Next Article in Journal
High Resolution, High Contrast Beamformer Using Minimum Variance and Plane Wave Nonlinear Compounding with Low Complexity
Next Article in Special Issue
Evaluation of Hygrothermal Behaviour in Heritage Buildings through Sensors, CFD Modelling and IRT
Previous Article in Journal
Rapid and Sensitive Quantification of the Pesticide Lindane by Polymer Modified Electrochemical Sensor
Previous Article in Special Issue
Enhanced Infrared Sparse Pattern Extraction and Usage for Impact Evaluation of Basalt-Carbon Hybrid Composites by Pulsed Thermography
Article

A Deep Learning Method for the Impact Damage Segmentation of Curve-Shaped CFRP Specimens Inspected by Infrared Thermography

1
Fraunhofer IZFP Institute for Nondestructive Testing, 66123 Saarbrucken, Germany
2
School of Engineering, University of Applied Sciences, 66117 Saarbrucken, Germany
3
Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil
4
Chair of Lightweight Systems, Saarland University, 66123 Saarbrucken, Germany
5
Sao Carlos School of Engineering (EESC-USP), Sao Carlos 13566-590, Brazil
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Sensors 2021, 21(2), 395; https://doi.org/10.3390/s21020395
Received: 30 November 2020 / Revised: 30 December 2020 / Accepted: 5 January 2021 / Published: 8 January 2021
Advanced materials such as continuous carbon fiber-reinforced thermoplastic (CFRP) laminates are commonly used in many industries, mainly because of their strength, stiffness to weight ratio, toughness, weldability, and repairability. Structural components working in harsh environments such as satellites are permanently exposed to some sort of damage during their lifetimes. To detect and characterize these damages, non-destructive testing and evaluation techniques are essential tools, especially for composite materials. In this study, artificial intelligence was applied in combination with infrared thermography to detected and segment impact damage on curved laminates that were previously submitted to a severe thermal stress cycles and subsequent ballistic impacts. Segmentation was performed on both mid-wave and long-wave infrared sequences obtained simultaneously during pulsed thermography experiments by means of a deep neural network. A deep neural network was trained for each wavelength. Both networks generated satisfactory results. The model trained with mid-wave images achieved an F1-score of 92.74% and the model trained with long-wave images achieved an F1-score of 87.39%. View Full-Text
Keywords: composite materials; infrared thermography; deep learning; damage segmentation; curve shaped laminates composite materials; infrared thermography; deep learning; damage segmentation; curve shaped laminates
Show Figures

Figure 1

MDPI and ACS Style

Wei, Z.; Fernandes, H.; Herrmann, H.-G.; Tarpani, J.R.; Osman, A. A Deep Learning Method for the Impact Damage Segmentation of Curve-Shaped CFRP Specimens Inspected by Infrared Thermography. Sensors 2021, 21, 395. https://doi.org/10.3390/s21020395

AMA Style

Wei Z, Fernandes H, Herrmann H-G, Tarpani JR, Osman A. A Deep Learning Method for the Impact Damage Segmentation of Curve-Shaped CFRP Specimens Inspected by Infrared Thermography. Sensors. 2021; 21(2):395. https://doi.org/10.3390/s21020395

Chicago/Turabian Style

Wei, Ziang, Henrique Fernandes, Hans-Georg Herrmann, Jose R. Tarpani, and Ahmad Osman. 2021. "A Deep Learning Method for the Impact Damage Segmentation of Curve-Shaped CFRP Specimens Inspected by Infrared Thermography" Sensors 21, no. 2: 395. https://doi.org/10.3390/s21020395

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop