Dataset for a framework for assessing the impact of geometric imperfections in concrete shell structures using deep learning

1532 83 19169 4 76647 document 19169 models.zip application/zip 2058f3b28fb7b52844513b33c650f362 MD5 1496374741 2025-06-07 12:05:24 https://researchdata.bath.ac.uk/1532/1/models.zip 1532 1 1 application/zip other This folder contains the trained deep learning models used to achieve the predictive performances highlighted in the thesis. Files formats: PyTorch (.pth). en public cc_by

models.zip

data 19170 4 76650 document 19170 results.zip application/zip 27c4a69aec416d372b387d4d9b7b48e5 MD5 85350335 2025-06-07 12:08:33 https://researchdata.bath.ac.uk/1532/2/results.zip 1532 2 2 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 thesis. Files formats: PyTorch (.pth). en public cc_by

results.zip

data 19171 4 76653 document 19171 datasets.py text/x-script.python 3684c141862d8715e7243ac4d371409a MD5 11267 2025-06-07 12:09:48 https://researchdata.bath.ac.uk/1532/3/datasets.py 1532 3 3 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 19172 4 76656 document 19172 metrics.py text/x-script.python 7ec90f227ce8fada9f55e98b7d38ef6e MD5 8150 2025-06-07 12:10:32 https://researchdata.bath.ac.uk/1532/4/metrics.py 1532 4 4 text/x-script.python other A Python script with error metrics classes. en public cc_mit

metrics.py

code 19173 4 76659 document 19173 models.py text/x-script.python ceefac2e6ea79218cced827b62536911 MD5 6205 2025-06-07 12:11:31 https://researchdata.bath.ac.uk/1532/5/models.py 1532 5 5 text/x-script.python other A Python script with the deep learning model classes. en public cc_mit

models.py

code 19174 4 76662 document 19174 tools.py text/x-script.python a5022b7c29f806851c9f4ef7da2dfc73 MD5 11748 2025-06-07 12:12:14 https://researchdata.bath.ac.uk/1532/6/tools.py 1532 6 6 text/x-script.python other A Python script that contains some tool functions. en public cc_mit

tools.py

code 19175 4 76665 document 19175 train_CNN_buckling.py text/x-script.python 01e361759ec8ea9f2c4bc6aef748a5a0 MD5 16150 2025-06-07 12:13:11 https://researchdata.bath.ac.uk/1532/7/train_CNN_buckling.py 1532 7 7 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 19176 4 76668 document 19176 train_CNN_stress.py text/x-script.python c26f62202ebdccbd904d3660150b4345 MD5 19638 2025-06-07 12:13:48 https://researchdata.bath.ac.uk/1532/8/train_CNN_stress.py 1532 8 8 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 19177 4 76671 document 19177 train_MLP_buckling.py text/x-script.python f3b8996410e156b930cc5e540a9e34da MD5 15120 2025-06-07 12:14:26 https://researchdata.bath.ac.uk/1532/9/train_MLP_buckling.py 1532 9 9 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 19178 4 76674 document 19178 train_MLP_stress.py text/x-script.python 7526643459940670223dd8f01ba590eb MD5 18351 2025-06-07 12:15:07 https://researchdata.bath.ac.uk/1532/10/train_MLP_stress.py 1532 10 10 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 19180 3 76681 document 19180 requirements.txt text/plain 46b12de63bee698dca8402268a103b69 MD5 589 2025-06-07 12:24:13 https://researchdata.bath.ac.uk/1532/12/requirements.txt 1532 12 12 text/plain other en public cc_by

requirements.txt

documentation 19181 2 76690 document 19181 indexcodes.txt text/plain 501779c8ad5ee2645b7e370fdd9d4939 MD5 304 2025-06-07 12:27:56 https://researchdata.bath.ac.uk/1532/13/indexcodes.txt 1532 13 13 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/19180 http://eprints.org/relation/isVolatileVersionOf https://researchdata.bath.ac.uk/id/document/19180 http://eprints.org/relation/isIndexCodesVersionOf https://researchdata.bath.ac.uk/id/document/19180 19257 2 81613 document 19257 README.md text/plain 27744117318279698a484a9845aefdec MD5 3891 2026-02-09 10:28:49 https://researchdata.bath.ac.uk/1532/14/README.md 1532 14 14 text/plain other en public cc_by

README.md

documentation archive 12262 disk0/00/00/15/32 2026-02-09 10:37:34 2026-02-14 05:56:00 2026-02-09 10:37:34 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 a framework for assessing the impact of geometric imperfections in concrete shell structures 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 new folder 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 following thesis: Pollet, M. (2025). Rapid structural analysis of prefabricated thin concrete shells using deep learning (Thesis). University of Bath. Concrete thin-shells are materially efficient structures, which can be used to reduce the environmental impact of concrete structures. However, geometric imperfections, which may occur during production can negatively impact their structural behaviour. While this impact can be assessed through Finite Element Analysis (FEA), a faster analysis method, such as surrogate modelling, could benefit concrete shell manufacturers. This dataset contains deep learning models – Multilayer Perceptrons, and Convolutional Neural Networks – that have been trained to predict the buckling factor and stress fields of geometrically imperfect 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 thesis. 2026-02-09 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 thesis. 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://researchportal.bath.ac.uk/en/studentTheses/cc35ec1d-d15a-45d9-8f8c-248d7e859253 en 1 10.15125/BATH-01532 https://doi.org/10.15125/BATH-01519 data https://researchportal.bath.ac.uk/en/studentTheses/cc35ec1d-d15a-45d9-8f8c-248d7e859253 thesis open