Cycle-consistent generative adversarial networks for damage evolution analysis in fiber-reinforced polymers based on synthetic damage states

Simple item page
dc.contributor.authorHelwing, Ramon
dc.contributor.authorMrzljak, Selim
dc.contributor.authorHülsbusch, Daniel
dc.contributor.authorWalther, Frank
dc.date.accessioned2026-01-16T13:44:30Z
dc.date.available2026-01-16T13:44:30Z
dc.date.issued2024-06-03
dc.description.abstractAnalyzing computed tomography (CT) scans is challenging and time-consuming due to their high complexity. Machine learning, particularly in the form of segmentation techniques, has emerged as the state-of-the-art approach for defect detection in parts and materials. However, the lack of pixel-accurate labeled training data remains a significant challenge. This paper presents a damage state transformation approach based on a cycle-consistent generative adversarial network (CycleGAN) using fatigue damage states of fiber-reinforced polymers. The generated synthetic data is visually almost indistinguishable from real data. Introduced damage can be determined by calculating the damage removed during the transformation from a high-damage state to a low-damage state. Using multiple transformation steps in detecting and distinguishing different damage states the effectiveness is demonstrated. In addition, the virtual addition of damage to undamaged specimens is investigated. The results show that certain damages exhibit chaotic generation across successive slices while maintaining semantic connections in specific regions across multiple slices. Overall, this research presents a valuable approach for improved self-supervised damage detection and characterization in CT scans, with potential applications in materials analysis and structural health monitoring.en
dc.identifier.urihttp://hdl.handle.net/2003/44661
dc.language.isoen
dc.relation.ispartofseriesComposites science and technology; 254
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectDefectsen
dc.subjectFatigueen
dc.subjectDamage mechanicsen
dc.subjectX-ray computed tomographyen
dc.subjectDeep learningen
dc.subject.ddc660
dc.subject.rswkWerkstofffehler
dc.subject.rswkMaterialermüdung
dc.subject.rswkWerkstoffschädigung
dc.subject.rswkComputertomografie
dc.subject.rswkDeep Learning
dc.subject.rswkFaserverstärkter Kunststoff
dc.titleCycle-consistent generative adversarial networks for damage evolution analysis in fiber-reinforced polymers based on synthetic damage statesen
dc.typeText
dc.type.publicationtypeArticle
dcterms.accessRightsopen access
eldorado.dnb.deposittrue
eldorado.doi.registerfalse
eldorado.secondarypublicationtrue
eldorado.secondarypublication.primarycitationRamon Helwing, Selim Mrzljak, Daniel Hülsbusch, Frank Walther, Cycle-consistent generative adversarial networks for damage evolution analysis in fiber-reinforced polymers based on synthetic damage states, Composites Science and Technology, Volume 254, 2024, 110695, https://doi.org/10.1016/j.compscitech.2024.110695
eldorado.secondarypublication.primaryidentifierhttps://doi.org/10.1016/j.compscitech.2024.110695

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S0266353824002653-main.pdf
Size:
11.46 MB
Format:
Adobe Portable Document Format
Description:
DNB
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.82 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Lehrstuhl für Werkstoffprüftechnik