{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T15:02:03Z","timestamp":1780066923528,"version":"3.54.0"},"reference-count":63,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T00:00:00Z","timestamp":1573516800000},"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>This paper reports on a novel metamodel for impact detection, localization and characterization of complex composite structures based on Convolutional Neural Networks (CNN) and passive sensing. Methods to generate appropriate input datasets and network architectures for impact localization and characterization were proposed, investigated and optimized. The ultrasonic waves generated by external impact events and recorded by piezoelectric sensors are transferred to 2D images which are used for impact detection and characterization. The accuracy of the detection was tested on a composite fuselage panel which was shown to be over 94%. In addition, the scalability of this metamodelling technique has been investigated by training the CNN metamodels with the data from part of the stiffened panel and testing the performance on other sections with similar geometry. Impacts were detected with an accuracy of over 95%. Impact energy levels were also successfully categorized while trained at coupon level and applied to sub-components with greater complexity. These results validated the applicability of the proposed CNN-based metamodel to real-life application such as composite aircraft parts.<\/jats:p>","DOI":"10.3390\/s19224933","type":"journal-article","created":{"date-parts":[[2019,11,13]],"date-time":"2019-11-13T09:11:27Z","timestamp":1573636287000},"page":"4933","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":163,"title":["A Convolutional Neural Network for Impact Detection and Characterization of Complex Composite Structures"],"prefix":"10.3390","volume":"19","author":[{"given":"Iuliana","family":"Tabian","sequence":"first","affiliation":[{"name":"Department of Aeronautics, Imperial College London, London SW7 2AZ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7557-3853","authenticated-orcid":false,"given":"Hailing","family":"Fu","sequence":"additional","affiliation":[{"name":"Wolfson School of Mechanical, Electrical and Manufacturing Engineering, Loughborough University, Loughborough LE11 3TU, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5106-2197","authenticated-orcid":false,"given":"Zahra","family":"Sharif Khodaei","sequence":"additional","affiliation":[{"name":"Department of Aeronautics, Imperial College London, London SW7 2AZ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,11,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Maizuar, M., Zhang, L., Miramini, S., Mendis, P., and Thompson, R.G. (2017). Detecting structural damage to bridge girders using radar interferometry and computational modelling. Struct. Control Health Monit., 24.","DOI":"10.1002\/stc.1985"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.compstruct.2015.02.080","article-title":"Damage identification in aircraft composite structures: A case study using various non-destructive testing techniques","volume":"127","author":"Katunin","year":"2015","journal-title":"Compos. Struct."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1080\/10589759.2018.1525378","article-title":"Characterising fundamental properties of foam concrete with a non-destructive technique","volume":"34","author":"Liu","year":"2019","journal-title":"Nondestr. Test. Eval."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Aliabadi, M.F., and Sharif-Khodaei, Z. (2017). Structural Health Monitoring for Advanced Composite Structures, World Scientific Publishing Company.","DOI":"10.1142\/q0114"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.compstruct.2015.02.046","article-title":"Damage localization in composite lattice truss core sandwich structures based on vibration characteristics","volume":"126","author":"Li","year":"2015","journal-title":"Compos. Struct."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.ymssp.2016.01.023","article-title":"Evaluation of barely visible indentation damage (BVID) in CF\/EP sandwich composites using guided wave signals","volume":"76","author":"Mustapha","year":"2016","journal-title":"Mech. Syst. Sig. Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"105026","DOI":"10.1088\/0964-1726\/21\/10\/105026","article-title":"Determination of impact location on composite stiffened panels","volume":"21","author":"Ghajari","year":"2012","journal-title":"Smart Mater. Struct."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"085014","DOI":"10.1088\/0964-1726\/22\/8\/085014","article-title":"Identification of impact force for smart composite stiffened panels","volume":"22","author":"Ghajari","year":"2013","journal-title":"Smart Mater. Struct."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"075007","DOI":"10.1088\/0964-1726\/23\/7\/075007","article-title":"Assessment of delay-and-sum algorithms for damage detection in aluminium and composite plates","volume":"23","author":"Aliabadi","year":"2014","journal-title":"Smart Mater. Struct."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sharif Khodaei, Z., and Aliabadi, M. (2016). A multi-level decision fusion strategy for condition based maintenance of composite structures. Materials, 9.","DOI":"10.3390\/ma9090790"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/j.yofte.2017.12.001","article-title":"Impact localization on composite laminates using fiber Bragg grating sensors and a novel technique based on strain amplitude","volume":"40","author":"Zhao","year":"2018","journal-title":"Opt. Fiber Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.ymssp.2017.05.047","article-title":"Reliability based impact localization in composite panels using Bayesian updating and the Kalman filter","volume":"99","author":"Morse","year":"2018","journal-title":"Mech. Syst. Sig. Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s00521-014-1568-2","article-title":"Fast detection of impact location using kernel extreme learning machine","volume":"27","author":"Fu","year":"2016","journal-title":"Neural Comput. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1106\/H0EV-7PWM-QYHW-E7VF","article-title":"Impedance-based structural health monitoring with artificial neural networks","volume":"11","author":"Lopes","year":"2000","journal-title":"J. Intell. Mater. Syst. Struct."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"895","DOI":"10.4028\/www.scientific.net\/AMR.123-125.895","article-title":"Detection of Impact Location for Composite Stiffened Panel Using FBG Sensors","volume":"123","author":"Park","year":"2010","journal-title":"Adv. Mater. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1640005","DOI":"10.1142\/S1756973716400059","article-title":"Assessment of impact detection techniques for aeronautical application: ANN vs. LSSVM","volume":"7","author":"Yue","year":"2016","journal-title":"J. Multiscale Modell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Seno, A.H., and Aliabadi, M. (2019). Impact localisation in composite plates of different stiffness impactors under simulated environmental and operational conditions. Sensors, 19.","DOI":"10.3390\/s19173659"},{"key":"ref_18","first-page":"1","article-title":"A comparison study of extreme learning machine and least squares support vector machine for structural impact localization","volume":"2014","author":"Xu","year":"2014","journal-title":"Math. Prob. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kang, F., Liu, J., Li, J., and Li, S. (2017). Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Struct. Control Health Monit., 24.","DOI":"10.1002\/stc.1997"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.compscitech.2013.08.019","article-title":"Neural network approach for damaged area location prediction of a composite plate using electromechanical impedance technique","volume":"88","author":"Na","year":"2013","journal-title":"Compos. Sci. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"De Oliveira, M., Araujo, N., da Silva, R., da Silva, T., and Epaarachchi, J. (2018). Use of savitzky\u2013golay filter for performances improvement of SHM systems based on neural networks and distributed PZT sensors. Sensors, 18.","DOI":"10.3390\/s18010152"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2014\/401942","article-title":"Probabilistic neural network and fuzzy cluster analysis methods applied to impedance-based SHM for damage classification","volume":"2014","author":"Palomino","year":"2014","journal-title":"Shock Vibr."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5372","DOI":"10.1016\/j.eswa.2013.03.040","article-title":"An application to transient current signal based induction motor fault diagnosis of Fourier\u2013Bessel expansion and simplified fuzzy ARTMAP","volume":"40","author":"AlThobiani","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.asoc.2016.12.020","article-title":"Performance analysis of simplified Fuzzy ARTMAP and Probabilistic Neural Networks for identifying structural damage growth","volume":"52","author":"Inman","year":"2017","journal-title":"Appl. Soft Comput."},{"key":"ref_25","unstructured":"Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M.S., Van Esesn, B.C., Awwal, A.A.S., and Asari, V.K. (2018). The history began from AlexNet: A comprehensive survey on deep learning approaches. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep convolutional neural networks for image classification: A comprehensive review","volume":"29","author":"Rawat","year":"2017","journal-title":"Neural Computation"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Alom, M.Z., Alam, M., Taha, T.M., and Iftekharuddin, K.M. (2017, January 14\u201319). Object recognition using cellular simultaneous recurrent networks and convolutional neural network. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966211"},{"key":"ref_28","unstructured":"Lakhani, V.A., and Mahadev, R. (2016). Multi-Language Identification Using Convolutional Recurrent Neural Network. arXiv."},{"key":"ref_29","unstructured":"Hannun, A., Case, C., Casper, J., Catanzaro, B., Diamos, G., Elsen, E., Prenger, R., Satheesh, S., Sengupta, S., and Coates, A. (2014). Deep speech: Scaling up end-to-end speech recognition. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition CVPR, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1109\/TMI.2016.2548501","article-title":"Automatic segmentation of MR brain images with a convolutional neural network","volume":"35","author":"Moeskops","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.eswa.2016.04.032","article-title":"Human activity recognition with smartphone sensors using deep learning neural networks","volume":"59","author":"Ronao","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.ymssp.2017.11.024","article-title":"A review on the application of deep learning in system health management","volume":"107","author":"Khan","year":"2018","journal-title":"Mech. Syst. Sig. Process."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.ymssp.2018.05.050","article-title":"Deep learning and its applications to machine health monitoring","volume":"115","author":"Zhao","year":"2019","journal-title":"Mech. Syst. Sig. Process."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Abdeljaber, O. (2017). Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J. Sound Vib., 388.","DOI":"10.1016\/j.jsv.2016.10.043"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1016\/j.neucom.2017.09.069","article-title":"1-D CNNs for structural damage detection: verification on a structural health monitoring benchmark data","volume":"275","author":"Abdeljaber","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"De Oliveira, M., Monteiro, A., and Vieira Filho, J. (2018). A New Structural Health Monitoring Strategy Based on PZT Sensors and Convolutional Neural Network. Sensors, 18.","DOI":"10.20944\/preprints201808.0130.v1"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"4392","DOI":"10.1109\/TIE.2017.2764844","article-title":"NB-CNN: Deep learning-based crack detection using convolutional neural network and Na\u00efve Bayes data fusion","volume":"65","author":"Chen","year":"2018","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/TMECH.2017.2728371","article-title":"Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks","volume":"23","author":"Xia","year":"2018","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.jsv.2016.05.027","article-title":"Convolutional neural network based fault detection for rotating machinery","volume":"377","author":"Janssens","year":"2016","journal-title":"J. Sound Vib."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1016\/j.promfg.2016.08.083","article-title":"Rotating machinery diagnostics using deep learning on orbit plot images","volume":"5","author":"Jeong","year":"2016","journal-title":"Procedia Manuf."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Guo, S., Yang, T., Gao, W., and Zhang, C. (2018). A Novel Fault Diagnosis Method for Rotating Machinery Based on a Convolutional Neural Network. Sensors, 18.","DOI":"10.3390\/s18051429"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"15066","DOI":"10.1109\/ACCESS.2017.2728010","article-title":"Stacked Sparse Autoencoder-Based Deep Network for Fault Diagnosis of Rotating Machinery","volume":"5","author":"Qi","year":"2017","journal-title":"IEEE Access"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1109\/JIOT.2018.2867722","article-title":"An event-triggered energy-efficient wireless structural health monitoring system for impact detection in composite airframes","volume":"6","author":"Fu","year":"2018","journal-title":"IEEE Internet Things J."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/j.ymssp.2019.03.050","article-title":"An energy-efficient cyber\u2013physical system for wireless on-board aircraft structural health monitoring","volume":"128","author":"Fu","year":"2019","journal-title":"Mech. Syst. Sig. Process."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","article-title":"Recent advances in convolutional neural networks","volume":"77","author":"Gu","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_48","unstructured":"LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., and Jackel, L.D. (1990). Handwritten digit recognition with a back-propagation network. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1113\/jphysiol.1968.sp008455","article-title":"Receptive fields and functional architecture of monkey striate cortex","volume":"195","author":"Hubel","year":"1968","journal-title":"J. Physiol."},{"key":"ref_50","unstructured":"Brownlee, J. (2019). Deep Learning for Computer Vision - Image Classification, Object Detection and Face Recognition in Python, Machine Learning Mastery."},{"key":"ref_51","unstructured":"(2019, November 11). CS231n: Convolutional Neural Networks for Visual Recognition, Stanford University. Available online: http:\/\/cs231n.github.io\/convolutional-networks\/."},{"key":"ref_52","unstructured":"(2019, November 11). Convolution Neural Networks vs Fully Connected Neural Networks. Available online: https:\/\/medium.com\/datadriveninvestor\/convolution-neural-networks-vs-fully-connected-neural-networks-8171a6e86f15."},{"key":"ref_53","unstructured":"Zadeh, R.B., and Ramsundar, B. (2018). Fully Connected Deep Networks. TensorFlow for Deep Learning, O\u2019Reilly Media."},{"key":"ref_54","unstructured":"Walia Singh, A. (2019, November 11). Activation Functions and It\u2019S Types-Which Is Better?. Available online: https:\/\/towardsdatascience.com\/activation-functions-and-its-types-which-is-better-a9a5310cc8f."},{"key":"ref_55","unstructured":"Wang, C.F. (2019, November 11). The Vanishing Gradient Problem. Available online: https:\/\/towardsdatascience.com\/the-vanishing-gradient-problem-69bf08b15484."},{"key":"ref_56","unstructured":"Sharma V, A. (2019, November 11). Understanding Activation Functions in Neural Networks. Available online: https:\/\/medium.com\/the-theory-of-everything\/understanding-activation-functions-in-neural-networks-9491262884e0."},{"key":"ref_57","unstructured":"Lan, H. (2019, November 11). The Softmax Function, Neural Net Outputs as Probabilities, and Ensemble Classifiers. Available online: https:\/\/towardsdatascience.com\/the-softmax-function-neural-net-outputs-as-probabilities-and-ensemble-classifiers-9bd94d75932."},{"key":"ref_58","unstructured":"Mishra, A. (2019, November 11). Metrics to Evaluate your Machine Learning Algorithm. Available online: https:\/\/towardsdatascience.com\/metrics-to-evaluate-your-machine-learning-algorithm-f10ba6e38234."},{"key":"ref_59","unstructured":"Parmar, R. (2019, November 11). Common Loss functions in machine learning. Available online: https:\/\/towardsdatascience.com\/common-loss-functions-in-machine-learning-46af0ffc4d23."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"095037","DOI":"10.1088\/0964-1726\/25\/9\/095037","article-title":"Optimal sensor placement for maximum area coverage (MAC) for damage localization in composite structures","volume":"25","author":"Thiene","year":"2016","journal-title":"Smart Mater. Struct."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1177\/1045389X12464280","article-title":"Optimal sensor positioning for impact localization in smart composite panels","volume":"24","author":"Mallardo","year":"2013","journal-title":"J. Intell. Mater. Syst. Struct."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Fu, H., Sharif-Khodaei, Z., and Aliabadi, M.H.F. (2019, January 1). An energy efficient wireless module for on-board aircraft impact detection. Proceedings of the Nondestructive Characterization and Monitoring of Advanced Materials Aerospace, Civil Infrastructure, and Transportation XIII, Denver, CO, USA.","DOI":"10.1117\/12.2513534"},{"key":"ref_63","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/22\/4933\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:33:53Z","timestamp":1760189633000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/22\/4933"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,12]]},"references-count":63,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2019,11]]}},"alternative-id":["s19224933"],"URL":"https:\/\/doi.org\/10.3390\/s19224933","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,12]]}}}