Machine learning models for predicting the axial compression capacity of cold‑formed steel elliptical hollow section columns
Asian Journal of Civil Engineering - Trang 1-13
Tóm tắt
This study presents the performance of three machine learning (ML) models including gradient boosting regression trees (GBRT), artificial neural network model (ANN), and artificial neural network–particle swarm optimization (ANN-PSO) for predicting the axial compression capacity (ACC) of cold‑formed steel elliptical hollow section (EHS) columns. To achieve the goal, a set of 291 data is collected from previous studies to develop GBRT, ANN, and ANN-PSO models. The performance of GBRT, ANN, and ANN-PSO models is evaluated based on the statistical indicators, which are $${R}^{2}, \mathrm{RMSE},\mathrm{ MAPE},$$ and $$i20-\mathrm{index}$$ . The results show that the ANN-PSO model with $${R}^{2}=1.00, \mathrm{RMSE} = 41.3631, \mathrm{MAPE }= 1.3689,$$ and $$i20-\mathrm{index} = 0.9966$$ has the best performance compared to GBRT and ANN models. Moreover, a graphical user interface tool is developed based on the ANN-PSO model for practical designs.
Tài liệu tham khảo
1993-3-1 E. (2006). Eurocode 3: Design of steel structures—Part 3–1. In: The European Union Per Regulation 305/2011.
citation_title=North American Specification for the Design of Cold-Formed Steel Structural Members; citation_publication_date=2016; citation_id=CR2; citation_publisher=American Iron and Steel Institute
Alizamir, M., & Sobhanardakani, S. (2018). An artificial neural network-particle swarm optimization (ANN-PSO) approach to predict heavy metals contamination in groundwater resources. Jundishapur Journal of Health Sciences, 10(2).
citation_journal_title=Geosystem Engineering; citation_title=Comparing ANFIS and integrating algorithm models (ICA-ANN, PSO-ANN, and GA-ANN) for prediction of energy consumption for irrigation land leveling; citation_author=I Alzoubi, MR Delavar, F Mirzaei, B NadjarArrabi; citation_volume=21; citation_issue=2; citation_publication_date=2018; citation_pages=81-94; citation_doi=10.1080/12269328.2017.1372225; citation_id=CR4
citation_title=Specification for Structural Steel Buildings; citation_publication_date=2016; citation_id=CR5; citation_publisher=American Institute of Steel Construction
citation_journal_title=Journal of Structural Engineering; citation_title=Flexural buckling of elliptical hollow section columns; citation_author=TM Chan, L Gardner; citation_volume=135; citation_issue=5; citation_publication_date=2009; citation_pages=546; citation_doi=10.1061/(ASCE)ST.1943-541X.0000005; citation_id=CR6
citation_journal_title=Journal of Constructional Steel Research; citation_title=Behavior of cold-formed steel elliptical hollow sections subjected to bending; citation_author=M-T Chen, B Young; citation_volume=158; citation_publication_date=2019; citation_pages=317-330; citation_doi=10.1016/j.jcsr.2019.02.022; citation_id=CR7
citation_journal_title=Thin-Walled Structures; citation_title=Material properties and structural behavior of cold-formed steel elliptical hollow section stub columns; citation_author=M-T Chen, B Young; citation_volume=134; citation_publication_date=2019; citation_pages=111-126; citation_doi=10.1016/j.tws.2018.07.055; citation_id=CR8
citation_journal_title=Thin-Walled Structures; citation_title=Structural performance of cold-formed steel elliptical hollow section pin-ended columns; citation_author=M-T Chen, B Young; citation_volume=136; citation_publication_date=2019; citation_pages=267-279; citation_doi=10.1016/j.tws.2018.11.024; citation_id=CR9
citation_journal_title=Engineering Structures; citation_title=Beam-column tests of cold-formed steel elliptical hollow sections; citation_author=M-T Chen, B Young; citation_volume=210; citation_publication_date=2020; citation_doi=10.1016/j.engstruct.2019.109911; citation_id=CR10
citation_journal_title=Engineering Structures; citation_title=A neural network based closed-form solution for the distortional buckling of elliptical tubes; citation_author=J Dias, N Silvestre; citation_volume=33; citation_issue=6; citation_publication_date=2011; citation_pages=2015-2024; citation_doi=10.1016/j.engstruct.2011.02.038; citation_id=CR11
citation_title=Swarm intelligence; citation_publication_date=2001; citation_id=CR12; citation_author=RC Eberhart; citation_author=Y Shi; citation_author=J Kennedy; citation_publisher=Elsevier
citation_journal_title=Annals of Statistics; citation_title=Greedy function approximation: a gradient boosting machine; citation_author=JH Friedman; citation_publication_date=2001; citation_doi=10.1080/15567036.2019.1630521; citation_id=CR13
citation_journal_title=Advances in Engineering Software; citation_title=A feasibility study of BBP for predicting shear capacity of FRP reinforced concrete beams without stirrups; citation_author=EM Golafshani, A Ashour; citation_volume=97; citation_publication_date=2016; citation_pages=29-39; citation_doi=10.1016/j.advengsoft.2016.02.007; citation_id=CR14
citation_journal_title=Urban Climate; citation_title=Estimating urban PM2.5 concentration: An analysis on the nonlinear effects of explanatory variables based on gradient boosted regression tree; citation_author=X Hao, X Hu, T Liu, C Wang, L Wang; citation_volume=44; citation_publication_date=2022; citation_pages=101172; citation_doi=10.1016/j.uclim.2022.101172; citation_id=CR15
citation_title=Advances in metaheuristic algorithms for optimal design of structures; citation_publication_date=2014; citation_id=CR16; citation_author=A Kaveh; citation_publisher=Springer
citation_journal_title=International Journal for Numerical Methods in Engineering; citation_title=Wavefront reduction using graphs, neural networks and genetic algorithm; citation_author=A Kaveh, HR Bondarabady; citation_volume=60; citation_issue=11; citation_publication_date=2004; citation_pages=1803-1815; citation_doi=10.1002/nme.1023; citation_id=CR17
citation_journal_title=International Journal of Space Structures; citation_title=Optimal design of transmission towers using genetic algorithm and neural networks; citation_author=A Kaveh, Y Gholipour, H Rahami; citation_volume=23; citation_issue=1; citation_publication_date=2008; citation_pages=1-19; citation_doi=10.1260/026635108785342073; citation_id=CR18
citation_journal_title=International Journal on Interactive Design and Manufacturing (IJIDeM); citation_title=Applying ANN–PSO algorithm to maximize the compressive strength and split tensile strength of blended self curing concrete on the impact of supplementary cementitious materials; citation_author=CV Kumar, K Sargunan, J Vasa, VP Jesuraj, A Punitha, R Karthikeyan; citation_publication_date=2022; citation_doi=10.1007/s12008-022-00907-z; citation_id=CR19
citation_journal_title=International Journal of Steel Structures; citation_title=Global instability of elliptical hollow section beam-columns under compression and biaxial bending; citation_author=K Law, L Gardner; citation_volume=13; citation_issue=4; citation_publication_date=2013; citation_pages=745-759; citation_doi=10.1007/s13296-013-4015-9; citation_id=CR20
citation_journal_title=Applied Sciences; citation_title=A comparative study of PSO-ANN, GA-ANN, ICA-ANN, and ABC-ANN in estimating the heating load of buildings’ energy efficiency for smart city planning; citation_author=LT Le, H Nguyen, J Dou, J Zhou; citation_volume=9; citation_issue=13; citation_publication_date=2019; citation_pages=2630; citation_doi=10.3390/app9132630; citation_id=CR21
citation_journal_title=Bulletin of Engineering Geology and the Environment; citation_title=Optimized ANN model for predicting rock mass quality ahead of tunnel face using measure-while-drilling data; citation_author=J Liu, Y Jiang, W Han, O Sakaguchi; citation_volume=80; citation_issue=3; citation_publication_date=2021; citation_pages=2283-2305; citation_doi=10.1007/s10064-020-02057-6; citation_id=CR22
Manna, S., Biswas, S., Kundu, R., Rakshit, S., Gupta, P., & Barman, S. (2017). A statistical approach to predict flight delay using gradient boosted decision tree. In: 2017 International conference on computational intelligence in data science (ICCIDS).
citation_journal_title=Steel Construction; citation_title=Cross-sectional behaviour and design of ferritic and duplex stainless steel EHS in compression; citation_author=A Mohammed, KA Cashell; citation_volume=14; citation_issue=4; citation_publication_date=2021; citation_pages=279-287; citation_doi=10.1002/stco.202100001; citation_id=CR24
citation_journal_title=Journal of Building Engineering; citation_title=Evaluating structural response of concrete-filled steel tubular columns through machine learning; citation_author=M Naser, S Thai, H-T Thai; citation_volume=34; citation_publication_date=2021; citation_pages=101888; citation_doi=10.1016/j.jobe.2020.101888; citation_id=CR25
citation_journal_title=Asian Journal of Civil Engineering; citation_title=GBRT-based model for predicting the axial load capacity of the CFS-SOHS columns; citation_author=D-D Nguyen, T-H Nguyen; citation_publication_date=2023; citation_doi=10.1007/s42107-023-00743-w; citation_id=CR26
citation_journal_title=Asian Journal of Civil Engineering; citation_title=ANN-based model for predicting the axial load capacity of the cold-formed steel semi-oval hollow section column; citation_author=D-D Nguyen, N-L Tran, T-H Nguyen; citation_volume=24; citation_issue=5; citation_publication_date=2023; citation_pages=1165-1179; citation_doi=10.1007/s42107-022-00560-7; citation_id=CR27
citation_journal_title=Engineering Fracture Mechanics; citation_title=A new empirical formula for prediction of fracture energy of concrete based on the artificial neural network; citation_author=IM Nikbin, S Rahimi, H Allahyari; citation_volume=186; citation_publication_date=2017; citation_pages=466-482; citation_doi=10.1016/j.engfracmech.2017.11.010; citation_id=CR28
citation_journal_title=Sādhanā; citation_title=Thermal performance prediction models for a pulsating heat pipe using artificial neural network (ANN) and regression/correlation analysis (RCA); citation_author=VM Patel, HB Mehta; citation_volume=43; citation_issue=11; citation_publication_date=2018; citation_pages=1-16; citation_doi=10.1007/s12046-018-0954-3; citation_id=CR29
Prettenhofer, P., & Louppe, G. (2014). Gradient boosted regression trees in scikit-learn. PyData 2014
citation_journal_title=Journal of Computing in Civil Engineering; citation_title=Back-analysis method for stope displacements using gradient-boosted regression tree and firefly algorithm; citation_author=C Qi, A Fourie, X Zhao; citation_volume=32; citation_issue=5; citation_publication_date=2018; citation_pages=04018031; citation_doi=10.1061/(ASCE)CP.1943-5487.0000779; citation_id=CR31
citation_title=ANN modeling applied to NO X reduction with octane. A nn future in personal vehicles; citation_inbook_title=Adaptive and Natural Computing Algorithms; citation_publication_date=2005; citation_pages=100-103; citation_id=CR32; citation_author=M Rönnholm; citation_author=K Arve; citation_author=K Eränen; citation_author=F Klingstedt; citation_author=T Salmi; citation_author=H Saxén; citation_publisher=Springer
citation_journal_title=Applied Sciences; citation_title=Application of a hybrid artificial neural network-particle swarm optimization (ANN-PSO) model in behavior prediction of channel shear connectors embedded in normal and high-strength concrete; citation_author=M Shariati, MS Mafipour, P Mehrabi, A Bahadori, Y Zandi, MN Salih, S Poi-Ngian; citation_volume=9; citation_issue=24; citation_publication_date=2019; citation_pages=5534; citation_doi=10.3390/app9245534; citation_id=CR33
citation_journal_title=Chemical Product and Process Modeling; citation_title=The optimization of biodiesel production from transesterification of sesame oil via applying ultrasound-assisted techniques: Comparison of RSM and ANN–PSO hybrid model; citation_author=H Soltani, A Karimi, S Falahatpisheh; citation_volume=17; citation_issue=1; citation_publication_date=2022; citation_pages=55-67; citation_doi=10.1515/cppm-2020-0076; citation_id=CR34
citation_journal_title=Engineering Structures; citation_title=Structural response of stainless steel oval hollow section compression members; citation_author=M Theofanous, TM Chan, L Gardner; citation_volume=31; citation_issue=4; citation_publication_date=2009; citation_pages=922-934; citation_doi=10.1016/j.engstruct.2008.12.002; citation_id=CR35
citation_journal_title=International Journal of Ambient Energy; citation_title=Artificial neural network, ANN-PSO and ANN-ICA for modelling the Stirling engine; citation_author=S Toghyani, MH Ahmadi, A Kasaeian, AH Mohammadi; citation_volume=37; citation_issue=5; citation_publication_date=2016; citation_pages=456-468; citation_doi=10.1080/01430750.2014.986289; citation_id=CR36
citation_journal_title=Sādhanā; citation_title=Prediction of speed limit of cars moving on corroded steel girder bridges using artificial neural networks; citation_author=N-L Tran, D-D Nguyen, T-H Nguyen; citation_volume=47; citation_issue=3; citation_publication_date=2022; citation_pages=1-14; citation_doi=10.1007/s12046-022-01899-y; citation_id=CR37
citation_journal_title=Advances in Materials Science and Engineering; citation_title=A machine learning-based model for predicting atmospheric corrosion rate of carbon steel; citation_author=N-L Tran, T-H Nguyen, V-T Phan, D-D Nguyen; citation_publication_date=2021; citation_doi=10.1155/2021/6967550; citation_id=CR38
citation_journal_title=Thin-Walled Structures; citation_title=Efficiency of three advanced data-driven models for predicting axial compression capacity of CFDST columns; citation_author=V-L Tran, S-E Kim; citation_volume=152; citation_publication_date=2020; citation_doi=10.1016/j.tws.2020.106744; citation_id=CR39
citation_journal_title=Composite Structures; citation_title=Application of ANN in predicting ACC of SCFST column; citation_author=V-L Tran, D-K Thai, S-E Kim; citation_volume=228; citation_publication_date=2019; citation_doi=10.1016/j.compstruct.2019.111332; citation_id=CR40
citation_journal_title=Engineering Structures; citation_title=Cross-section behavior of cold-formed steel elliptical hollow sections—A numerical study; citation_author=Y Yao, W-M Quach, B Young; citation_volume=201; citation_publication_date=2019; citation_doi=10.1016/j.engstruct.2019.109797; citation_id=CR41