Seismic response prediction for torsionally irregular buildings using structural health monitoring and machine learning
DOI:
https://doi.org/10.21754/tecnia.v35i1.2510Palabras clave:
Seleccionado:degree of torsional irregularity, structural health monitoring, maximum drift, numerical simulation, dynamic testsResumen
Given the seismic risk that buildings in Peru face, monitoring the structural health of critical infrastructure is essential. Structural health monitoring (SHM) is commonly carried out at the center of mass (CM) of buildings using accelerometers. However, in torsional irregular structures, the maximum response does not occur at the CM due to the torsional effect produced by the existing in-plan eccentricity between the centers of stiffness (CS) and mass. This research proposes a methodology to estimate the maximum response in buildings with torsional effects using SHM with accelerometers positioned at the CM. In the proposed methodology, the degree of torsional irregularity was defined to enable the calculation of the maximum seismic response. Consequently, a new machine learning model for predicting the degree of torsional irregularity was developed using 9,358 seismic simulations. The prediction model achieved a normalized error of 4.054% in estimating the maximum seismic response. Likewise, incremental dynamic tests were carried out on a shaking table with 8 specimens having different structural configurations. The experimental results were used to assimilate the developed model with the numerical results, thus obtaining a hybrid prediction model for the degree of torsional irregularity. Finally, a mathematical expression was proposed to estimate the degree of torsional irregularity using experimental results based on the structural and seismic characteristics validated with the hybrid prediction model. The proposed methodology is important because this tool can provide a more accurate assessment of the state of torsional irregular structures after the occurrence of an earthquake.
Descargas
Citas
[1] N. Pulido et al., “Scenario Source Models and Strong Ground Motion for Future Mega‐earthquakes: Application to Lima, Central Peru,” Bulletin of the Seismological Society of America, vol. 105, no. 1, pp. 368–386, Feb. 2015, doi: 10.1785/0120140098.
[2] A. Ibrahim, A. Eltawil, Y. Na, and S. El-Tawil, “A Machine Learning Approach for Structural Health Monitoring Using Noisy Data Sets,” IEEE Trans. Automat. Sci. Eng., vol. 17, no. 2, pp. 900–908, Apr. 2020, doi: 10.1109/TASE.2019.2950958.
[3] C. Gonzales et al., “Preliminary System for the Estimation of Peak Ground Acceleration Distribution in Metropolitan Lima and Callao: Application in Recent Seismic Events,” JDR, vol. 18, no. 4, pp. 319–328, Jun. 2023, doi: 10.20965/jdr.2023.p0319.
[4] H. Gokdemir, H. Ozbasaran, M. Dogan, E. Unluoglu, and U. Albayrak, “Effects of torsional irregularity to structures during earthquakes,” Engineering Failure Analysis, vol. 35, pp. 713–717, Dec. 2013, doi: 10.1016/j.engfailanal.2013.06.028.
[5] Y. Bozorgnia and W. K. Tso, “Inelastic earthquake response of asymmetric structures,” Journal of Structural Engineering, vol. 112, no. 2, pp. 383-400, Feb. 1986, doi: 10.1061/(ASCE)0733-9445(1986)112:2(383).
[6] A. K. Chopra and R. K. Goel, “Effects of plan asymmetry in inelastic seismic response of one-story systems,” Journal of Structural Engineering, vol. 117, no. 5, pp. 1492–1513, May 1991, doi: 10.1061/(ASCE)0733-9445(1991)117:5(1492).
[7] K. M. Alaa, K. F. El-Kashif, and H. M. Salem, “New definition for torsional irregularity based on floor rotations of reinforced concrete buildings,” Journal of Engineering and Applied Science, vol. 69, no. 12, 2022, doi: 10.1186/s44147-021-00061-5.
[8] B. K. Oh, B. Glisic, S. W. Park, and H. S. Park, “Neural network-based seismic response prediction model for building structures using artificial earthquakes,” Journal of Sound and Vibration, vol. 468, p. 115109, Mar. 2020, doi: 10.1016/j.jsv.2019.115109.
[9] J. Jaramillo, M. Diaz, C. Zavala, K. Kusunoki, I. Inocente, and D. Otero, “Wavelet Transform Method for the Evaluation of the Seismic Response of One Isolated Building in the Lima Metropolitan Area,” JDR, vol. 18, no. 4, pp. 338–349, Jun. 2023, doi: 10.20965/jdr.2023.p0338.
[10] K. A. O. Galindo, “Evaluación del efecto de la simultaneidad de las componentes de sismo en estructuras con irregularidad torsional,” Thesis, Universidad Nacional de Ingeniería, Lima, 2019.
[11] T. Suzuki, A. Puranam, K. Elwood, H. Lee, F. Hsiao, and S. Hwang, “Shake table tests of seven-story reinforced concrete structures with torsional irregularities: Test program and datasets,” Earthquake Spectra, vol. 37, no. 4, pp. 2946–2970, 2021, doi: 10.1177/87552930211016869.
[12] S. Raschka, Y. Liu, and V. Mirjalili, Machine Learning with PyTorch and Scikit-Learn, Packt Publishing, 1st ed., Feb. 2022, ISBN 978-1-80181-931-2.
[13] A. Géron, Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow Concepts, Tools, and Techniques to Build Intelligent Systems SECOND EDITION, 2nd ed. O’Reilly Media, 2019, ISBN 978-1-492-03264-9.
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2025 TECNIA
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Los artículos publicados por TECNIA pueden ser compartidos a través de la licencia pública internacional Creative Commons: CC BY 4.0. Permisos lejos de este alcance pueden ser consultados a través del correo tecnia@uni.edu.pe
