Determining the Defect Sizes of CFRP Laminates by Employing Step-Heating Thermography and an Artificial Neural Network Approach

first_page Download PDF settings Order Article Reprints Font Type: Arial Georgia Verdana Font Size: Aa Aa Aa Line Spacing:    Column Width:    Background: Open AccessAbstract Determining the Defect Sizes of CFRP Laminates by Employing Step-Heating Thermography and an Artificial Neural Network Approach † by Muhamad HidayatMuhamad Hidayat SciProfiles Scilit Preprints.org Google Scholar 1, Yishuo HuangYishuo Huang SciProfiles Scilit Preprints.org Google Scholar 2 and Chih-Hung ChiangChih-Hung Chiang SciProfiles Scilit Preprints.org Google Scholar 3,* 1 Department of Mechanical Engineering, Sumbawa University of Technology, Sumbawa 84371, West Nusa Tenggara, Indonesia 2 Department of Civil and Construction Engineering, Chaoyang University of Technology, Taichung City 413310, Taiwan 3 Center for NDT and Graduate Institute of Aeronautics, Chaoyang University of Technology, Taichung City 413310, Taiwan * Author to whom correspondence should be addressed. † Presented at the 18th International Workshop on Advanced Infrared Technology and Applications (AITA 2025), Kobe, Japan, 15–19 September 2025. Proceedings 2025, 129(1), 11; https://doi.org/10.3390/proceedings2025129011 Published: 12 September 2025 Download keyboard_arrow_down Download PDF Download PDF with Cover Download XML Download Epub Browse Figures Versions Notes Keywords: step-heating thermography; image segmentation; artificial neural net 1. IntroductionComponents and structures made from composite materials can develop defects at various stages, including during manufacturing [1] and as a result of in-service use [2]. These issues can manifest as impact damage, internal flaws like resin or transverse ply cracks, voids, porosity, and poorly bonded interlaminar regions [3], often stemming from production errors. Such defects compromise the structural integrity and reduce the strength of the component.While surface defects are readily observable, internal defects pose a greater challenge for detection. Traditional inspection methods often lack the effectiveness to identify these subsurface flaws, highlighting the need for more sophisticated non-destructive testing (NDT) techniques. Thermography testing (TNDT) has emerged as one of the promising NDT methods for detecting defects within Carbon Fiber Reinforced Polymer (CFRP) structures.Experimental methods for defect detection often require substantial time and financial resources. To address these limitations, simulation-based approaches have been increasingly adopted. In particular, simulation-based TNDT has proven effective for identifying internal defects in CFRP composites [4].Defect size in materials can be measured using methods like Full-Width Half Maximum (FWHM) [5], temperature profile derivatives [6], and machine learning [7]. This study explores this problem using a combined methodology.Deep learning is widely used in defect detection. This study leverages deep learning to explore the relationship between thermal images—capturing surface temperatures of CFRP samples—and FEA-simulated images. A Generative Adversarial Network (GAN) was developed to train the data and generate simulations closely matching the originals. 2. Model and SpecimenThe simulation model and experimental specimen were both constructed from woven rectangular CFRP prepreg, comprising seven layers with a stacking sequence of [+45/0/−45/0/−45/0/+45]. Each layer had a nominal thickness of 0.28 mm. However, the overall thicknesses differed: the model had a thickness of 1.96 mm, while the manufactured specimen measured 1.89 mm, likely due to thickness shrinkage during the fabrication process. The dimensions and defect layout are detailed in Figure 1. Two types of defects have been analyzed: void defects (1A, 1B, 1C) and polyethylene defects (2A, 2B, 2C).Specimen material thermal conductivity values were based on Joven's research [8] for Cytec T300 3k/977-2 plain weave, with additional data for Cytec T300 sourced from Toray [9]. Material properties are listed in Table 1. 2.1. Finite Element AnalysisThe mesh model, constructed with Ansys® SOLID278 and SURF152 elements, used a 0.25 mm mesh size, chosen to approximate the 0.36 mm pixel size of the experiment. Natural cooling of the model was simulated with convective heat transfer (h = 5 W/(m2.K)) occurring at all surfaces. The ambient temperature was 26.5 °C, and the data acquisition rate was 3 Hz. Two analyses were carried out. The first applied a uniform heat flux of 650 W/m2 to the front surface for 21 s. The second analysis applied a uniform heat flux of 925 W/m2 to the back surface for 30 s. 2.2. Experimental DesignTwo identical Projecteur halogen 500W lamps, by SMJ Electrical & Hardware, Selangor, Malaysia, provided the heat source. The lamps heat the specimen surface for about 34 s for the front heating and 37 s for the back heating. An infrared camera, Avio InfRec R500EX, by Nippon Avionics Co., Ltd., Yokohama, Japan, captured the thermal images and provided the thermal data. The camera acquisition rate was set at 3 Hz for 120 s. The room temperature was 25 °C. 3. Defect Size DeterminationThe defect size measured along the y-axis at position x = 20, 30, 40, and 50 mm for polyethylene defects, and x = 140, 130, 120, and 110 mm for void defects, correspond to defect widths (Δy) of 8, 6, 4, and 2 mm, respectively, as shown in Figure 1a.Defect size was quantified using two methods: Full-Width Half Maximum (FWHM) and the derivative of the temperature profile. FWHM measures the width at half the maximum temperature contrast. The derivative method measures the distance between the peaks of the temperature profile's first derivative around the defect, a technique linked to maximum lateral heat fluxes at defect border projections [6]. 4. ResultMeasurement error comparisons of the front and back heating simulation and experiments are tabulated in Table 2 and Table 3. In evaluating defect detectability using front heating:The simulation identified minimum detectable defect sizes of 6 mm (derivative) for polyethylene and 4 mm (FWHM and derivative) for void defects.Conversely, the experiment did not detect polyethylene defects, while it detected void defects with a minimum size of 6 mm (derivative).For back heating:3.The simulation achieved a minimum detectable defect size of 4 mm (derivative) for both polyethylene and void defects (FWHM and derivative).4.The experiment detected polyethylene defects at a minimum size of 8 mm (FWHM) and void defects at 4 mm (derivative). 5. DiscussionPerfect alignment between infrared thermal and FEA-simulated images is difficult to obtain. However, the simulated results are difficult to distinguish from the discriminators those provided by GAN. CycleGAN addresses this by learning to translate between the two image domains without requiring paired data [10].In this study, we leverage the CycleGAN model to learn the translation between collected infrared thermal images and FEA simulated images. The 2000 iterations can reach the convergence. The differences between Generator G and F are decreasing as the iterations increase. Furthermore, the differences between the discriminators X and Y can decrease after 2000 iterations, as shown in Figure 2. 6. ConclusionsTwo main conclusions can be drawn based on the results of the current study:For estimating defect size, the derivative method demonstrated good performance in the simulation, whereas the FWHM method yielded better results in the experiment.Further refinement of the CycleGAN model is necessary before it can be reliably used for defect predictions. Author ContributionsConceptualization and methodology, M.H. and C.-H.C.; software, validation, formal analysis, data curation, visualization and investigation: M.H. and Y.H.; Writing—original draft preparation, M.H.; writing—review and editing: M.H., Y.H. and C.-H.C.; project administration, and funding acquisition, C.-H.C. All authors have read and agreed to the published version of the manuscript.FundingThis work was supported by NSTC, Taiwan. Project number NSTC 113-2221-E-324-005.Institutional Review Board StatementNot applicable.Informed Consent StatementNot applicable.Data Availability StatementThe data presented in this study are available upon reasonable request from the corresponding author due to confidentiality agreement.Conflicts of InterestThe authors declare there are no conflicts of interest.ReferencesAlmeida, J.H.S.; Angrizani, C.C.; Botelho, E.C.; Amico, S.C. Effect of Fiber Orientation on the Shear Behavior of Glass Fiber/Epoxy Composites. Mater. Des. 1980–2015 2015, 65, 789–795. [Google Scholar] [CrossRef]Rao, K.S.; Varadarajan, Y.S.; Rajendra, N. Erosive Wear Behaviour of Carbon Fiber-Reinforced Epoxy Composite. Mater. Today Proc. 2015, 2, 2975–2983. [Google Scholar] [CrossRef]Nsengiyumva, W.; Zhong, S.; Lin, J.; Zhang, Q.; Zhong, J.; Huang, Y. Advances, Limitations and Prospects of Nondestructive Testing and Evaluation of Thick Composites and Sandwich Structures: A State-of-the-Art Review. Compos. Struct. 2021, 256, 112951. [Google Scholar] [CrossRef]Hidayat, M.; Chiang, C.-H.; Yen, M. Determination of the Defect's Size of Multi-Layer Woven CFRP Based on Its Temperature Profile. Int. J. Appl. Sci. Eng. 2023, 20, 1–9. [Google Scholar] [CrossRef]Guo, W.; Dong, L.; Wang, H.; Feng, F.; Xing, Z.; Ma, R.; Shao, H.; Gao, Z.; Wang, B.; Yang, J. Size Estimation of Coating Disbonds Using the First Derivative Images in Pulsed Thermography. Infrared Phys. Technol. 2020, 104, 103106. [Google Scholar] [CrossRef]Vavilov, V.P. 3D Modeling of Pulsed Thermal NDT: Back to Basic Features and Subtle Phenomena. NDT E Int. 2022, 130, 102659. [Google Scholar] [CrossRef]Daghigh, V.; Ramezani, S.B.; Daghigh, H.; Lacy, T. Explainable artificial intelligence prediction of defect characterization in composite materials. Compos. Sci. Technol. 2024, 256, 110759. [Google Scholar] [CrossRef]Joven, R.; Das, R.; Ahmed, A.; Roozbehjavan, P.; Minaie, B. Thermal Properties Of Carbon Fiber-Epoxy Composites with Different Fabric Weaves. In Proceedings of the SAMPE International Symposium Proceedings, Munich, Germany, 24–25 May 2012. [Google Scholar]Carbon Fiber and Prepreg Data Sheets. Toray Composite Materials America. Available online: https://www.toraycma.com/resources/data-sheets/ (accessed on 20 May 2025).Zhu, Y.-H.; Park, T.; Isola, P.; Efros, A.A. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017; pp. 2242–2251. [Google Scholar] [CrossRef] Figure 1. Dimension and defect layout: (a) model and (b) experiment. Figure 1. Dimension and defect layout: (a) model and (b) experiment. Figure 2. The relations of the loss functions and generators G and F and the discriminators X and Y. Figure 2. The relations of the loss functions and generators G and F and the discriminators X and Y. Table 1. Material's properties. Table 1. Material's properties. MaterialThermal Conductivity 1Specific Heat 2Density 3xyzWoven CFRP Prepeg3.13.10.610001420Polyethylene-0.28-2300950Void (air)-0.026-10211.13 1 Thermal Conductivity in W/(m.K); 2 Specific Heat in J/(kg.K); 3 Density in kg/m3. Table 2. Measurement error for the front heating. Table 2. Measurement error for the front heating. DefectSizeSimulationExperimentFWHMDerivativeFWHMDerivativePolyethylene8 mm27%12%24%33%6 mm43%13%65%72%4 mm76%22%113%-Void8 mm14%11%7%9%6 mm27%10%15%8%4 mm60%16%35%67% Table 3. Measurement error for the back heating. Table 3. Measurement error for the back heating. DefectSizeSimulationExperimentFWHMDerivativeFWHMDerivativePolyethylene8 mm26%7%19%29%6 mm55%8%36%64%4 mm95%16%--Void8 mm16%17%27%20%6 mm11%11%18%11%4 mm13%15%43%7% Disclaimer/Publisher's Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Share and Cite MDPI and ACS Style Hidayat, M.; Huang, Y.; Chiang, C.-H. Determining the Defect Sizes of CFRP Laminates by Employing Step-Heating Thermography and an Artificial Neural Network Approach. Proceedings 2025, 129, 11. https://doi.org/10.3390/proceedings2025129011 AMA Style Hidayat M, Huang Y, Chiang C-H. Determining the Defect Sizes of CFRP Laminates by Employing Step-Heating Thermography and an Artificial Neural Network Approach. Proceedings. 2025; 129(1):11. https://doi.org/10.3390/proceedings2025129011 Chicago/Turabian Style Hidayat, Muhamad, Yishuo Huang, and Chih-Hung Chiang. 2025. "Determining the Defect Sizes of CFRP Laminates by Employing Step-Heating Thermography and an Artificial Neural Network Approach" Proceedings 129, no. 1: 11. https://doi.org/10.3390/proceedings2025129011 APA Style Hidayat, M., Huang, Y., & Chiang, C.-H. (2025). Determining the Defect Sizes of CFRP Laminates by Employing Step-Heating Thermography and an Artificial Neural Network Approach. Proceedings, 129(1), 11. https://doi.org/10.3390/proceedings2025129011 Article Metrics No No Article Access Statistics Multiple requests from the same IP address are counted as one view.