Defect identification in composite materials via thermography and deep learning techniques

被引：120

作者：

Bang H.-T. ^{[1
]}

Park S. ^{[2
]}

Jeon H. ^{[1
]}

机构：

[1] Department of Civil and Environmental Engineering, Hanbat National University, 125 Dongseo-daero, Yuseong-gu, Daejeon

[2] Department of Civil Engineering, Pukyong National University, 45 Yongso-ro, Nam-gu, Busan

来源：

Composite Structures | 2021年 / 246卷

关键词：

Composite materials; Deep learning; Defect identification; Faster RCNN; Thermography;

D O I：

10.1016/j.compstruct.2020.112405

中图分类号：

学科分类号：

摘要：

Composite materials are widely used in aircraft, vehicle, and various industries due to their excellent mechanical properties. A thermography-based nondestructive test is often employed for diagnosis of defects in composite laminates, while the test results are largely affected by the environmental conditions, and show significant dependence to the inspector, instruments being used, and the test objectives. To overcome the limitation, the present study proposes a framework for identifying defects in composite materials by integrating a thermography test with a deep learning technique. A dataset of thermographic images of composite materials with defects were collected from literatures and were used for training the system to identify defects from given thermographic images. The versatile application of the proposed technique was validated by testing it on composite specimens produced by resin transfer molding and thermoplastic injection molding, using a combination of carbon/organo fabrics and thermoset/thermoplastic resins. The performance of the proposed system was evaluated by assessing its ability to identify defects from the specimens with artificial defects, and is discussed in light of average precision for identification of defects. © 2020 Elsevier Ltd

引用

共 30 条

[1]

Cho J., Lee S.K., Eem S.H., Jang J.G., Yang B., Enhanced mechanical and thermal properties of carbon fiber-reinforced thermoplastic polyketone composites, Compos Part A Appl Sci Manuf, (2019)

[2]

Kim Y.J., Park J., Yang C.M., Jeong H.S., Kim S.M., Han S.W., Et al., Bio-inspired incorporation of functionalized graphene oxide into carbon nanotube fibers for their efficient mechanical reinforcement, Compos Sci Technol, (2019)

[3]

Garnier C., Pastor M.L., Eyma F., Lorrain B., The detection of aeronautical defects in situ on composite structures using non destructive testing, Compos Struct, 93, pp. 1328-1336, (2011)

[4]

Kim K., Jung Y.C., Kim S.Y., Yang B.J., Kim J., Adhesion enhancement and damage protection for carbon fiber-reinforced polymer (CFRP) composites via silica particle coating, Compos Part A Appl Sci Manuf, 109, pp. 105-114, (2018)

[5]

Jeon H., Yu J., Lee H., Kim G.M., Kim J.W., Jung Y.C., Et al., A combined analytical formulation and genetic algorithm to analyze the nonlinear damage responses of continuous fiber toughened composites, Comput Mech, 60, pp. 393-408, (2017)

[6]

Vollmer M., Mollmann K., Infrared thermal imaging: fundamentals, research and applications, (2017)

[7]

Yang R., He Y., Optically and non-optically excited thermography for composites: A review, Infrared Phys Technol, 75, pp. 26-50, (2016)

[8]

Ciampa F., Mahmoodi P., Pinto F., Meo M., Recent advances in active infrared thermography for non-destructive testing of aerospace components, Sensors (Switzerland), (2018)

[9]

Schroeder J.A., Ahmed T., Chaudhry B., Shepard S., Non-destructive testing of structural composites and adhesively bonded composite joints: Pulsed thermography, Compos Part A Appl Sci Manuf, 33, pp. 1511-1517, (2002)

[10]

Yang J., Hwang S., An Y.K., Lee K., Sohn H., Multi-spot laser lock-in thermography for real-time imaging of cracks in semiconductor chips during a manufacturing process, J Mater Process Technol, 229, pp. 94-101, (2016)

← 1 2 3 →