Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

• Autorzy: Farrokhi Farshid , Rahimi Sepideh

Identyfikatory

DOI

10.2478/sgem-2019-0043

• Języki publikacji: EN

Abstrakty

EN

In this study, firstly, the behavior of a high steel frame equipped with tuned mass damper (TMD) due to several seismic records is investigated considering the structural and seismic uncertainties. Then, machine learning methods including artificial neural networks (ANN), decision tree (DT), Naïve Bayes (NB) and support vector machines (SVM) are used to predict the behavior of the structure. Results showed that among the machine learning models, SVM with Gaussian kernel has better performance since it is capable of predicting the drift of stories and the failure probability with R² value equal to 0.99. Furthermore, results of feature selection algorithms revealed that when using TMD in high steel structures, seismic uncertainties have greater influences on drift of stories in comparison with structural uncertainties. Findings of this study can be used in design and probabilistic analysis of high steel frames equipped with TMDs.

Słowa kluczowe

EN

failure analysis; supervised machine learning; feature selection; tuned mass damper

• Wydawca: De Gruyter
• Czasopismo: Studia Geotechnica et Mechanica
• Rocznik: 2020
• Tom: Vol. 42, nr 3
• Strony: 179--190
• Opis fizyczny: Bibliogr. 31 poz., tab., rys.

Twórcy

autor

Farrokhi Farshid

• Department of Civil Engineering, Noor Branch, Islamic Azad University, Iran

autor

Rahimi Sepideh

• Department of Civil Engineering, Noor Branch, Islamic Azad University, Iran

Bibliografia

• [1] Ahmad, M. F., Haydar, S., Bhatti, A. A., Bari, A. J. (2014). Application of artificial neural network for the prediction of biosorption capacity of immobilized Bacillus subtilis for the removal of cadmium ions from aqueous solution. Biochemical engineering journal, 84, 83–90.
• [2] Asefpour Vakilian, K., Massah, J. (2018). A portable nitrate biosensing device using electrochemistry and spectroscopy. IEEE Sensors Journal, 18(8), 3080–3089.
• [3] Basak, D., Pal, S., Patranabis, D. C. (2007). Support vector regression. Neural Information Processing-Letters and Reviews, 11(10), 203–224.
• [4] Bekdaş, G., Nigdeli, S. M. (2011). Estimating optimum parameters of tuned mass dampers using harmony search. Engineering Structures, 33(9), 2716–2723.
• [5] Chey, M. H., Chase, J. G., Mander, J. B., Carr, A. J. (2010). Semi-active tuned mass damper building systems: Application. Earthquake Engineering & Structural Dynamics, 39(1), 69–89.
• [6] Cramér H. (2016). Mathematical Methods of Statistics, vol. 9. Princeton, NJ, USA: Princeton University Press.
• [7] Debbarma R., Debnath D. (2013). Earthquake Response Control of 3-Story Building Structures by Tuned Mass Damper. International Journal of Engineering and Innovative Technology, 2, 187–192.
• [8] Deierlein, G. G., Reinhorn, A. M., Willford, M. R. (2010). Nonlinear structural analysis for seismic design. NEHRP seismic design technical brief, 4, 1–36.
• [9] Farrokhi, F., Rahimi, S. (2017). Probabilistic failure analysis of high steel frames with tuned mass damper. In XI Conference on Steel and Composite Construction, Coimbra, Portugal, 23 and 24 November, 2017, 507–514.
• [10] Giaralis, A., Taflanidis, A. A. (2018). Optimal tuned mass-damper-inerter (TMDI) design for seismically excited MDOF structures with model uncertainties based on reliability criteria. Structural Control and Health Monitoring, 25(2), e2082.
• [11] Guyon, I., Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of machine learning research, 3, 1157–1182.
• [12] Hashemi, A., Asefpour Vakilian, K., Khazaei, J., Massah, J. (2014). An artificial neural network modeling for force control system of a robotic pruning machine. Journal of Information and Organizational Sciences, 38(1), 35–41.
• [13] Huang, J., Cai, Y., Xu, X. (2007). A hybrid genetic algorithm for feature selection wrapper based on mutual information. Pattern Recognition Letters, 28(13), 1825–1844.
• [14] Kappos, A. J., Papanikolaou, V. K. (2016). Nonlinear dynamic analysis of masonry buildings and definition of seismic damage states. The Open Construction and Building Technology Journal, 10(1), 192–209.
• [15] Krishnan, S. (2007). Case studies of damage to 19-storey irregular steel moment-frame buildings under near-source ground motion. Earthquake engineering & structural dynamics, 36(7), 861–885.
• [16] Li, H., Huo, L. (2010). Advances in structural control in civil engineering in China. Mathematical Problems in Engineering, 1–23.
• [17] Lin, S. W., Lee, Z. J., Chen, S. C., Tseng, T. Y. (2008). Parameter determination of support vector machine and feature selection using simulated annealing approach. Applied soft computing, 8(4), 1505–1512.
• [18] Liu, H., Li, J., Wong, L. (2002). A comparative study on feature selection and classification methods using gene expression profiles and proteomic patterns. Genome informatics, 13, 51–60.
• [19] Liu, H., Liu, L., Zhang, H. (2009). Boosting feature selection using information metric for classification. Neurocomputing, 73(1), 295–303.
• [20] Marano, G. C., Greco, R., Chiaia, B. (2010). A comparison between different optimization criteria for tuned mass dampers design. Journal of Sound and Vibration, 329(23), 4880–4890.
• [21] Massah, J., Asefpour Vakilian, K. (2019). An intelligent portable biosensor for fast and accurate nitrate determination using cyclic voltammetry. Biosystems Engineering, 177, 49–58.
• [22] Michalski, R.S., Carbonell, J. G., Mitchell, T. M. (2013). Machine Learning, An Artificial Intelligence Approach. Berlin, Germany: Springer.
• [23] Mohebbi, M., Shakeri, K., Ghanbarpour, Y., Majzoub, H. (2013). Designing optimal multiple tuned mass dampers using genetic algorithms (GAs) for mitigating the seismic response of structures. Journal of Vibration and Control, 19(4), 605–625.
• [24] Moustakidis, S. P., Theocharis, J. B. (2010). SVM-FuzCoC: A novel SVM-based feature selection method using a fuzzy complementary criterion. Pattern Recognition, 43(11), 3712–3729.
• [25] Muto, M., Krishnan, S. (2011). Hope for the best, prepare for the worst: Response of tall steel buildings to the shakeout scenario earthquake. Earthquake Spectra, 27(2), 375–398.
• [26] Pozos-Estrada, A., Hong, H. P. (2015). Sensitivity Analysis of the Effectiveness of Tuned Mass Dampers to Reduce the Wind-Induced Torsional Responses. Latin American Journal of Solids and Structures, 12(13), 2520–2538.
• [27] Sadek, F., Mohraz, B., Taylor, A. W., Chung, R. M. (1997). A method of estimating the parameters of tuned mass dampers for seismic applications. Earthquake Engineering & Structural Dynamics, 26(6), 617–635.
• [28] Soto, M. G., Adeli, H. (2013). Tuned mass dampers. Archives of Computational Methods in Engineering, 20(4), 419–431.
• [29] Sun, X., Liu, Y., Li, J., Zhu, J., Chen, H., Liu, X. (2012). Feature evaluation and selection with cooperative game theory. Pattern recognition, 45(8), 2992-3002.
• [30] Vickery, B. J., Galsworthy, J. K., Gerges, R. (2001). The behaviour of simple non-linear tuned mass dampers. In 6th World Congress of the Council on Tall Buildings and Urban Habitat, Melbourne, Australia.
• [31] Wang, L., Shi, W., Zhou, Y. (2019). Study on self-adjustable variable pendulum tuned mass damper. The Structural Design of Tall and Special Buildings, 28(1), e1561.