Prediction of crippling load of I-shaped steel columns by using soft computing techniques

Abstract

This study is primarily aimed at creating three machine learning models: artificial neural network (ANN), random forest (RF), and k-nearest neighbour (KNN), so as to predict the crippling load (CL) of I-shaped steel columns. Five input parameters, namely length of column (L), width of flange (b _f), flange thickness (t _f), web thickness (t _w) and height of column (H), are used to compute the crippling load (CL). A range of performance indicators, including the coefficient of determination (R ²), variance account factor (VAF), a-10 index, root mean square error (RMSE), mean absolute error (MAE) and mean absolute deviation (MAD), are used to assess the effectiveness of the established machine learning models. The results show that all of the three ML (machine learning) models can accurately predict the crippling load, but the performance of ANN is superior: it delivers the highest value of R ² = 0.998 and the lowest value of RMSE = 0.008 in the training phase, as well as the highest value of R ² = 0.996 and the smaller value of RMSE = 0.012 in the testing phase. Additional methods, including rank analysis, reliability analysis, regression plot, Taylor diagram and error matrix plot, are employed to assess the models’ performance. The reliability index (β) of the models is calculated by using the first-order second moment (FOSM) technique, and the result is compared with the actual value. Additionally, sensitivity analysis is performed to check the impact of the input variables on the output (CL), finding that b _f has the greatest impact on the crippling load, followed by t _f, t _w, H and L, in that order. This study demonstrates that ML techniques are useful for developing a reliable numerical tool for measuring the crippling load of I-shaped steel columns. It is found that the proposed techniques can also be used to predict other kinds of failures as well as different kinds of perforated columns.

Keywords

I-shaped steel column / Crippling load / ANN / KNN / RF / Reliability analysis

References

[1] Abambres M, Rajana K, Tsavdaridis KD, Ribeiro TP. Neural network-based formula for the buckling load prediction of I-section cellular steel beams. Computers, 2019, 8(2): 1-26

[2] Adeniyi DA, Wei Z, Yongquan Y. Automated web usage data mining and recommendation system using K-nearest neighbor (KNN) classification method. Applied Computing and Informatics, 2016, 12: 90-108

[3] Al Yamani WH, Ghunimat DM, Bisharah MM. Modeling and predicting the sensitivity of high-performance concrete compressive strength using machine learning methods. Asian Journal of Civil Engineering, 2023, 24: 1943-1955

[4] Anand MAT, Anandakumar S, Pare A, Chandrasekar V, Venkatachalapath N. Modelling of process parameters to predict the efficiency of shallots stem cutting machine using multiple regression and artificial neural network. Journal of Food Process Engineering, 2021

[5] Bhatia, N. (2010). Survey of nearest neighbor techniques. Preprint retrieved from arXiv arXiv:1007.0085. https://doi.org/10.48550/arXiv.1007.0085.

[6] Bhavikatti SS. Strength of materials, 2008 3 Vikas Publishing House

[7] Breiman L. Random forests. Machine Learning, 2001, 45: 5-32

[8] Cevik A, Atmaca N, Ekmekyapar T, Guzelbey IH. Flexural buckling load prediction of aluminium alloy columns using soft computing techniques. Expert Systems with Applications, 2009, 36: 6332-6342

[9] Ghani S, Kumar N, Gupta M, et al. Machine learning approaches foe real-time prediction of compressive strength in self-compacting concrete. Asian Journal of Civil Engineering, 2024, 25: 2743-2760

[10] Hakim SJS, Paknahad M, Kamarudin AF, Ravanfar SA, Mokhatar SN. Buckling prediction in steel columns: Unveiling insights with artificial neural networks. International Journal of Engineering Trends and Technology, 2023, 71(9): 322-330

[11] Homaeinezhad MR, Atyabi SA, Tavakkoli E, Toosi HN, Ghaffari A, Ebrahimpour R. ECG arrhythmia recognition via a Neuro-SVM–KNN Hybrid classifier with virtual QRS image-based geometrical features. Expert Systems with Applications, 2012, 39: 2047-2058

[12] Jayabalan J, Dominic M, Ebid MA, Soleymani A, Onyelowe KC, Jahangir H. Estimating the buckling load of steel plates with centre cut-outs by ANN, GEP and EPR Techniques. Designs, 2022, 6(5): 84

[13] Kaveh A, Ghaffarian R. Shape optimization of arch dams with frequency constraints by enhanced charged system search algorithm and neural network. IJCE, 2015, 13(1): 102-111

[14] Kaveh A, Hasana S. Optimal design of tapered latticed columns using four meta-heuristic optimization algorithms. Asian J Civ Eng, 2016, 17: 259-270

[15] Kaveh A, Khavnaninzadeh N. Efficient training of two ANNs using four meta-heuristic algorithms for predicting the FRP strength. Structures, 2023, 52: 256-272

[16] Kaveh A, Mahdavi VR. Shape optimization of arch dams under earthquake loading using meta-heuristic algorithms. KSCE Journal of Civil Engineering, 2013, 17: 1690-1699

[17] Kaveh A, Mottaghi L, Izadifard RA. Optimal design of a non-prismatic reinforced concrete box girder bridge with three meta-heuristic algorithms. Scientia Iranica, 2022, 29(3): 1154-1167

[18] Le LM, Ly H-B, Pham BT, Le VM, Pham TA, Nguyen D-H, Tran X-T, Le T-T. Hybrid artificial intelligence approaches for predicting buckling damage of steel columns under axial compression. Materials, 2019, 12(10): 1670

[19] Ly H-B, Le T-T, Le LM, Tran V, Le VM, Vu H-LT, Nguyen Q, Pham B. Development of hybrid machine learning models for predicting the critical buckling load of I-shaped cellular beams. Applied Sciences, 2019, 9(24): 5458

[20] Mahmoodzadeh A, Mohammadi M, Farid Hama Ali H, Hashim Ibrahim H, Nariman Abdulhamid S, Nejati HR. Prediction of safety factors for slope stability: comparison of machine learning techniques. Natural Hazards, 2022, 111: 1771-1799

[21] Mendez G, Sharon L. Estimating residual variance in random forest regression. Computational Statistics & Data Analysis, 2011, 55: 2937-2950

[22] Mishra P, Samui P, Mahmoudi E. Probabilistic design of retaining wall using machine learning methods. Applied Sciences, 2021, 11(12): 5411

[23] Mouzoun K, Zemed N, Bouyahyaoui A, et al. Artificial neural networks and support vector regression for predicting slump and compressive strength of PET-modified concrete. Asian J Civ Eng, 2024

[24] Mukherjee A, Deshpande JM, Anmala J. Prediction of buckling of columns using artificial neural networks. Journal of Structural Engineering, 1996

[25] Mustafa R, Samui P, Kumari S. Reliability analysis of gravity retaining wall using hybrid ANFIS. Infrastructures, 2022, 7(9): 121

[26] Nath SK, Sengupta A, Srivastava A. Remote sensing GIS-based landslide susceptibility & risk modelling in Darjeeling–Sikkim Himalaya together with FEM-based slope stability analysis of the terrain. Natural Hazards, 2021, 108: 3271-3304

[27] Nguyen TA, Ly HB, Mai HVH, Tran VQ. Using ANN to estimate the critical buckling load of Y shaped cross-section steel columns. Scientific Programming, 2021

[28] Ozbayrak A, Ali MK, Citakoglu H. Buckling load estimation using multiple linear regression analysis and multigene genetic programming method in cantilever beams with transverse stiffeners. Arabian Journal for Science and Engineering, 2022, 48(4): 5347-5370

[29] Shah AD, Bartlett JW, Carpenter J, Nicholas O, Notes HHA. Comparison of random forest and parametric imputation models for imputing missing data using MICE: A CALIBER study. American Journal of Epidemiology, 2014, 179: 764-774

[30] Shahbazi Y, Delavari E, Chenaghlou R. Predicting the buckling load of smart multilayer columns using soft computing tools. Smart Structures and Systems, 2013, 13: 81-98

[31] Shahin RI, Ahmed M, Liang QQ, Yehia SA. Predicting the web crippling capacity of cold-formed steel lipped channels using hybrid machine learning techniques. Engineering Structures, 2024, 309: 118061

[32] Sharifi Y, Hosseinpour M, Moghbeli A, Sharifi H. Lateral torsional buckling capacity assessment of castellated steel beams using artificial neural networks. International Journal of Steel Structures, 2019

[33] Sheidaii MR, Bahraminejad R. Evaluation of compression member buckling and post-buckling behavior using artificial neural network. Journal of Constructional Steel Research, 2012, 70: 71-77

[34] Tahir ZR, Mandal P, Adil MT, Naz F. Application of artificial neural network to predict buckling load of thin cylindrical shells under axial compression. Engineering Structures, 2021, 248: 113221

[35] Tan S. An effective refinement strategy for KNN text classifier. Expert Systems with Applications, 2006, 30: 290-298

[36] Trstenjak B, Mikac S, Donko D. KNN with TF-IDF based framework for text categorization. Procedia Engineering, 2014, 69: 1356-1364

[37] Wang T, Zha Z, Pan C. Prediction for elastic local buckling stress and ultimate strength of H-section beam. Heliyon, 2023, 9(4):

[38] Wu K, Qiang X, Xing Z, Jiang X. Buckling in prestressed stayed beam–columns and intelligent evaluation. Engineering Structures, 2022, 255: 113902

[39] Zhang, H., Berg, A. C., Maire, M., & Malik, J. (2006). SVM-KNN: Discriminative nearest neighbor classification for visual category recognition. In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR06) (IEEE). https://doi.org/10.1109/CVPR.2006.301

[40] Zhang H, Li D, Li F. Buckling critical load prediction of pultruded fibre-reinforced polymer columns and features analysis by machine learning. Advances in Structural Engineering, 2024

[41] Ziegler A, Konig IR. Mining data with random forests: Current options for real–world applications. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2014, 4: 55-63