On the Use of  Spectral Data from Smartphone Accelerometer Signals and  Constituent Material for the Identification of Damaged Walls

Tales Boratto; Douglas Lima Fonseca; Heder Soares Bernardino; Alex Borges; Alexandre Cury; Leonardo Goliatt

doi:10.22456/2175-2745.142129

Authors

Tales Boratto Universidade Federal de Juiz de Fora (UFJF)
Douglas Lima Fonseca Universidade Federal de Juiz de Fora (UFJF)
Heder Soares Bernardino Universidade Federal de Juiz de Fora (UFJF)
Alex Borges Universidade Federal de Juiz de Fora (UFJF)
Alexandre Cury Universidade Federal de Juiz de Fora (UFJF)
Leonardo Goliatt Universidade Federal de Juiz de Fora (UFJF) https://orcid.org/0000-0002-2844-9470

DOI:

https://doi.org/10.22456/2175-2745.142129

Keywords:

Damage Detection, Structural Health Monitoring, Vibration Monitoring, Machine Learning

Abstract

Monitoring the integrity of civil structures is crucial for ensuring their safety and longevity. Assessing the structural condition of walls is particularly important due to their role in stability and load distribution in buildings. Smartphones can be used to collect dynamic data from the walls of modern buildings. This strategy is an easier and cheaper way to obtain information concerning the wall's structural condition compared to other costly instrumentation plans using deflectomers, accelerometers, etc. Such a type of data was explored in the literature with good results. However, despite the quality of the models obtained, other features can be included to improve the results. For instance, spectral information may characterize the frequency content of a signal. Moreover, the material used to build the structure affects the signals collected. Thus, we propose the use of three machine learning models (Decision Tree, Random Forest, and K-Nearest Neighbors (KNN)) to identify damage in walls from vibration signals using their spectral data and the wall's constituent material in addition to those already used in the literature. The proposed improvements increased accuracy by about 23%, leading to an average accuracy of 97.78% with KNN when combining statistical and spectral features.

Downloads

Download data is not yet available.

References

FRANGOPOL, D. M.; LIU, M. Maintenance and management of civil infrastructure based on condition, safety, optimization, and life-cycle cost. Structures and Infrastructure Systems, Routledge, p. 96–108, 2019.

ROBSON, P. Structural repair of traditional buildings. [S.l.]: Routledge, 2015.

STEWART, M. G.; ROSOWSKY, D. V. Structural safety and serviceability of concrete bridges subject to corrosion. Journal of Infrastructure Systems, American Society of Civil Engineers, v. 4, n. 4, p. 146–155, 1998.

ALVES, V.; CURY, A.; CREMONA, C. On the use of symbolic vibration data for robust structural health monitoring. Proceedings of the Institution of Civil Engineers - Structures and Buildings, v. 169, n. 9, p. 715–723, 2016.

ALVES, V.; CURY, A. An automated vibration-based structural damage localization strategy using filter-type feature selection. Mechanical Systems and Signal Processing, v. 190, p. 110145, 2023. ISSN 0888-3270.

AZIMI, M.; ESLAMLOU, A. D.; PEKCAN, G. Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review. Sensors, v. 20, n. 10, 2020. ISSN 1424-8220.

SARMADI, H. et al. Review on smartphone sensing technology for structural health monitoring. Measurement, v. 223, p. 113716, 2023. ISSN 0263-2241.

FINOTTI, R. P. et al. Numerical and experimental evaluation of structural changes using sparse auto-encoders and SVM applied to dynamic responses. Applied Sciences, v. 11, n. 24, 2021. ISSN 2076-3417.

MAGALHÃES, F.; CUNHA, A.; CAETANO, E. Vibration-based structural health monitoring of an arch bridge: From automated OMA to damage detection. Mechanical Systems and Signal Processing, v. 28, p. 212–228, 2012. ISSN 0888-3270. Interdisciplinary and Integration Aspects in Structural Health Monitoring.

GENTILE, C.; RUCCOLO, A.; CANALI, F. Continuous monitoring of the Milan Cathedral: Dynamic characteristics and vibration-based SHM. Journal of Civil Structural Health Monitoring, Springer Science and Business Media LLC, v. 9, n. 5, p. 671–688, out. 2019. ISSN 2190-5479.

UBERTINI, F.; COMANDUCCI, G.; CAVALAGLI, N. Vibration-based structural health monitoring of a historic bell-tower using output-only measurements and multivariate statistical analysis. Structural Health Monitoring, v. 15, n. 4, p. 438–457, 2016.

GHOSHAL, A. et al. Structural health monitoring techniques for wind turbine blades. Journal of Wind Engineering and Industrial Aerodynamics, v. 85, n. 3, p. 309–324, 2000. ISSN 0167-6105.

PEREIRA, S. et al. Vibration-based damage detection of a concrete arch dam. Engineering Structures, v. 235, p. 112032, 2021. ISSN 0141-0296.

FENG, M. et al. Citizen sensors for SHM: Use of accelerometer data from smartphones. Sensors, v. 15, n. 2, p. 2980–2998, 2015. ISSN 1424-8220.

KANG, J.-D.; BAEK, E.-R.; PARK, S.-H. Evaluation of vibration detection using smartphones in a two-story masonry-infilled RC frame building. Buildings, v. 13, n. 4, 2023. ISSN 2075-5309.

FIGUEIREDO, E. et al. Smartphone application for structural health monitoring of bridges. Sensors, v. 22, n. 21, 2022. ISSN 1424-8220.

SUN, W. Vibwall: Smartphone’s vibration challenge-response for wall crack detection. ACM J. Comput. Sustain. Soc., Association for Computing Machinery, New York, NY, USA, v. 1, n. 1, sep. 2023.

ABDUL, Z. K.; AL-TALABANI, A. K. Mel frequency cepstral coefficient and its applications: A review. IEEE Access, v. 10, p. 122136–122158, 2022.

SHALEV-SHWARTZ, S.; BEN-DAVID, S. Understanding Machine Learning: From Theory to Algorithms. USA: Cambridge University Press, 2014. ISBN 1107057132.

LIAO, Y.; VEMURI, V. R. Use of k-nearest neighbor classifier for intrusion detection. Computers & Security, Elsevier, v. 21, n. 5, p. 439–448, 2002.

GUO, G. et al. KNN model-based approach in classification. In: MEERSMAN, R.; TARI, Z.; SCHMIDT, D. C. (Ed.). On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE. Berlin, Heidelberg: Springer Berlin Heidelberg, 2003. p. 986–996. ISBN 978-3-540-39964-3.

ALFEILAT, H. A. A. et al. Effects of distance measure choice on k-nearest neighbor classifier performance: A review. Big Data, Mary Ann Liebert Inc, v. 7, n. 4, p. 221–248, dez. 2019. ISSN 2167-647X.

LAAKSONEN, J.; OJA, E. Classification with learning k-nearest neighbors. In: IEEE. Proceedings of International Conference on Neural Networks (ICNN’96). [S.l.], 1996. v. 3, p. 1480–1483.

DUDANI, S. A. The distance-weighted k-nearest-neighbor rule. IEEE Transactions on Systems, Man, and Cybernetics, SMC-6, n. 4, p. 325–327, 1976.

SAFAVIAN, S. R.; LANDGREBE, D. A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, IEEE, v. 21, n. 3, p. 660–674, 1991.

PEDREGOSA, F. et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, v. 12, p. 2825–2830, 2011.

BREIMAN, L. Classification and Regression Trees. [S.l.]: Routledge, 2017.

WEBB, A. R.; COPSEY, K. D.; CAWLEY, G. Statistical Pattern Recognition. 3. ed. Hoboken, NJ: Wiley-Blackwell, 2011.

BREIMAN, L. Random forests. Machine Learning, v. 45, n. 1, p. 5–32, Oct. 2001. ISSN 1573-0565.

PAL, M. Random forest classifier for remote sensing classification. International Journal of Remote Sensing, Taylor & Francis, v. 26, n. 1, p. 217–222, 2005.

LYONS, J. et al. jameslyons/python_speech_features: Release v0.6.1. [S.l.]: Zenodo, 2020.

CLOUGH, R. W.; PENZIEN, J. Dynamics of Structures. New York, NY: McGraw-Hill, 1975.

BARANDAS, M. et al. TSFEL: Time series feature extraction library. SoftwareX, Elsevier, v. 11, p. 100456, 2020.

HARRIS, C. R. et al. Array programming with NumPy. Nature, Nature Publishing Group UK London, v. 585, n. 7825, p. 357–362, 2020.

VIRTANEN, P. et al. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nature Methods, Nature Publishing Group, v. 17, n. 3, p. 261–272, 2020.

BORATTO, T.; CURY, A.; GOLIATT, L. A fuzzy approach to drum cymbals classification. IEEE Latin America Transactions, v. 20, n. 9, p. 2172–2180, Jun. 2022.

BORATTO, T. H. A. et al. Data-driven cymbal bronze alloy identification via evolutionary machine learning with automatic feature selection. Journal of Intelligent Manufacturing, Springer Science and Business Media LLC, nov. 2022.