Machine learning based thermal imaging damage detection in glass-epoxy composite materials

Sarhadi, Ali; Albuquerque, Rodrigo Q.; Demleitner, Martin; Ruckdäschel, Holger; Eder, Maximilian

doi:10.1016/j.compstruct.2022.115786

Cited by 13 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thermal cameras can capture objects' surface temperature distribution and detect potential defects by analyzing temperature anomalies. Relevant literature indicates that thermal imaging detection technology can provide high sensitivity and resolution for composite material structures [17,18]. In this study, we employed machine learning and image processing techniques to precisely analyze thermal images and detect defects in composite material structures.…”

Section: Thermal Imaging Detectionmentioning

confidence: 99%

Detection and Analysis of Aircraft Composite Material Structures Using UAV

Liao,

Liou,

Hidayat

et al. 2024

Inventions

View full text Add to dashboard Cite

Pre-flight inspection and maintenance are essential prerequisites for aviation safety. This study focused on developing a real-time monitoring system designed to assess the condition of composite material structures on the exterior of aircraft. Implementing such a system can reduce operational costs, enhance flight safety, and increase aircraft availability. This study aims to detect defects in aircraft fuselages manufactured from composite materials by applying image visual recognition technology. This study integrated a drone and an infrared camera for real-time image transmission to ground stations. MATLAB image analysis software (MATLAB 2020b) was used to analyze infrared (IR) images and detect structural defects in the aircraft’s appearance. This methodology was based on the inspection of damaged engine cowlings. The developed approach compares composite material conditions with known defects before and after repair, considering mechanical performance, defect size, and strength. Simultaneously, tests were conducted on various composite material panels with unknown defects, yielding favorable results. This study underscores an integrated system offering rapid detection, real-time feedback, and analysis, effectively reducing time, and potential hazards associated with high-altitude operations. Furthermore, it addresses blind spots in aircraft inspections, contributing to effective flight safety maintenance.

show abstract

Section: Thermal Imaging Detectionmentioning

confidence: 99%

Detection and Analysis of Aircraft Composite Material Structures Using UAV

Liao,

Liou,

Hidayat

et al. 2024

Inventions

View full text Add to dashboard Cite

show abstract

“…Internal defects on such materials could be characterized from infrared imaging acquired from the material surface via a fully theoretical methodology. [ 123 ] This was achieved by training a ML model (kernel ridge regression) using the infrared pixels artificially generated from finite‐element simulations of materials bearing a variety of defects. The size and depth of the defects were predicted with accuracies in the range of 85% to 98% revealing that this technique might be helpful to detect and, therefore, prevent the worsening of the mechanical properties of polymer‐based materials.…”

Section: Properties Of Polymeric Materialsmentioning

confidence: 99%

“…In a different approach, a ML model was trained to predict damage parameters in epoxy composites from artificially generated infrared images. [ 123 ] With this approach, it was possible to detect the shape, size and depth of hotspots with an accuracy in the range of 85 to 99%, as calculated for the test set.…”

Section: Applicationsmentioning

confidence: 99%

Application of Digital Methods in Polymer Science and Engineering

Schuett,

Endres,

Standau

et al. 2023

Adv Funct Materials

Self Cite

View full text Add to dashboard Cite

The development of new polymer materials is an emerging field for more than 100 years. However, it is currently facing major challenges and the application of digital methods can help to develop new processes, discover new materials and, thus, contribute to the challenges of today and the future. Though, the application of digital methods in the field of polymer science is currently very limited, when compared to other classes of materials such as small molecules or inorganic high‐performance materials. Nevertheless, there are already first, very promising approaches. The current review article focuses on the application of these methods in different aspects of polymer research including polymer design, synthesis, and characterization. Furthermore, the digital discovery of polymer engineering is highlighted in detail showing the broad range of potential applications of these methods in polymer science. Finally, future possibilities and opportunities are derived from the current state‐of‐the‐art and perspectives for a potential evolution of polymer science are provided.

show abstract

“…Non‐destructive testing (NDT) techniques have been widely utilized for the detection of impact damage in composite materials. Various methods, such as acoustic emission, 5 ultrasound technology, 6 gratings, 7 Lamb waves, 8 thermal imaging, 9 and X‐rays, 10 have been employed for this purpose. These methods have found extensive application and have proven to be effective in detecting damage 11,12 .…”

Section: Introductionmentioning

confidence: 99%

Comparative study of dynamic parameters for damage identification of carbon fiber reinforced polymer tube

Luo,

Yu,

Zhang

et al. 2024

Polymer Composites

View full text Add to dashboard Cite

The primary objective of the paper is the numerical and experimental investigation related to the damage recognition effects for CFRP tubes of four dynamic parameters. Four damage identification indexes consisting of natural frequency‐based index, Mode Shape‐based index (MS), Mode Shape Curvature‐based index (MSC), and Modal Flexibility Curvature‐based index (MFC) are established by analyzing the dynamic parameter data obtained before and after damage occurs. The performances of dynamic parameters are thoroughly discussed in the context of numerical simulations and experiment. The results indicate that the effect of natural frequency is not as significant as that of mode shape. MFC has the most notable effectiveness out of the four indexes. The simulation peak index pair is predicted to rise from 0.3 to 0.6 as the damage in the simulation model increases by 25% from 12.5%, indicating that MFC can feedback the damage degree. Moreover, the circumferential curvature index exhibits superior performance compared to the axial curvature index. To enhance the accuracy of the axial curvature index, it is proposed to increase the number of measuring sites along the tube's long direction.Highlights Damage identification indexes of four dynamic parameters are established. Discuss the identification ability of dynamic parameters by simulation and test. Two numerical models of CFRP tube with delamination damage are established. Impact and modal tests are executed to study the ability of four indexes.

show abstract

Machine learning based thermal imaging damage detection in glass-epoxy composite materials

Cited by 13 publications

References 20 publications

Detection and Analysis of Aircraft Composite Material Structures Using UAV

Detection and Analysis of Aircraft Composite Material Structures Using UAV

Application of Digital Methods in Polymer Science and Engineering

Comparative study of dynamic parameters for damage identification of carbon fiber reinforced polymer tube

Contact Info

Product

Resources

About