Е-Публикации
Технически университет - София

Abstract: This paper presents the transfer learning model for studying the accuracy of railway surface defect detection and classification. The research focuses on one of the major structural faults defect, the railway track. The types of defects include cracking, flacking, shelling, and spalling, many of which were selected because of the distinctiveness of the defect. While many research studies classify defect, they are often not accurately classified using traditional machine learning methods due to the variability of defects and complexity of defect patterns. To solve the problem, this research demonstrates a pre-trained model, with a DenseNet121 architecture, to provide transfer learning to focus on surface fault detection. The model achieved accuracy of close to 99%, which is near perfect, and is significantly better than majority generalized models. The proposed model not only uses the representational strength of DenseNet but allows for good generalization across all defect classes with minimum feature engineering and augmentation. This framework can also be extended to other industrial fault detection tasks, which can demonstrate its scalability and effectiveness in the real-world

References

1. M. Pawlik, "Concept of the railway safety, security and cybersecurity Network Accelerators, " Proceedings of the IEEE VLSI Test functional integrity levels, " MATEC Web of Conferences, vol. 294, p. Symposium, 2024, doi: 10. 1109/VTS60656. 2024. 10538531. 03003, 2019, doi: 10. 1051/MATECCONF/201929403003.
2. S. Liu, Q. Wang, and Y. Luo, "A review of applications of visual inspection technology based on image processing in the railway industry, " Transportation Safety and Environment, vol. 1, no. 3, pp. 185-204, Dec. 2019, doi: 10. 1093/TSE/TDZ007.
3. F. Rustam et al., "Railway Track Fault Detection Using Selective MFCC Features from Acoustic Data, " Sensors 2023, Vol. 23, Page 7018, vol. 23, no. 16, p. 7018, Aug. 2023, doi: 10. 3390/S23167018.
4. F. Ghofrani, Q. He, R. M. P. Goverde, and X. Liu, "Recent applications of big data analytics in railway transportation systems: A survey, " Transp Res Part C Emerg Technol, vol. 90, pp. 226-246, May 2018, doi: 10. 1016/J. TRC. 2018. 03. 010.
5. M. Priestley, F. O'Donnell, and E. Simperl, "A Survey of Data Quality Requirements That Matter in ML Development Pipelines, " Journal of Data and Information Quality, vol. 15, no. 2, Jun. 2023, doi: 10. 1145/3592616/ASSET/2583075A-F931-414C-9045-EFC03428BFFB/ASSETS/GRAPHIC/JDIQ-2022-04-SRV-0005F05. JPG.
6. S. Hong et al., "The relationship between data skewness and accuracy of Artificial Neural Network predictive model, " IOP Conf Ser Mater Sci Eng, vol. 523, no. 1, p. 012070, May 2019, doi: 10. 1088/1757899X/523/1/012070.
7. H. Liu, M. Long, J. Wang, and Y. Wang, "Learning to Adapt to Evolving Domains, " Adv Neural Inf Process Syst, vol. 33, pp. 22338-22348, 2020.
8. A. Arain, S. Mehran, M. Z. Shaikh, D. Kumar, B. S. Chowdhry, and T. Hussain, "Railway track surface faults dataset, " Data Brief, vol. 52, p. 110050, Feb. 2024, doi: 10. 1016/J. DIB. 2024. 110050.
9. Y. W. Lin, C. C. Hsieh, W. H. Huang, S. L. Hsieh, and W. H. Hung, "Railway Track Fasteners Fault Detection using Deep Learning, " 2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019, pp. 187-190, Oct. 2019, doi: 10. 1109/ECICE47484. 2019. 8942769.
10. J. Li, R. Huang, G. He, S. Wang, G. Li, and W. Li, "A Deep Adversarial Transfer Learning Network for Machinery Emerging Fault Detection, " IEEE Sens J, vol. 20, no. 15, pp. 8413-8422, Aug. 2020, doi: 10. 1109/JSEN. 2020. 2975286.
11. Y. Ye, P. Huang, and Y. Zhang, "Deep learning-based fault diagnostic network of high-speed train secondary suspension systems for immunity to track irregularities and wheel wear, " Railway Engineering Science, vol. 30, no. 1, pp. 96-116, Mar. 2022, doi: 10. 1007/S40534021-00252-Z/FIGURES/14.
12. K. Rai, F. Hojatpanah, F. Badrkhani Ajaei, and K. Grolinger, "Deep Learning for High-Impedance Fault Detection: Convolutional Autoencoders, " Energies 2021, Vol. 14, Page 3623, vol. 14, no. 12, p. 3623, Jun. 2021, doi: 10. 3390/EN14123623.
13. R. Shafique et al., "A Novel Approach to Railway Track Faults Detection Using Acoustic Analysis, " Sensors 2021, Vol. 21, Page 6221, vol. 21, no. 18, p. 6221, Sep. 2021, doi: 10. 3390/S21186221.
14. T. Bai, J. Gao, J. Yang, and D. Yao, "A Study on Railway Surface Defects Detection Based on Machine Vision, " Entropy 2021, Vol. 23, Page 1437, vol. 23, no. 11, p. 1437, Oct. 2021, doi: 10. 3390/E23111437.

Issue

Copyright IEEE