Machine learning for optimal design of circular hollow section stainless steel stub columns: A comparative analysis with Eurocode 3 predictions

Journal article


Abarkan, I, Rabi, M., Ferreira, F., Shamass, R., Limbachiya, V., Jweihan, Y. and Pinho Santos, L. (2024). Machine learning for optimal design of circular hollow section stainless steel stub columns: A comparative analysis with Eurocode 3 predictions. Engineering Applications of Artificial Intelligence. 132 (107952). https://doi.org/10.1016/j.engappai.2024.107952
AuthorsAbarkan, I, Rabi, M., Ferreira, F., Shamass, R., Limbachiya, V., Jweihan, Y. and Pinho Santos, L.
Abstract

Stainless steel has many advantages when used in structures, however, the initial cost is high. Hence, it is essential to develop reliable and accurate design methods that can optimize the material. As novel, reliable soft computation methods, machine learning provided more accurate predictions than analytical formulae and solved highly complex problems. The present study aims to develop machine learning models to predict the cross-section resistance of circular hollow section stainless steel stub column. A parametric study is conducted by varying the diameter, thickness, length, and mechanical properties of the column. This database is used to train, validate, and test machine learning models, Artificial Neural Network (ANN), Decision Trees for Regression (DTR), Gene Expression Programming (GEP) and Support Vector Machine Regression (SVMR). Thereafter, results are compared with finite element models and Eurocode 3 (EC3) to assess their accuracy. It was concluded that the EC3 models provided conservative predictions with an average Predicted-to-Actual ratio of 0.698 and Root Mean Square Error (RMSE) of 437.3. The machine learning models presented the highest level of accuracy. However, the SVMR model based on RBF kernel presented a better performance than the ANN, GEP and DTR machine learning models, and RMSE value for SVMR, ANN, GEP and DTR is 22.6, 31.6, 152.84 and 29.07, respectively. The GEP leads to the lowest level of accuracy among the other three machine learning models, yet, it is more accurate than EC3. The machine learning models were implemented in a user-friendly tool, which can be used for design purposes.

KeywordsCircular hollow sectionsStainless steelFinite element modelArtificial neural networkSupport vector machine regressionGene Expression ProgrammingDecision Trees for Regression
Year2024
JournalEngineering Applications of Artificial Intelligence
Journal citation132 (107952)
PublisherElsevier
ISSN1873-6769
Digital Object Identifier (DOI)https://doi.org/10.1016/j.engappai.2024.107952
Web address (URL)https://www.sciencedirect.com/science/article/pii/S0952197624001106
Publication dates
Print15 Feb 2024
Publication process dates
Accepted19 Jan 2024
Deposited21 Feb 2024
Publisher's version
License
File Access Level
Open
Accepted author manuscript
License
File Access Level
Controlled
Permalink -

https://openresearch.lsbu.ac.uk/item/966x2

Download files


Publisher's version
1-s2.0-S0952197624001106-main.pdf
License: CC BY 4.0
File access level: Open

  • 9
    total views
  • 6
    total downloads
  • 2
    views this month
  • 0
    downloads this month

Export as

Related outputs

Machine learning-driven web-post buckling resistance prediction for high-strength steel beams with elliptically-based web openings
Rabi, M, Jweihan, Y, Abarkan, I, Ferreira, F, Shamass, R, Limbachiya, V., Tsavaridis, K and Pinho Santos, L. (2024). Machine learning-driven web-post buckling resistance prediction for high-strength steel beams with elliptically-based web openings. Results in Engineering. 21, p. 101749. https://doi.org/10.1016/j.rineng.2024.101749
Web-post buckling resistance calculation of perforated high-strength steel beams with elliptically-based web openings for EC3
Ferreira, F., Shamass, R., Santos, L., Tsavdaridis, K. and Limbachiya, V. (2023). Web-post buckling resistance calculation of perforated high-strength steel beams with elliptically-based web openings for EC3. Structures. https://doi.org/10.1016/j.istruc.2023.05.139
Mechanical and GWP Assessment of Concrete Using Blast Furnace Slag, Silica Fume and Recycled Aggregate
Shamass, R., Rispoli, O., Limbachiya, V. and Kovacs, R. (2023). Mechanical and GWP Assessment of Concrete Using Blast Furnace Slag, Silica Fume and Recycled Aggregate. Case Studies in Construction Materials. 18. https://doi.org/10.1016/j.cscm.2023.e02164
Prediction of the cross-sectional capacity of cold-formed CHS using numerical modelling and machine learning
Musab,R., Ferreira, F., Abarkan, A., Limbachiya, V. and Shamass, R. (2023). Prediction of the cross-sectional capacity of cold-formed CHS using numerical modelling and machine learning. Results in Engineering. 17 (100902). https://doi.org/10.1016/j.rineng.2023.100902
A Numerical Study of Shape Memory Alloy (SMA) Reinforced Beam Subjected to Seismic Loading
Bloy, J., Shamass, R., Limbachiya, V. and El-Desoqi, M. (2022). A Numerical Study of Shape Memory Alloy (SMA) Reinforced Beam Subjected to Seismic Loading. 4th Conference on Sustainability in Civil Engineering (CSCE’22) . Department of Civil Engineering Capital University of Science and Technology, Islamabad Pakistan 31 - 31 Aug 2022
Web-Post Buckling Prediction Resistance of Steel Beams with Elliptically-Based Web Openings using Artificial Neural Networks (ANN)
Shamass, R., Ferreira, F., Limbachiya, V., Pinho Santos, L. and Tsavdaridis, K.D. (2022). Web-Post Buckling Prediction Resistance of Steel Beams with Elliptically-Based Web Openings using Artificial Neural Networks (ANN). Thin-Walled Structures. 180 (109959). https://doi.org/10.1016/j.tws.2022.109959
Mechanical Properties of Bamboo Core Sandwich Panels
Limbachiya, V., Shamass, R. and Perera, J (2022). Mechanical Properties of Bamboo Core Sandwich Panels. 4th Conference on Sustainability in Civil Engineering. Pakistan 31 - 31 Aug 2022
Gradient-based optimisation of rectangular honeycomb core sandwich panels
Luis Santos, Bassam A. Izzuddin, Lorenzo Macorini and Pinho Santos, L. (2022). Gradient-based optimisation of rectangular honeycomb core sandwich panels. Structural and Multidisciplinary Optimization. 65 (242). https://doi.org/10.1007/s00158-022-03341-7
EC3 design of web-post buckling resistance for perforated steel beams with elliptically-based web openings
Ferreira, F., Shamass, R., Pinho Santos, L., Limbachiya, V. and Tsavdaridis, K. (2022). EC3 design of web-post buckling resistance for perforated steel beams with elliptically-based web openings. Thin-Walled Structures. 175, p. 109196. https://doi.org/10.1016/j.tws.2022.109196
Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN)
Ferreira, F., Shamass, R., Limbachiya, V., Tsavdarisdis, K. and Martins, C. (2021). Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN). Thin-Walled Structures. 170, p. 108592. https://doi.org/10.1016/j.tws.2021.108592
Predicting the Impact of Chemical and Physical Variability in Binary and Ternary Cementitious Blends
Limbachiya, V. and Shamass, R. (2021). Predicting the Impact of Chemical and Physical Variability in Binary and Ternary Cementitious Blends. 3rd Conference on Sustainability in Civil Engineering (CSCE’21). Capital University of Science & Technology, . Islamabad Expressway, Kahuta Road, Zone-V Islamabad 11 - 11 Aug 2021 Department of Civil Engineering at Capital University of Science and Technology.
Impact of chopped basalt fibres on the mechanical proper- ties of concrete
Shamass, R. and Limbachiya, V. (2021). Impact of chopped basalt fibres on the mechanical proper- ties of concrete. 3rd Conference on Sustainability in Civil Engineering (CSCE’21). Capital University of Science & Technology, . Islamabad Expressway, Kahuta Road, Zone-V Islamabad 11 - 11 Aug 2021 Department of Civil Engineering at Capital University of Science and Technology.
Application of Artificial Neural Networks for web-post shear resistance of cellular steel beams
Limbachiya, V. and Shamass, R. (2021). Application of Artificial Neural Networks for web-post shear resistance of cellular steel beams. Thin-Walled Structures. 161, pp. 107414-107414. https://doi.org/10.1016/j.tws.2020.107414
Experimental Investigation on the Behaviour of Recycled Aggregate Concrete
Kovacs, R, Shamass, R, Limbachiya, V and Datoo, M (2019). Experimental Investigation on the Behaviour of Recycled Aggregate Concrete. 5th International Conference on Sustainable Construction Materials & Technologies. Surrey 14 - 17 Jul 2019
High-fidelity non-linear analysis of metal sandwich panels
Nordas, A.N., Pinho Santos, L., Izzuddin, B. and Macorini, L. (2018). High-fidelity non-linear analysis of metal sandwich panels. Proceedings of the Institution of Civil Engineers - Engineering and Computational Mechanics. 171 (2), pp. 79-96. https://doi.org/10.1680/jencm.18.00022
Mechanical models for local buckling of metal sandwich panels
Pinho Santos, L., Nordas, A.N., Izzuddin, B. and Macorini, L. (2018). Mechanical models for local buckling of metal sandwich panels. Proceedings of the Institution of Civil Engineers - Engineering and Computational Mechanics. 171 (2), pp. 65-78. https://doi.org/10.1680/jencm.18.00021
Improved Seismic Design of Concentrically X-Braced Steel Frames to Eurocode 8
Silva, A., Pinho Santos, L., Pinto Ribeiro, T. and Castro, J.M. (2018). Improved Seismic Design of Concentrically X-Braced Steel Frames to Eurocode 8. Journal of Earthquake Engineering. https://doi.org/10.1080/13632469.2018.1528912
The impact of variation in chemical and physical properties of PFA and BPD semi-dry cement paste on strength properties
Limbachiya, V, Ganjian, E and Claisse, P (2015). The impact of variation in chemical and physical properties of PFA and BPD semi-dry cement paste on strength properties. Construction and Building Materials. 96, pp. 248-255. https://doi.org/10.1016/j.conbuildmat.2015.08.002
Strength, durability and leaching properties of concrete paving blocks incorporating GGBS and SF
Limbachiya, V (2016). Strength, durability and leaching properties of concrete paving blocks incorporating GGBS and SF. Construction and Building Materials. 113, pp. 273-279. https://doi.org/10.1016/j.conbuildmat.2016.02.152
The impact of variation in chemical and physical properties of PFA and BPD semi dry cement paste on strength properties
Limbachiya, V (2015). The impact of variation in chemical and physical properties of PFA and BPD semi dry cement paste on strength properties. Construction and Building Materials. 96, pp. 248-255. https://doi.org/10.1016/j.conbuildmat.2015.08.002