Dataset for "Fast structural analysis of concrete thin-shells using deep learning"

1504 119 19155 2 76587 document 19155 requirements.txt text/plain 9ac97ebece99e187fc33b99afa691db0 MD5 3596 2025-06-07 10:51:03 https://researchdata.bath.ac.uk/1504/2/requirements.txt 1504 2 2 text/plain other en public cc_by

requirements.txt

documentation 19156 3 76593 document 19156 models.zip application/zip ddb5ad417a3e1c1c2861885b52add172 MD5 213959314 2025-06-07 11:01:11 https://researchdata.bath.ac.uk/1504/3/models.zip 1504 3 3 application/zip other This folder contains the trained deep learning models used to achieve the predictive performances highlighted in the research article. Files formats: PyTorch (.pth). en public cc_by

models.zip

data 19157 5 76595 document 19157 datasets.py text/x-script.python 74312c80a79c30f220c0d42d727c26d0 MD5 11355 2025-06-07 11:17:31 https://researchdata.bath.ac.uk/1504/4/datasets.py 1504 4 4 text/x-script.python other A Python script with classes that can be used to load the datasets. en public cc_mit

datasets.py

code 19158 3 76599 document 19158 results.zip application/zip a81aa7a9fa68c16351506eda82acd35f MD5 3296668280 2025-06-07 11:33:14 https://researchdata.bath.ac.uk/1504/5/results.zip 1504 5 5 application/zip other This folder contains the predictions made by the deep learning models, which were used to calculate used to the predictive performances highlighted in the research article. Files formats: PyTorch (.pth). en public cc_by

results.zip

data 19159 6 76602 document 19159 metrics.py text/x-script.python cd8a8ffa37a4129a8d841cac1d8d17d6 MD5 6537 2025-06-07 11:35:02 https://researchdata.bath.ac.uk/1504/6/metrics.py 1504 6 6 text/x-script.python other A Python script with error metrics classes. en public cc_mit

metrics.py

code 19160 7 76605 document 19160 models.py text/x-script.python a0a527040d45a5a58216e14f5715006c MD5 14467 2025-06-07 11:35:55 https://researchdata.bath.ac.uk/1504/7/models.py 1504 7 7 text/x-script.python other A Python script with the deep learning model classes. en public cc_mit

models.py

code 19161 6 76608 document 19161 tools.py text/x-script.python c2a65a1f1be7d82ffa7a9d83516efc19 MD5 11515 2025-06-07 11:37:09 https://researchdata.bath.ac.uk/1504/8/tools.py 1504 8 8 text/x-script.python other A Python script that contains some tool functions. en public cc_mit

tools.py

code 19162 6 76611 document 19162 train_CNN_buckling.py text/x-script.python dfa00b63a1ab2c8dada99406de3e877c MD5 13300 2025-06-07 11:38:08 https://researchdata.bath.ac.uk/1504/9/train_CNN_buckling.py 1504 9 9 text/x-script.python other A Python script that can be used to train and evaluate a CNN for buckling prediction. en public cc_mit

train_CNN_buckling.py

code 19163 6 76614 document 19163 train_CNN_stress.py text/x-script.python 7d69919b8ebf7f75b77c7e4bca735bd0 MD5 16487 2025-06-07 11:39:28 https://researchdata.bath.ac.uk/1504/10/train_CNN_stress.py 1504 10 10 text/x-script.python other A Python script that can be used to train and evaluate a CNN for stress prediction. en public cc_mit

train_CNN_stress.py

code 19164 6 76617 document 19164 train_GNN_buckling.py text/x-script.python c5c1e9a2cc2c5f0b515b509931193ae9 MD5 13808 2025-06-07 11:40:35 https://researchdata.bath.ac.uk/1504/11/train_GNN_buckling.py 1504 11 11 text/x-script.python other A Python script that can be used to train and evaluate a GNN for buckling prediction. en public cc_mit

train_GNN_buckling.py

code 19165 6 76620 document 19165 train_GNN_stress.py text/x-script.python 1e08bc5d41476ef52f933ed53fe63f8f MD5 14682 2025-06-07 11:41:32 https://researchdata.bath.ac.uk/1504/12/train_GNN_stress.py 1504 12 12 text/x-script.python other A Python script that can be used to train and evaluate a GNN for stress prediction. en public cc_mit

train_GNN_stress.py

code 19166 6 76623 document 19166 train_MLP_buckling.py text/x-script.python c5b30417fc2af8127ef0c4ee13245949 MD5 12406 2025-06-07 11:42:14 https://researchdata.bath.ac.uk/1504/13/train_MLP_buckling.py 1504 13 13 text/x-script.python other A Python script that can be used to train and evaluate a MLP for buckling prediction. en public cc_mit

train_MLP_buckling.py

code 19167 6 76626 document 19167 train_MLP_stress.py text/x-script.python 2e6ed293c7e42fda50f6461a93afb054 MD5 15637 2025-06-07 11:42:50 https://researchdata.bath.ac.uk/1504/14/train_MLP_stress.py 1504 14 14 text/x-script.python other A Python script that can be used to train and evaluate a MLP for stress prediction. en public cc_mit

train_MLP_stress.py

code 19168 1 76646 document 19168 indexcodes.txt text/plain fbd9ab508cee8d25053af51766fe8bb3 MD5 1775 2025-06-07 11:59:19 https://researchdata.bath.ac.uk/1504/15/indexcodes.txt 1504 15 15 text/plain other Generate index codes conversion from other to indexcodes en public

indexcodes.txt

http://eprints.org/relation/isVersionOf https://researchdata.bath.ac.uk/id/document/19155 http://eprints.org/relation/isVolatileVersionOf https://researchdata.bath.ac.uk/id/document/19155 http://eprints.org/relation/isIndexCodesVersionOf https://researchdata.bath.ac.uk/id/document/19155 19256 2 81614 document 19256 README.md text/plain f07c17d1587e7de315ee09f690030c2e MD5 5578 2026-02-09 10:31:22 https://researchdata.bath.ac.uk/1504/16/README.md 1504 16 16 text/plain other en public cc_by

README.md

documentation archive 12262 disk0/00/00/15/04 2026-02-09 10:37:14 2026-02-14 05:55:58 2026-02-09 10:37:14 data_collection show Pollet Maxime mp2333@bath.ac.uk 0000-0002-1894-1998 University of Bath TRUE Shepherd Paul ps281@bath.ac.uk 0000-0001-7078-4232 University of Bath FALSE Hawkins Will wh604@bath.ac.uk 0000-0003-4918-7665 University of Bath FALSE Costa Eduardo Eduardo.Costa@uwe.ac.uk 0000-0002-3113-9270 University of Bath FALSE Dataset for "Fast structural analysis of concrete thin-shells using deep learning" CP0120 dept_civ_eng Concrete, Thin-shell, Finite Element Analysis, Machine Learning, Deep Learning, Buckling, Stress The original folder structure is given in README.md. To reproduce it, create a folder "FastStructuralAnalysisOfConcreteThinShellsUsingDeepLearning" and extract the "models.zip" and "results.zip" folders inside. Additionally, create a "scripts" folder and store all Python scripts inside. The path to the ConcreteShellFEA dataset needs to be specified in each script, under the DATASET_ROOT variable. This dataset contains scripts and data supporting the following research article: Pollet, M., Shepherd, P., Hawkins, W., and Costa, E., 2026. Fast structural analysis of concrete thin-shells using deep learning. Computers & Structures, 320, 108042. Concrete thin-shells are materially efficient structures, which can be used to reduce the environmental impact of concrete structures. Their shape is typically determined iteratively and evaluated through Finite Element Analysis (FEA). This research proposes the use of surrogate models as faster alternatives to FEA, thus enabling wider design space exploration. This dataset contains deep learning models – Multilayer Perceptrons, Convolutional Neural Networks, and Graph Neural Networks – that have been trained to predict the buckling factor and stress fields of concrete thin-shells of various shapes under design loads. It also contains the Python scripts that were used to train these models and assess their performance. Running these scripts necessitates the associated ConcreteShellFEA dataset to be downloaded. Further details about this data can be found in the related research article. 2026-02-09 University of Bath public RightsHolder University of Bath University of Bath https://doi.org/10.13039/501100000835 PhD studentship cent_dmade Full details of the methodology used may be found in the associated article. The data in the models and results folders was generated using the Python code in scripts folder. These scripts rely on the dependencies listed in requirements.txt. https://doi.org/10.1016/J.COMPSTRUC.2025.108042 en 1 10.15125/BATH-01504 https://doi.org/10.15125/BATH-01519 data https://doi.org/10.1016/J.COMPSTRUC.2025.108042 pub other Dataset