Cycle-consistent generative adversarial networks for damage evolution analysis in fiber-reinforced polymers based on synthetic damage states
Source abstract
Abstract
Analyzing 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.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · High-Velocity Impact and Material Behavior · Integrated Circuits and Semiconductor Failure Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Impact crack quantification analyses in 3-D angle-interlock woven composite using image segmentation method10.1016/j.engfracmech.2022.108529 ↗
2. Active yarn meshes for segmentation on X-ray computed tomography of textile composite materials at the mesoscopic scale10.1016/j.compstruct.2021.115084 ↗
3. Effect of carbon nanofibre orientation on fatigue properties of carbon fibre-reinforced polymers
4. Assessing thermophysical properties of parameterized woven composite models using image-based simulations10.1016/j.compscitech.2023.110136 ↗
5. Automated brain tumor detection using machine learning: a bibliometric review10.1016/j.wneu.2023.03.115 ↗
6. Flynet–Neural network model for automatic building detection from satellite images10.1007/s12524-023-01703-2 ↗
7. Deriving agricultural field boundaries for crop management from satellite images using semantic feature pyramid network
8. Characterization of pultruded glass-fiber reinforced polymers with two-step homogenization10.1590/1980-5373-mr-2022-0252 ↗
9. Analysing the interactions between training dataset size, label noise and model performance in remote sensing data
10. Label noise in segmentation networks: mitigation must deal with bias
11. Deep learning-based fatigue damage segmentation of wind turbine blades under complex dynamic thermal backgrounds
12. Classification of barely visible impact damage in composite laminates using deep learning and pulsed thermographic inspection
13. Digital image correlation (DIC) based damage detection for CFRP laminates by using machine learning based image semantic segmentation10.1016/j.ijmecsci.2022.107529 ↗
14. Application-oriented digital image correlation for the high-speed deformation and fracture analysis of AISI 1045 and Ti6Al4V materials
15. A modular U-Net for automated segmentation of X-ray tomography images in composite materials10.3389/fmats.2021.761229 ↗
16. Deep learning method for analysis and segmentation of fatigue damage in X-ray computed tomography data for fiber-reinforced polymers10.1016/j.compscitech.2022.109781 ↗
17. Effective segmentation of short fibers in glass fiber reinforced concrete's X-ray images using deep learning technology10.1016/j.matdes.2021.110024 ↗
18. Semantic segmentation for non-destructive testing with step-heating thermography for composite laminates
19. An improved dataset augmentation approach for deep learning-based XCT images segmentation in layered composite fabric10.1016/j.compstruct.2023.117052 ↗
20. IRT-GAN: a generative adversarial network with a multi-headed fusion strategy for automated defect detection in composites using infrared thermography10.1016/j.compstruct.2022.115543 ↗
21. A methodology to automatically segment 3D ultrasonic data using X-ray computed tomography and a Convolutional Neural Network
22. Automated image segmentation of 3D printed fibrous composite micro-structures using a neural network10.1016/j.conbuildmat.2022.130099 ↗
23. Automatic defects segmentation and identification by deep learning algorithm with pulsed thermography: synthetic and experimental data
24. Delamination identification using global convolution networks
25. Deep learning approach for delamination identification using animation of Lamb waves10.1016/j.engappai.2022.105520 ↗
26. Validation of deep learning segmentation of CT images of fiber-reinforced composites
27. A weakly reiterative patches-wise framework for CT liver and lesions segmentation
28. Discriminative localization in CNNs for weakly-supervised segmentation of pulmonary nodules
29. Weakly supervised semantic segmentation for MRI: exploring the advantages and disadvantages of class activation maps for biological image segmentation with soft boundaries
30. Generative adversarial networks for synthetic defect generation in assembly and test manufacturing
31. A surface defect detection method based on positive samples
32. Unpaired image-to-image translation using cycle-consistent adversarial networks
33. Weakly-supervised defect segmentation on periodic textures using CycleGAN
34. DefectGAN: weakly-supervised defect detection using generative adversarial network
35. Comparison of the damage evolution in glass fiber-reinforced polyurethane and epoxy in the HCF and VHCF regimes investigated by intermittent in situ X-ray computed tomography
36. Hülsbusch · 2021
37. X-ray computed tomography of polymer composites10.1016/j.compscitech.2017.10.023 ↗
38. X-ray computed microtomography of internal damage in fiber reinforced polymer matrix composites
39. In situ computed tomography for the characterization of the fatigue damage development in glass fiber-reinforced polyurethane
40. V-Net: fully convolutional neural networks for volumetric medical image segmentation
41. Image-to-image translation with conditional adversarial networks
42. Perceptual losses for real-time style transfer and super-resolution
43. GAN slimming: all-in-one GAN compression by A unified optimization framework
44. CycleGAN, a master of steganography