Dataset for: Multi-Fidelity deep learning for predicting the nonlinear buckling behaviour of concrete thin-shells

1533 145 19182 7 76691 document 19182 datasets.py text/x-script.python fe590d8ffb0c324129214c44ffd66d3f MD5 8906 2025-06-07 12:28:47 https://researchdata.bath.ac.uk/1533/1/datasets.py 1533 1 1 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 19183 7 76694 document 19183 metrics.py text/x-script.python 433edaaccab01285a5a5ccad493a4755 MD5 5605 2025-06-07 12:29:40 https://researchdata.bath.ac.uk/1533/2/metrics.py 1533 2 2 text/x-script.python other A Python script with error metrics classes. en public cc_mit

metrics.py

code 19184 7 76697 document 19184 models.py text/x-script.python d4ad78db7a9b563039cc1498c7ff8302 MD5 1947 2025-06-07 12:30:30 https://researchdata.bath.ac.uk/1533/3/models.py 1533 3 3 text/x-script.python other A Python script with the deep learning model classes. en public cc_mit

models.py

code 19185 7 76700 document 19185 tools.py text/x-script.python caf2d66eead03931284ddb5ee5febed6 MD5 968 2025-06-07 12:31:15 https://researchdata.bath.ac.uk/1533/4/tools.py 1533 4 4 text/x-script.python other A Python script that contains some tool functions. en public cc_mit

tools.py

code 19186 8 76703 document 19186 hf_MLP_varying_dataset_size.py text/plain cbd01888369bf0f2efeff37c8b5e0c60 MD5 6286 2025-06-07 12:32:54 https://researchdata.bath.ac.uk/1533/5/hf_MLP_varying_dataset_size.py 1533 5 5 text/plain other A Python script for the evaluation of the baseline high-fidelity MLPs trained with varying amounts of data. en public cc_by

hf_MLP_varying_dataset_size.py

code 19187 7 76705 document 19187 lf_MLP_varying_dataset_size.py text/plain e6e8988d327b3c4c3fa07a55ec918cdc MD5 6168 2025-06-07 12:33:07 https://researchdata.bath.ac.uk/1533/6/lf_MLP_varying_dataset_size.py 1533 6 6 text/plain other A Python script for the evaluation of low-fidelity MLPs trained with varying amounts of data. en public cc_by

lf_MLP_varying_dataset_size.py

code 19188 8 76707 document 19188 mf_sequential_MLP_varying_dataset_size.py text/plain 02515d39f7ad255cc489955b28f7c0f4 MD5 6740 2025-06-07 12:33:16 https://researchdata.bath.ac.uk/1533/7/mf_sequential_MLP_varying_dataset_size.py 1533 7 7 text/plain other A python script for the evaluation of Multi-Fidelity (sequential) MLPs trained with varying amounts of data. en public cc_by

mf_sequential_MLP_varying_dataset_size.py

code 19189 8 76709 document 19189 mf_transfer_MLP_varying_dataset_size.py text/plain cf1b72322fd344d879b53181c520b5b9 MD5 6519 2025-06-07 12:33:26 https://researchdata.bath.ac.uk/1533/8/mf_transfer_MLP_varying_dataset_size.py 1533 8 8 text/plain other A Python script for the evaluation of Multi-Fidelity (transfer learning) MLPs trained with varying amounts of data. en public cc_by

mf_transfer_MLP_varying_dataset_size.py

code 19190 7 76711 document 19190 train_hf_MLP.py text/x-script.python 491a19ba79cf9ca0650d8bd8b28fae93 MD5 12515 2025-06-07 12:33:36 https://researchdata.bath.ac.uk/1533/9/train_hf_MLP.py 1533 9 9 text/x-script.python other A Python script for the nonlinear buckling prediction using the baseline high-fidelity MLP. en public cc_by

train_hf_MLP.py

code 19191 7 76713 document 19191 train_lf_MLP.py text/x-script.python 25e58d6e1abfa7922609b57455940173 MD5 12493 2025-06-07 12:33:46 https://researchdata.bath.ac.uk/1533/10/train_lf_MLP.py 1533 10 10 text/x-script.python other A Python script for linear buckling prediction using the Low-fidelity MLP. en public cc_by

train_lf_MLP.py

code 19192 9 76715 document 19192 train_mf_sequential_MLP.py text/x-script.python 61683ec3013c2e5ba918015430bb165a MD5 12944 2025-06-07 12:33:55 https://researchdata.bath.ac.uk/1533/11/train_mf_sequential_MLP.py 1533 11 11 text/x-script.python other A Python script for nonlinear buckling prediction using Multi-Fidelity (sequential) MLP. en public cc_by

train_mf_sequential_MLP.py

code 19193 8 76717 document 19193 train_mf_transfer_MLP.py text/x-script.python ec5ae9184d32343e1d1a9d08f62de7a3 MD5 12878 2025-06-07 12:34:04 https://researchdata.bath.ac.uk/1533/12/train_mf_transfer_MLP.py 1533 12 12 text/x-script.python other A Python script for nonlinear buckling prediction using Multi-Fidelity (transfer learning) MLP. en public cc_by

train_mf_transfer_MLP.py

code 19194 5 76728 document 19194 models.zip application/zip 4bb4e94e50b3493b001e42aabe9bfa9b MD5 832426564 2025-06-07 12:50:30 https://researchdata.bath.ac.uk/1533/13/models.zip 1533 13 13 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 19195 5 76731 document 19195 results.zip application/zip a01f1969e6c063e1084293d3c37a5304 MD5 164428 2025-06-07 12:53:14 https://researchdata.bath.ac.uk/1533/14/results.zip 1533 14 14 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 19197 3 76739 document 19197 requirements.txt text/plain 1e7f84723131d590d2772a1be9c6e9a1 MD5 529 2025-06-07 13:01:33 https://researchdata.bath.ac.uk/1533/16/requirements.txt 1533 16 16 text/plain other en public cc_by

requirements.txt

documentation 19198 2 76746 document 19198 indexcodes.txt text/plain 4b63f7562caed85ed4b52cd06bb3fa7e MD5 279 2025-06-07 13:08:08 https://researchdata.bath.ac.uk/1533/17/indexcodes.txt 1533 17 17 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/19197 http://eprints.org/relation/isVolatileVersionOf https://researchdata.bath.ac.uk/id/document/19197 http://eprints.org/relation/isIndexCodesVersionOf https://researchdata.bath.ac.uk/id/document/19197 19258 2 82457 document 19258 README.md text/plain 62d722b9f699effc2395bbabcc3af3b9 MD5 7795 2026-03-23 15:38:06 https://researchdata.bath.ac.uk/1533/18/README.md 1533 18 18 text/plain other en public cc_by

README.md

documentation archive 12262 disk0/00/00/15/33 2025-06-11 12:36:15 2026-03-23 15:45:53 2026-03-23 15:43:54 data_collection show Pollet Maxime mp2333@bath.ac.uk 0000-0002-1894-1998 University of Bath TRUE Shepherd Paul P.Shepherd@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 Dataset for: Multi-Fidelity deep learning for predicting the nonlinear buckling behaviour of concrete thin-shells CP0120 dept_civ_eng Concrete, Thin-shell, Finite Element Analysis, Machine Learning, Deep Learning, Buckling, Multi-Fidelity The original folder structure is given in README.md. To reproduce it, create a new folder and extract the "models.zip" and "results.zip" folders inside. Additionally, create a "scripts" folder and store all Python scripts inside. This dataset contains scripts and data supporting the research article, "Multi-Fidelity deep learning for predicting the nonlinear buckling behaviour of concrete thin-shells". 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 – Multi-Fidelity Multilayer Perceptrons – that have been trained to predict the nonlinear buckling factor 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. 2026-03-21 University of Bath public RightsHolder University of Bath University of Bath https://doi.org/10.13039/501100000835 cent_dmade The methods used to generate this data can be found in the related 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.engappai.2026.114490 en 1 10.15125/BATH-01533 https://doi.org/10.15125/BATH-01519 data https://doi.org/10.1016/j.engappai.2026.114490 pub open