International Journal of Mechanical and Production Engineering (IJMPE)
Follow Us On :
current issues
Volume-12,Issue-1  ( Jan, 2024 )
Past issues
  1. Volume-11,Issue-12  ( Dec, 2023 )
  2. Volume-11,Issue-11  ( Nov, 2023 )
  3. Volume-11,Issue-10  ( Oct, 2023 )
  4. Volume-11,Issue-9  ( Sep, 2023 )
  5. Volume-11,Issue-8  ( Aug, 2023 )
  6. Volume-11,Issue-7  ( Jul, 2023 )
  7. Volume-11,Issue-6  ( Jun, 2023 )
  8. Volume-11,Issue-5  ( May, 2023 )
  9. Volume-11,Issue-4  ( Apr, 2023 )
  10. Volume-11,Issue-3  ( Mar, 2023 )

Statistics report
Apr. 2024
Submitted Papers : 80
Accepted Papers : 10
Rejected Papers : 70
Acc. Perc : 12%
Issue Published : 130
Paper Published : 2388
No. of Authors : 6802
  Journal Paper

Paper Title :
Defect image sample Generation for Automatic rail defect Recognition

Author :Yuwei Xia, Yanjun Qian, Hyock Ju Kwon

Article Citation :Yuwei Xia ,Yanjun Qian ,Hyock Ju Kwon , (2022 ) " Defect image sample Generation for Automatic rail defect Recognition " , International Journal of Mechanical and Production Engineering (IJMPE) , pp. 105-110, Volume-10,Issue-10

Abstract : Abstract - Railway defects can lead to enormous economic and human loss. Among all the defects, surface defects are most common and prominent type, and there have been many attempts to detect them with optical-based non-destructive testing (NDT) methods. However, there are many sources of errors that can jeopardize the NDT operation, among which human errors are the most unpredictable and frequent. The application of artificial intelligence (AI) to NDT interpretation has the potential to minimize human intervention, but the lack of sufficient images of the railways with various type of defects is the major obstacles to train the AI models. To address the issue of data scarcity, RailGAN model was proposed, which can improve the Cycle GANmodel by introducing an additional pre-sampling stage for the railway tracks in the algorithm. Two pre-sampling techniques were tested for RailGAN model: image-filtration and U-Net. By applying both techniques to 20 real-time railway images, U-Net could produce more consistent results of performing image segmentation on all the images while being less affected by pixel intensity values. Adoption of U-Net for the RailGAN model and applying both the RailGAN and the original CycleGAN models to the same real-time railway images showed that the original CycleGAN model tends to generate defects in the irrelevant background, whereas the RailGAN adds these synthetic defect patterns only on the railway surface. These images resemble real cracks on the railways and can be used for the training of neural network-based defect identification algorithms Keywords - Railway Defects, Nondestructive Testing, Image Augmentation, Machine Learning.

Type : Research paper

Published : Volume-10,Issue-10


Copyright: © Institute of Research and Journals

| PDF |
Viewed - 36
| Published on 2023-02-15
IRAJ Other Journals
IJMPE updates
Volume-12,Issue-1 (Jan, 2024 )
The Conference World