {2710-4257 (Print) / 2710-4265 (Online)},
keywords = {P266 ai from:zuardinakbar matpro myown peer},
language = {English},
organization = {The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong},
pages = {393-402},
preprinturl = {https://caadria2022.org/wp-content/uploads/2022/04/277-1.pdf},
publisher = {{CAADRIA}},
timestamp = {2023-02-05T22:58:05.000+0100},
title = {A Data-Driven Workflow for Modelling Self-Shaping Wood Bilayer, Utilizing Natural Material Variations with Machine Vision and Machine Learning},
url = {https://doi.org/10.52842%2Fconf.caadria.2022.1.393},
venue = {Sydney, Australia},
volume = 1,
year = 2022
}