Surrogate model predicting the load-displacement curve of monopiles in the PISA Dunkirk testing site
Authors/Creators
-
1.
Imperial College London
Description
A surrogate model was created using Support Vector Regression from the scikit-learn library (Pedregosa et al., 2011). The Latin Hypercube Sampling method was utilised to generate the input pile geometries, with the diameter varying between 0.5 m and 2.5 m, the slenderness ratio L/D varying between 3 and 10 and the thickness ratio D/t varying between 30 and 100. 500 geometries were created assuming the ground conditions observed in the PISA Dunkirk testing site (Taborda et al., 2020). A state-parameter constitutive model (Taborda et al., 2022; Taborda et al., 2023) was used to simulate the response of sand behaviour.
This surrogate allows the user to obtain a prediction of the load-displacement curve for any geometry within the ranges shown above, which include all pile geometries tested at Dunkirk for the PISA project.
This work was the recipient of the 2023 Amiya Basu prize for use of AI technologies in Civil Engineering.
Files
Files
(345.0 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:52ebf6aa0a13d4d41dc09dd95877b84f
|
345.0 MB | Download |
Additional details
Funding
- Engineering and Physical Sciences Research Council
- SIDeTools - Imperial College London UKRI Impact Acceleration Account EP/X52556X/1
References
- Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R. & Dubourg, V. (2011) Scikit-learn: Machine learning in Python. The Journal of Machine Learning Research. 12 2825-2830.
- Taborda, D. M. G., Pedro, A. M. & Pirrone, A. I. (2022) A state parameter-dependent constitutive model for sands based on the Mohr-Coulomb failure criterion. Computers and Geotechnics. 148 104811.
- Taborda, D. M., Zdravković, L., Potts, D. M., Burd, H. J., Byrne, B. W., Gavin, K. G., Houlsby, G. T., Jardine, R. J., Liu, T. & Martin, C. M. (2020) Finite-element modelling of laterally loaded piles in a dense marine sand at Dunkirk. Géotechnique. 70 (11), 1014-1029.
- Taborda, DMG, Pedro, AMG, Kontoe, S, Tsiampousi, A (2023) IC MAGE Model 02 – Simple state-parameter dependent model with isotropic small strain stiffness (Version 2.6). Zenodo. doi: 10.5281/zenodo.7629677
- Yang, Y (2023) Development of surrogate models for the design of offshore monopiles, MSc thesis, Imperial College London.