{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:55:07Z","timestamp":1780332907046,"version":"3.54.1"},"reference-count":73,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T00:00:00Z","timestamp":1688428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>For the purpose of maintaining and prolonging the service life of civil constructions, structural damage must be closely monitored. Monitoring the incidence, formation, and spread of damage is crucial to ensure a structure\u2019s ongoing performance. This research proposes a unique approach for multiclass damage detection using acceleration responses based on synchrosqueezing transform (SST) together with deep learning algorithms. In particular, our pipeline is able to classify correctly the time series representing the responses of accelerometers placed on a bridge, which are classified with respect to different types of damage scenarios applied to the bridge. Using benchmark data from the Z24 bridge for multiclass classification for different damage situations, the suggested method is validated. This dataset includes labeled accelerometer measurements from a real-world bridge that has been gradually damaged by various conditions. The findings demonstrate that the suggested approach is successful in exploiting pre-trained 2D convolutional neural networks, obtaining a high classification accuracy that can be further boosted by the application of simple voting methods.<\/jats:p>","DOI":"10.3390\/s23136152","type":"journal-article","created":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T00:53:04Z","timestamp":1688518384000},"page":"6152","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Bridge Damage Identification Using Deep Neural Networks on Time\u2013Frequency Signals Representation"],"prefix":"10.3390","volume":"23","author":[{"given":"Pasquale","family":"Santaniello","sequence":"first","affiliation":[{"name":"DIAG Department, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185 Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1886-3491","authenticated-orcid":false,"given":"Paolo","family":"Russo","sequence":"additional","affiliation":[{"name":"DIAG Department, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185 Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,4]]},"reference":[{"key":"ref_1","unstructured":"Rytter, A. (1993). Vibrational Based Inspection of Civil Engineering Structures. [Ph.D. Thesis, Aalborg University]."},{"key":"ref_2","unstructured":"Farrar, C., Sohn, H., Hemez, F., Anderson, M., Bement, M., Cornwell, P., Doebling, S., Schultze, J., Lieven, N., and Robertson, A. (2003). Damage Prognosis: Current Status and Future Needs, Los Alamos National Laboratory. Technical Report, LA-14051-MS."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Inman, D.J., Farrar, C.R., Junior, V.L., and Junior, V.S. (2005). Damage Prognosis: For Aerospace, Civil and Mechanical Systems, John Wiley & Sons.","DOI":"10.1002\/0470869097"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1177\/1475921717750047","article-title":"Structural health monitoring: Closing the gap between research and industrial deployment","volume":"17","author":"Cawley","year":"2018","journal-title":"Struct. Health Monit."},{"key":"ref_5","unstructured":"Fritzen, C.P. (2014). Vibration-Based Methods for SHM, NATO."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/j.jsv.2003.06.010","article-title":"Damage identification in structures using the time-domain response","volume":"275","author":"Choi","year":"2004","journal-title":"J. Sound Vib."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1006\/mssp.1996.0086","article-title":"Time domain analysis for damage detection in smart structures","volume":"11","author":"Cattarius","year":"1997","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Barthorpe, R.J., and Worden, K. (2020). Emerging trends in optimal structural health monitoring system design: From sensor placement to system evaluation. J. Sens. Actuator Netw., 9.","DOI":"10.3390\/jsan9030031"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1006\/jsvi.1996.0160","article-title":"An experimentally validated damage detection theory in smart structures","volume":"191","author":"Banks","year":"1996","journal-title":"J. Sound Vib."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/S0045-7949(99)00194-7","article-title":"A study on crack detection using eigenfrequency test data","volume":"77","author":"Lee","year":"2000","journal-title":"Comput. Struct."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1016\/j.compstruct.2017.06.019","article-title":"Sensitivity analysis of inverse algorithms for damage detection in composites","volume":"176","author":"Zhang","year":"2017","journal-title":"Compos. Struct."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1177\/1475921708089830","article-title":"Time-frequency method for nonlinear system identification and damage detection","volume":"7","author":"Pai","year":"2008","journal-title":"Struct. Health Monit."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1109\/18.57199","article-title":"The wavelet transform, time-frequency localization and signal analysis","volume":"36","author":"Daubechies","year":"1990","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_14","unstructured":"Andria, G., D\u2019ambrosio, E., Savino, M., and Trotta, A. (1993, January 18\u201320). Application of Wigner-Ville distribution to measurements on transient signals. Proceedings of the 1993 IEEE Instrumentation and Measurement Technology Conference, Irvine, CA, USA."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Karami-Mohammadi, R., Mirtaheri, M., Salkhordeh, M., and Hariri-Ardebili, M.A. (2020). Vibration anatomy and damage detection in power transmission towers with limited sensors. Sensors, 20.","DOI":"10.3390\/s20061731"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1109\/PROC.1977.10770","article-title":"A unified approach to short-time Fourier analysis and synthesis","volume":"65","author":"Allen","year":"1977","journal-title":"Proc. IEEE"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhang, Y., and Tan, X. (2021). Review on vibration-based structural health monitoring techniques and technical codes. Symmetry, 13.","DOI":"10.3390\/sym13111998"},{"key":"ref_18","unstructured":"Li, D. (2012). Sensor Placement Methods and Evaluation Criteria in Structural Health Monitoring. [Ph.D. Thesis, Universoty Siegen]."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2230005","DOI":"10.1142\/S0219455422300051","article-title":"Recent advances in researches on vehicle scanning method for bridges","volume":"22","author":"Wang","year":"2022","journal-title":"Int. J. Struct. Stab. Dyn."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mousa, M.A., Yussof, M.M., Udi, U.J., Nazri, F.M., Kamarudin, M.K., Parke, G.A., Assi, L.N., and Ghahari, S.A. (2021). Application of digital image correlation in structural health monitoring of bridge infrastructures: A review. Infrastructures, 6.","DOI":"10.3390\/infrastructures6120176"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1016\/j.engstruct.2004.12.006","article-title":"Damage detection in bridges using neural networks for pattern recognition of vibration signatures","volume":"27","author":"Yeung","year":"2005","journal-title":"Eng. Struct."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1016\/j.ymssp.2006.10.002","article-title":"Development in vibration-based structural damage detection technique","volume":"21","author":"Yan","year":"2007","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1016\/S0141-0296(02)00194-3","article-title":"A review of time-frequency methods for structural vibration analysis","volume":"25","author":"Neild","year":"2003","journal-title":"Eng. Struct."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"04018033","DOI":"10.1061\/(ASCE)BE.1943-5592.0001199","article-title":"Time-frequency-based data-driven structural diagnosis and damage detection for cable-stayed bridges","volume":"23","author":"Pan","year":"2018","journal-title":"J. Bridge Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MSP.2013.2265316","article-title":"Recent advances in time-frequency reassignment and synchrosqueezing","volume":"30","author":"Auger","year":"2013","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3605","DOI":"10.1016\/j.istruc.2021.06.081","article-title":"A novel damage identification method based on short time Fourier transform and a new efficient index","volume":"33","author":"Ahmadi","year":"2021","journal-title":"Structures"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1109\/TASSP.1987.1165070","article-title":"An efficient real-time implementation of the Wigner-Ville distribution","volume":"35","author":"Boashash","year":"1987","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"107077","DOI":"10.1016\/j.ymssp.2020.107077","article-title":"A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications","volume":"147","author":"Avci","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.ymssp.2007.07.003","article-title":"ARMA modelled time-series classification for structural health monitoring of civil infrastructure","volume":"22","author":"Carden","year":"2008","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Schaffer, A.L., Dobbins, T.A., and Pearson, S.A. (2021). Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: A guide for evaluating large-scale health interventions. BMC Med. Res. Methodol., 21.","DOI":"10.1186\/s12874-021-01235-8"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"108743","DOI":"10.1016\/j.ymssp.2021.108743","article-title":"A Kalman filter based ARX time series modeling for force identification on flexible manipulators","volume":"169","author":"Nguyen","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1002\/stc.1743","article-title":"Damage detection in structures using a transmissibility-based Mahalanobis distance","volume":"22","author":"Zhou","year":"2015","journal-title":"Struct. Control Health Monit."},{"key":"ref_33","unstructured":"Gupta, T.K., and Raza, K. (2019). Machine Learning in Bio-Signal Analysis and Diagnostic Imaging, Academic Press."},{"key":"ref_34","unstructured":"Vishwanathan, S., and Murty, M.N. (2002, January 12\u201317). SSVM: A simple SVM algorithm. Proceedings of the 2002 International Joint Conference on Neural Networks (IJCNN\u201902 (Cat. No. 02CH37290)), Honolulu, HI, USA."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","article-title":"Random forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J. Insur. Med."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1243\/095440605X8298","article-title":"Selection of K in K-means clustering","volume":"219","author":"Pham","year":"2005","journal-title":"Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2621","DOI":"10.1007\/s11831-020-09471-9","article-title":"Machine learning algorithms in civil structural health monitoring: A systematic review","volume":"28","author":"Flah","year":"2021","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2595","DOI":"10.1177\/1077546319861878","article-title":"Evaluation of progressive damage in structures using tensor decomposition-based wavelet analysis","volume":"25","author":"Sadhu","year":"2019","journal-title":"J. Vib. Control"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhang, D., and Zhang, D. (2019). Wavelet transform. Fundamentals of Image Data Mining: Analysis, Features, Classification and Retrieval, Springer.","DOI":"10.1007\/978-3-030-17989-2"},{"key":"ref_40","unstructured":"Jorgensen, P.E., and Song, M.S. (2007). Comparison of discrete and continuous wavelet transforms. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.ymssp.2013.03.011","article-title":"Wavelet-based frequency response function for time-variant systems\u2014An exploratory study","volume":"47","author":"Staszewski","year":"2014","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_42","unstructured":"Madankumar, P., and Prawin, J. (2020, January 10\u201312). Reference Free Damage Localization using Teager Energy Operator-Wavelet Transform Mode Shapes. Proceedings of the NDE 2020\u2014Virtual Conference & Exhibition, Online. NDT.net Issue: 2021-04."},{"key":"ref_43","first-page":"461","article-title":"Damage detection in structural health monitoring using hybrid convolution neural network and recurrent neural network","volume":"16","year":"2022","journal-title":"Frat. Integrit\u00e0 Strutt."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1007\/s00779-014-0800-5","article-title":"Structural health monitoring by using a sparse coding-based deep learning algorithm with wireless sensor networks","volume":"18","author":"Guo","year":"2014","journal-title":"Pers. Ubiquitous Comput."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"6658575","DOI":"10.1155\/2021\/6658575","article-title":"Unsupervised structural damage detection technique based on a deep convolutional autoencoder","volume":"2021","author":"Rastin","year":"2021","journal-title":"Shock Vib."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"04019041","DOI":"10.1061\/(ASCE)CP.1943-5487.0000855","article-title":"Toward compressed sensing of structural monitoring data using discrete cosine transform","volume":"34","author":"Almasri","year":"2020","journal-title":"J. Comput. Civ. Eng."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Jiang, C., Zhou, Q., Lei, J., and Wang, X. (2022). A Two-Stage Structural Damage Detection Method Based on 1D-CNN and SVM. Appl. Sci., 12.","DOI":"10.3390\/app122010394"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"04021035","DOI":"10.1061\/(ASCE)CP.1943-5487.0001003","article-title":"Multiclass damage identification in a full-scale bridge using optimally tuned one-dimensional convolutional neural network","volume":"36","author":"Sony","year":"2022","journal-title":"J. Comput. Civ. Eng."},{"key":"ref_49","first-page":"e2308","article-title":"Vibration-based structural condition assessment using convolution neural networks","volume":"26","author":"Khodabandehlou","year":"2019","journal-title":"Struct. Control Health Monit."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"04020012","DOI":"10.1061\/(ASCE)BE.1943-5592.0001531","article-title":"Detectability of bridge-structural damage based on fiber-optic sensing through deep-convolutional neural networks","volume":"25","author":"Li","year":"2020","journal-title":"J. Bridge Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"3916","DOI":"10.1038\/s41598-023-30683-z","article-title":"Anomaly detection in railway bridges using imaging techniques","volume":"13","author":"Russo","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"109175","DOI":"10.1016\/j.ymssp.2022.109175","article-title":"Vibration feature extraction using signal processing techniques for structural health monitoring: A review","volume":"177","author":"Zhang","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Oberlin, T., Meignen, S., and Perrier, V. (2014, January 4\u20139). The Fourier-based synchrosqueezing transform. Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy.","DOI":"10.1109\/ICASSP.2014.6853609"},{"key":"ref_54","first-page":"2196","article-title":"A class of multivariate denoising algorithms based on synchrosqueezing","volume":"63","author":"Ahrabian","year":"2015","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_55","first-page":"527","article-title":"Voice jitter estimation using high-order synchrosqueezing operators","volume":"29","author":"Miramont","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Manganelli Conforti, P., D\u2019Acunto, M., and Russo, P. (2022). Deep Learning for Chondrogenic Tumor Classification through Wavelet Transform of Raman Spectra. Sensors, 22.","DOI":"10.3390\/s22197492"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1175\/1520-0477(1998)079<0061:APGTWA>2.0.CO;2","article-title":"A practical guide to wavelet analysis","volume":"79","author":"Torrence","year":"1998","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/S0022-460X(02)01032-5","article-title":"Damping identification using a continuous wavelet transform: Application to real data","volume":"262","author":"Simonovski","year":"2003","journal-title":"J. Sound Vib."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neuroimage.2019.05.048","article-title":"A better way to define and describe Morlet wavelets for time-frequency analysis","volume":"199","author":"Cohen","year":"2019","journal-title":"NeuroImage"},{"key":"ref_60","unstructured":"Muradeli, J. (2023, January 30). Ssqueezepy. GitHub. Available online: https:\/\/github.com\/OverLordGoldDragon\/ssqueezepy."},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_63","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., and Sun, J. (2018). Detnet: A backbone network for object detection. arXiv.","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1007\/s10489-020-01867-1","article-title":"COVID-19 detection and disease progression visualization: Deep learning on chest X-rays for classification and coarse localization","volume":"51","author":"Zebin","year":"2021","journal-title":"Appl. Intell."},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.-F. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_67","first-page":"1023","article-title":"Z24 bridge damage detection tests","volume":"Volume 3727","year":"1999","journal-title":"Proceedings of the International Modal Analysis Conference (IMAC 17)"},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"103283","DOI":"10.1016\/j.autcon.2020.103283","article-title":"Concrete bridge damage detection using parallel simulation","volume":"119","author":"Lin","year":"2020","journal-title":"Autom. Constr."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"e2730","DOI":"10.1002\/env.2730","article-title":"Normalization methods for spatio-temporal analysis of environmental performance: Revisiting the Min\u2013Max method","volume":"33","author":"Mazziotta","year":"2022","journal-title":"Environmetrics"},{"key":"ref_70","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"Maas","year":"2013","journal-title":"Proc. ICML"},{"key":"ref_71","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.istruc.2021.10.088","article-title":"Vibration-based multiclass damage detection and localization using long short-term memory networks","volume":"35","author":"Sony","year":"2022","journal-title":"Structures"},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1007\/s13349-022-00591-3","article-title":"A transfer learning SHM strategy for bridges enriched by the use of speaker recognition x-vectors","volume":"12","author":"Tronci","year":"2022","journal-title":"J. Civ. Struct. Health Monit."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/13\/6152\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:06:13Z","timestamp":1760126773000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/13\/6152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,4]]},"references-count":73,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["s23136152"],"URL":"https:\/\/doi.org\/10.3390\/s23136152","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,4]]}}}