Abstract
Various methods have been proposed so far for damage detection of structures that use certain sensors to collect data. The sensitivity of different sensors to damage varies among the statistic parameters (features) extracted from signals obtained from them. In this paper, the concept of feature-sensor is proposed for the first time in this area. That is to say, for each effective sensor, a specific feature is designated. First, 17 features are selected, and each feature is assigned to all of the sensors. Using the Gini index, the most important feature-sensors are selected, and the accuracy of each feature-sensor is investigated using support vector machine (SVM). Next, feature selection is used to improve the accuracy of damage detection by using a combination of feature-sensors. The proposed method is validated by data from a real cable-stayed bridge. Results show that the method is able to distinguish damaged and healthy states with almost 98% accuracy.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig1_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40996-023-01228-1/MediaObjects/40996_2023_1228_Fig14_HTML.png)
Similar content being viewed by others
References
Alpaydin E (2014) Introduction to machine learning Ethem Alpaydin. MIT press
Alves V, Cury A (2021) A fast and efficient feature extraction methodology for structural damage localization based on raw acceleration measurements. Struct Control Health Monit. https://doi.org/10.1002/stc.2748
Alves VN, de Oliveira MM, Ribeiro D, Calçada R, Cury A (2020) Model-based damage identification of railway bridges using genetic algorithms. Eng Fail Anal 118:104845. https://doi.org/10.1016/j.engfailanal.2020.104845
Arangio S, Bontempi F (2015) Structural health monitoring of a cable-stayed bridge with Bayesian neural networks. Struct Infrastruct Eng. https://doi.org/10.1080/15732479.2014.951867
Aravanis TCI, Sakellariou JS, Fassois SD (2022) Damage precise localization under varying operating conditions via the vibration-data-based Functional Model method: Formulation and experimental validation. J Sound Vib. https://doi.org/10.1016/j.jsv.2022.117078
Asgarian B, Aghaeidoost V, Shokrgozar HR (2016) Damage detection of jacket type offshore platforms using rate of signal energy using wavelet packet transform. Mar Struct 45:1–21. https://doi.org/10.1016/j.marstruc.2015.10.003
Betti M, Facchini L, Biagini P (2015) Damage detection on a three-storey steel frame using artificial neural networks and genetic algorithms. Meccanica 50:875–886. https://doi.org/10.1007/s11012-014-0085-9
Casciati S, Elia L (2015) The potential of the firefly algorithm for damage localization and stiffness identification. Stud Comput Intel 585:163–178. https://doi.org/10.1007/978-3-319-13826-8_9
Dipietrangelo F, Nicassio F, Scarselli G (2022) Structural health monitoring for impact localisation via machine learning. Mech Syst Signal Process. https://doi.org/10.1016/j.ymssp.2022.109621
Fathi A, Esfandiari A, Fadavie M, Mojtahedi A (2020) Damage detection in an offshore platform using incomplete noisy FRF data by a novel Bayesian model updating method. Ocean Eng 217:108023. https://doi.org/10.1016/j.oceaneng.2020.108023
Flah M, Ragab M, Lazhari M, Nehdi ML (2022) Localization and classification of structural damage using deep learning single-channel signal-based measurement. Autom Constr. https://doi.org/10.1016/j.autcon.2022.104271
Kaloop MR, Hu JW (2015) Stayed-cable bridge damage detection and localization based on accelerometer health monitoring measurements. Shock Vib. https://doi.org/10.1155/2015/102680
Kaloop MR, Hu JW, Elbeltagi E (2016) Adjustment and assessment of the measurements of low and high sampling frequencies of GPS real-time monitoring of structural movement. ISPRS Int J Geoinf. https://doi.org/10.3390/ijgi5120222
Khuc T, Nguyen PT, Nguyen A, Catbas FN (2020) A nonparametric method for identifying structural damage in bridges based on the best-fit auto-regressive models. Int J Struct Stab Dyn. https://doi.org/10.1142/S0219455420420122
Li S et al (2014) SMC structural health monitoring benchmark problem using monitored data from an actual cable-stayed bridge. Struct Control Health Monit. https://doi.org/10.1002/stc.1559
Liu H, Yu L (2005) Toward integrating feature selection algorithms for classification and clustering. IEEE Trans Knowl Data Eng 17:491–502. https://doi.org/10.1109/TKDE.2005.66
Maszczyk T, Duch W. 2008. Comparison of Shannon, Renyi and Tsallis. 643–651
Mousavi AA, Zhang C, Masri SF, Gholipour G (2020) Structural damage localization and quantification based on a CEEMDAN hilbert transform neural network approach: A model steel truss bridge case study. Sensors (switzerland). https://doi.org/10.3390/s20051271
Nembrini S, König IR, Wright MN (2018) The revival of the Gini importance? Bioinformatics 34:3711–3718. https://doi.org/10.1093/bioinformatics/bty373
Renyi A (1970) Probability Theory, English. North-Holland Pub Co, Amsterdam
Shokoohi-Yekta M, Hu B, ** H, Wang J, Keogh E (2017) Generalizing DTW to the multi-dimensional case requires an adaptive approach. Data Min Knowl Discov. https://doi.org/10.1007/s10618-016-0455-0
Torabi M, Ghodrati Amiri G, Darvishan E (2022) Health monitoring of bridges by using the available data based on deep learning. J Struct Constr Eng 8:459–477. https://doi.org/10.22065/jsce.2021.274265.2367
Tsallis C, Mendes RS, Plastino AR (1998) The role of constraints within generalized nonextensive statistics. Physica A 261:534–554. https://doi.org/10.1016/S0378-4371(98)00437-3
Yin X, Huang Z, Liu Y (2022) Damage features extraction of prestressed near-surface mounted CFRP beams based on tunable Q-factor wavelet transform and improved variational modal decomposition. Structures. https://doi.org/10.1016/j.istruc.2022.10.0366
Funding
This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest regarding the publication of this paper.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Afsharmovahed, M.H., Ghodrati Amiri, G. & Darvishan, E. A Novel Damage Detection Approach Based on Feature Extraction and Selection Using Machine Learning Without Signal Processing: A Case Study on the Tian** Yonghe Bridge. Iran J Sci Technol Trans Civ Eng 47, 3649–3661 (2023). https://doi.org/10.1007/s40996-023-01228-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40996-023-01228-1