{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:07:46Z","timestamp":1788930466837,"version":"build-2803163510"},"reference-count":57,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Materials"],"abstract":"<jats:p>The fatigue degradation of polymer-matrix composite materials, especially in the case of thermomechanical fatigue, when the self-heating effect dominates the process of the cyclically bent structure in fully reversed mode, results in complex damage patterns with a heterogeneous nature. It is therefore essential to evaluate the structural condition of tested objects in a non-destructive way to predict their fatigue lifetime. One of the most accurate non-destructive testing techniques used for such examinations is X-ray computed tomography, which enables the evaluation of the resulting fatigue damage in a three-dimensional space. However, the main challenge in the evaluation of such results is the attribution of the observed damage to specific types, the assessment of its severity, and its quantitative analysis. In this study, we have proposed a novel framework based on intensity and morphological features for the classification of damage types and a 3D U-Net-based approach for segmentation. The acquired results demonstrated the high accuracy of the performance evaluation indices, which exceeded 99% for the proposed framework, allowing effective evaluation of the resulting damage and being potentially helpful in the assessment of structural performance and residual fatigue life. Such analysis contributes to the trends of NDE 4.0 and adaptive mechanics, where composite structures are tailored to specific operational conditions to reach the target lifecycle.<\/jats:p>","DOI":"10.3390\/ma19173752","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T16:21:21Z","timestamp":1788452481000},"page":"3752","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantitative Evaluation of Thermomechanical Fatigue Damage in Composite Materials Using X-Ray Computed Tomography and Machine Learning"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3412-4533","authenticated-orcid":false,"given":"Piotr","family":"Przysta\u0142ka","sequence":"first","affiliation":[{"name":"Department of Fundamentals of Machinery Design, Faculty of Mechanical Engineering, Silesian University of Technology, Konarskiego 18A, 44-100 Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8482-6170","authenticated-orcid":false,"given":"Pawe\u0142","family":"Chrzanowski","sequence":"additional","affiliation":[{"name":"Department of Fundamentals of Machinery Design, Faculty of Mechanical Engineering, Silesian University of Technology, Konarskiego 18A, 44-100 Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-5582","authenticated-orcid":false,"given":"Tomasz","family":"Rogala","sequence":"additional","affiliation":[{"name":"Department of Fundamentals of Machinery Design, Faculty of Mechanical Engineering, Silesian University of Technology, Konarskiego 18A, 44-100 Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9386-5104","authenticated-orcid":false,"given":"Andrzej","family":"Katunin","sequence":"additional","affiliation":[{"name":"Department of Fundamentals of Machinery Design, Faculty of Mechanical Engineering, Silesian University of Technology, Konarskiego 18A, 44-100 Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"ref_1","unstructured":"Sierakowski, R.L., and Newaz, G.M. (1995). Damage Tolerance in Advanced Composites, Technomic Publishing Company Inc."},{"key":"ref_2","first-page":"814","article-title":"The role of nondestructive testing in aircraft damage tolerance","volume":"61","author":"Ball","year":"2003","journal-title":"Mater. Eval."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1731","DOI":"10.1063\/1.2718173","article-title":"Aging aircraft NDE: Capabilities, challenges, opportunities","volume":"894","author":"Lindgren","year":"2007","journal-title":"AIP Conf. Proc."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Singh, S., Martinetti, A., Majumdar, A., and Dongen, L. (2019). Risk- and condition-based maintenance. Transportation Systems. Asset Analytics (Performance and Safety Management), Springer.","DOI":"10.1007\/978-981-32-9323-6"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"G\u00fcemes, A., Fernandez-Lopez, A., Pozo, A.R., and Sierra-P\u00e9rez, J. (2020). Structural health monitoring for advanced composite structures: A review. J. Compos. Sci., 4.","DOI":"10.3390\/jcs4010013"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"112951","DOI":"10.1016\/j.compstruct.2020.112951","article-title":"Advances, limitations and prospects of nondestructive testing and evaluation of thick composites and sandwich structures: A state-of-the-art review","volume":"256","author":"Nsengiyumva","year":"2021","journal-title":"Compos. Struct."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.compscitech.2012.12.006","article-title":"A comparison of multi-scale 3D X-ray tomographic inspection techniques for assessing carbon fibre composite impact damage","volume":"75","author":"Bull","year":"2013","journal-title":"Compos. Sci. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Katunin, A., Dragan, K., Nowak, T., and Chalimoniuk, M. (2021). Quality control approach for the detection of internal lower density areas in composite disks in industrial conditions based on a combination of NDT techniques. Sensors, 21.","DOI":"10.3390\/s21217174"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1177\/00219983211050705","article-title":"A review of applications of CT imaging on fiber reinforced composites","volume":"56","author":"Gao","year":"2022","journal-title":"J. Compos. Mater."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.compscitech.2017.10.023","article-title":"X-ray computed tomography of polymer composites","volume":"156","author":"Garcea","year":"2018","journal-title":"Compos. Sci. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/0261-3069(92)90187-M","article-title":"Computerized tomography for non-destructive testing of materials and its efficient use","volume":"13","author":"Carlsson","year":"1992","journal-title":"Mater. Des."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2016","DOI":"10.1016\/j.compscitech.2006.01.003","article-title":"Micro-computed tomography determination of glass fibre reinforced polymer meso-structure","volume":"66","author":"Schell","year":"2006","journal-title":"Compos. Sci. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.1016\/j.compscitech.2011.06.004","article-title":"In situ fibre fracture measurement in carbon-epoxy laminates using high resolution computed tomography","volume":"71","author":"Scott","year":"2011","journal-title":"Compos. Sci. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/j.compscitech.2011.11.025","article-title":"Determination of damage micromechanisms and fracture resistance of glass fiber\/epoxy cross-ply laminate by means of X-ray computed microtomography","volume":"72","author":"Sket","year":"2012","journal-title":"Compos. Sci. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.ndteint.2011.11.011","article-title":"Characterisation of voids in fibre reinforced composite materials","volume":"46","author":"Little","year":"2012","journal-title":"NDT&E Int."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.ndteint.2012.12.010","article-title":"Automatic extraction and visualization of spatial position data for bulk porosities in laser weldments with complex structures","volume":"54","author":"Shi","year":"2013","journal-title":"NDT&E Int."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.compstruct.2017.04.067","article-title":"Impact shear damage characterizations of 3D braided composite with X-ray micro-computed tomography and numerical methodologies","volume":"176","author":"Li","year":"2017","journal-title":"Compos. Struct."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105532","DOI":"10.1016\/j.compositesa.2019.105532","article-title":"Detailed characterization of voids in multidirectional carbon fiber\/epoxy composite laminates using X-ray micro-computed tomography","volume":"125","author":"Mehdikani","year":"2019","journal-title":"Compos. Part A"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Madra, A., Van-Pham, D.-T., Nguyen, M.-T., Nguyen, C.-N., Breitkopf, P., and Trochu, F. (2020). Automated identification of defect morphology and spatial distribution in woven composites. J. Compos. Sci., 4.","DOI":"10.3390\/jcs4040178"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.compositesa.2013.05.003","article-title":"Three-dimensional assessment of low velocity impact damage in particle toughened composite laminates using micro-focus X-ray computed tomography and synchrotron radiation laminography","volume":"52","author":"Bull","year":"2013","journal-title":"Compos. Part A"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.compositesa.2015.06.013","article-title":"2D and 3D imaging of fatigue failure mechanisms of 3D woven composites","volume":"77","author":"Yu","year":"2015","journal-title":"Compos. Part A"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.ultramic.2009.11.013","article-title":"A framework for automatic segmentation in three dimensions of microstructural tomography data","volume":"110","author":"Hansen","year":"2010","journal-title":"Ultramicroscopy"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.compscitech.2013.11.004","article-title":"Influence of voids on damage mechanisms in carbon\/epoxy composites determined via high resolution computed tomography","volume":"90","author":"Scott","year":"2014","journal-title":"Compos. Sci. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wronkowicz-Katunin, A., Katunin, A., Nagode, M., and Klemenc, J. (2021). Classification of cracks in composite structures subjected to low-velocity impact using distribution-based segmentation and wavelet analysis of X-ray tomograms. Sensors, 21.","DOI":"10.3390\/s21248342"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1109\/TVCG.2007.70598","article-title":"Surface extraction from multi-material components for metrology using dual energy CT","volume":"13","author":"Heinzl","year":"2007","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.acme.2014.08.002","article-title":"Automated identification and classification of internal defects in composite structures using computed tomography and 3D wavelet analysis","volume":"15","author":"Katunin","year":"2015","journal-title":"Arch. Civ. Mech. Eng."},{"key":"ref_27","first-page":"3","article-title":"Directionality detection of delaminations basing on analysis of CT slices using wavelet and Hough transforms-based algorithm","volume":"16","author":"Katunin","year":"2015","journal-title":"Diagnostyka"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.compstruct.2017.07.101","article-title":"Characterization of failure mechanisms of composite structures subjected to fatigue dominated with the self-heating effect","volume":"180","author":"Katunin","year":"2017","journal-title":"Compos. Struct."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.physa.2004.03.057","article-title":"Techniques for image enhancement and segmentation of tomographic images of porous materials","volume":"339","author":"Sheppard","year":"2004","journal-title":"Phys. A"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"20160037","DOI":"10.1098\/rsta.2016.0037","article-title":"A comparison of different approaches for imaging cracks in composites by X-ray microtomography","volume":"374","author":"Yu","year":"2016","journal-title":"Phil. Trans. R. Soc. A"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Heslehurst, R.B. (2014). Defects and Damage in Composite Materials and Structures, CRC Press.","DOI":"10.1201\/b16765"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.compositesb.2018.12.064","article-title":"Classification of damages in composite images using Zernike moments and support vector machines","volume":"168","author":"Abilash","year":"2019","journal-title":"Compos. Part B"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"110014","DOI":"10.1063\/1.4940585","article-title":"Segmenting delaminations in carbon fiber reinforced polymer composite CT using convolutional neural networks","volume":"1706","author":"Sammons","year":"2016","journal-title":"AIP Conf. Proc."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3194","DOI":"10.1002\/pc.25611","article-title":"Automated damage detection and characterization of polymer composite images using Tsallis-particle swarm optimization-based multilevel threshold and multifractals","volume":"41","author":"Abilash","year":"2020","journal-title":"Polym. Compos."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"114440","DOI":"10.1016\/j.compstruct.2021.114440","article-title":"Adopting traditional image algorithms and deep learning to build the finite model of a 2.5D composite based on X-Ray computed tomography","volume":"275","author":"Jia","year":"2021","journal-title":"Compos. Struct."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Sinchuk, Y., Kibleur, P., Aelterman, J., Boone, M.N., and Van Paepegem, W. (2020). Variational and deep learning segmentation of very-low-contrast X-ray computed tomography images of carbon\/epoxy woven composites. Materials, 13.","DOI":"10.3390\/ma13040936"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107823","DOI":"10.1016\/j.engfracmech.2021.107823","article-title":"Neural network segmentation methods for fatigue crack images obtained with X-ray tomography","volume":"252","author":"Xiao","year":"2021","journal-title":"Eng. Fract. Mech."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.compstruct.2018.02.096","article-title":"Quality assessment of porous CFRP specimens using X-ray Computed Tomography data and Artificial Neural Networks","volume":"192","author":"Stamopoulos","year":"2018","journal-title":"Compos. Struct."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"102549","DOI":"10.1016\/j.ndteint.2021.102549","article-title":"Automatic defect detection from X-ray scans for Aluminum Conductor Composite Core Wire based on Classification Neutral Network","volume":"124","author":"Hu","year":"2021","journal-title":"NDT&E Int."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"115136","DOI":"10.1016\/j.compstruct.2021.115136","article-title":"A transfer learning object detection model for defects detection in X-ray images of spacecraft composite structures","volume":"284","author":"Gong","year":"2022","journal-title":"Compos. Struct."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Bertoldo, J.P.C., Decenci\u00e8re, E., Ryckelynck, D., and Proudhon, H. (2021). A modular U-Net for automated segmentation of X-ray tomography images in composite materials. Front. Mater., 8.","DOI":"10.3389\/fmats.2021.761229"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Badran, A., Parkinson, D., Ushizima, D., Marshall, D., and Maillet, E. (2022). Validation of deep learning segmentation of CT images of fiber-reinforced composites. J. Compos. Sci., 6.","DOI":"10.3390\/jcs6020060"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"109781","DOI":"10.1016\/j.compscitech.2022.109781","article-title":"Deep learning method for analysis and segmentation of fatigue damage in X-ray computed tomography data for fiber-reinforced polymers","volume":"230","author":"Helwing","year":"2022","journal-title":"Compos. Sci. Technol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"110278","DOI":"10.1016\/j.compscitech.2023.110278","article-title":"Deep-learning image enhancement and fibre segmentation from time-resolved computed tomography of fibre-reinforced composites","volume":"244","author":"Guo","year":"2023","journal-title":"Compos. Sci. Technol."},{"key":"ref_45","first-page":"100028","article-title":"Semantic segmentation of progressive micro-cracking in polymer composites using Attention U-Net architecture","volume":"5","author":"Petkov","year":"2024","journal-title":"Tomogr. Mater. Struct."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"110650","DOI":"10.1016\/j.compscitech.2024.110650","article-title":"Characterizing damage evolution in fiber reinforced composites using in-situ X-ray computed tomography, deep machine learning and digital volume correlation (DVC)","volume":"254","author":"Wang","year":"2024","journal-title":"Compos. Sci. Technol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.prostr.2022.01.076","article-title":"Damage classification in composite structures based on X-ray computed tomography scans using features evaluation and deep neural networks","volume":"37","author":"Rogala","year":"2022","journal-title":"Procedia Struct. Integr."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"083001","DOI":"10.1088\/1361-665X\/ac099f","article-title":"Artificial intelligence in real-time diagnostics and prognostics of composite materials and its uncertainties\u2014A review","volume":"30","author":"Elenchezhian","year":"2021","journal-title":"Smart Mater. Struct."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1016\/j.comcom.2019.12.032","article-title":"New insights on ground control in intelligent mining with Internet of Things","volume":"150","author":"Hao","year":"2020","journal-title":"Comput. Commun."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_51","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"Volume 9351","author":"Ronneberger","year":"2015","journal-title":"Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Munich, Germany, 5\u20139 October 2015"},{"key":"ref_52","first-page":"424","article-title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","volume":"Volume 9901","author":"Abdulkadir","year":"2016","journal-title":"Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016, Athens, Greece, 17\u201321 October 2016"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1037\/0033-295X.84.4.327","article-title":"Features of similarity","volume":"84","author":"Tversky","year":"1977","journal-title":"Psychol. Rev."},{"key":"ref_54","first-page":"379","article-title":"Tversky loss function for image segmentation using 3D fully convolutional deep networks","volume":"Volume 10541","author":"Salehi","year":"2017","journal-title":"Proceedings of the Machine Learning in Medical Imaging\u2014MLMI 2017, Quebec City, QC, Canada, 10 September 2017"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1179\/1743289811Y.0000000037","article-title":"Influence of heating rate on evolution of dynamic properties of polymeric laminates","volume":"41","author":"Katunin","year":"2012","journal-title":"Plast. Rubber Compos."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"112353","DOI":"10.1016\/j.compositesb.2025.112353","article-title":"Thermomechanical fatigue life assessment of polymer-matrix composites via entropy-based damage evolution and stiffness degradation under different frequencies","volume":"298","author":"Amraei","year":"2025","journal-title":"Compos. Part B"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1038\/nmeth.2019","article-title":"Fiji: An open-source platform for biological-image analysis","volume":"9","author":"Schindelin","year":"2012","journal-title":"Nat. Meth."}],"container-title":["Materials"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1996-1944\/19\/17\/3752\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T04:23:37Z","timestamp":1788927817000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1996-1944\/19\/17\/3752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":57,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["ma19173752"],"URL":"https:\/\/doi.org\/10.3390\/ma19173752","relation":{},"ISSN":["1996-1944"],"issn-type":[{"value":"1996-1944","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]}}}