Tensorflow Kütüphanesi Kullanılarak Oluşturulan Derin Öğrenme Modeli ile Demiryolu Hattı Görüntülerinden Arıza Tespitinin Gerçekleştirilmesi

Abstract

Ulaşım aracı, bir nesnenin, bireyin veya hizmetin bir yerden başka bir yere aktarılmasını sağlayan vasıtadır. Demiryolu ulaşımı maliyet ve güvenirlilik açısından önemli bir yere sahiptir. Tren kazaların çoğu demiryolu raylarında meydana gelen arızalardan kaynaklanmaktadır. Demiryolu hatlarındaki arızaların tespiti geleneksel yöntemlere göre zor ve zaman alıcı bir süreçtir. Bu çalışmada demiryolu hatlarında meydana gelen arızaların tespitini gerçekleştirebilen yapay zekâ tabanlı bir model önerilmiştir. Çalışmada kullanılan veri kümesi arızalı ve arızalı olmayan ray görüntülerinden oluşmaktadır. Önerilen model Tensorflow Kütüphanesi kullanılarak tasarlanmış evrişimsel sinir ağlarından oluşmaktadır. Sınıflandırıcı olarak Softmax yöntemi kullanılmıştır. Gerçekleştirilen deneyde %92,21 genel doğruluk başarısı elde edilmiştir.

Keywords

• Karar destek sistemleri
• Derin öğrenme
• Ray arıza tespiti
• Yapay zekâ

Fault Detection from Images of Railroad Lines Using the Deep Learning Model Built with the Tensorflow Library

Abstract

A means of transportation is the way in which an object, person, or service is transported from one place to another. Rail transportation occupies an important place in terms of cost and reliability. Most train accidents are caused by faults in railroad tracks. Detecting faults in railroad tracks is a difficult and time-consuming process compared to conventional methods. In this study, an artificial intelligence based model is proposed that can detect faults in railroad tracks. The dataset used in the study consists of defective and non-defective railroad images. The proposed model consists of foldable neural networks developed using the Tensorflow library. Softmax method was used as a classifier. An overall accuracy of 92.21% was achieved in the experiment.

Keywords

• Decision support systems
• Deep learning
• Rail fault detection
• Artificial intelligence

References

1. [1] G. Sarang, “Replacement Of Stabilizers By Recycling Plastic In Asphalt Concrete,” in Use of Recycled Plastics in Eco-efficient Concrete, Elsevier, 2019, pp. 307–325.
2. [2] T. Deniz, “Türkiye’de Ulaşım Sektöründe Yaşanan Değişimler Ve Mevcut Durum,” Doğu Coğrafya Derg., vol. 21, no. 36, p. 135, Aug. 2016.
3. [3] A. Welankiwar, S. Sherekar, A. P. Bhagat, and P. A. Khodke, “Fault Detection in Railway Tracks Using Artificial Neural Networks,” in 2018 International Conference on Research in Intelligent and Computing in Engineering (RICE), 2018, pp. 1–5.
4. [4] A. James et al., “TrackNet - A Deep Learning Based Fault Detection for Railway Track Inspection,” in 2018 International Conference on Intelligent Rail Transportation (ICIRT), 2018, pp. 1–5.
5. [5] R. Shafique et al., “A Novel Approach to Railway Track Faults Detection Using Acoustic Analysis,” Sensors, vol. 21, no. 18, p. 6221, Sep. 2021.
6. [6] X. Wei, Z. Yang, Y. Liu, D. Wei, L. Jia, and Y. Li, “Railway Track Fastener Defect Detection Based on Image Processing and Deep Learning Techniques: A Comparative Study,” Eng. Appl. Artif. Intell., vol. 80, pp. 66–81, 2019.
7. [7] Y.-W. Lin, C.-C. Hsieh, W.-H. Huang, S.-L. Hsieh, and W.-H. Hung, “Railway Track Fasteners Fault Detection using Deep Learning,” in 2019 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), 2019, pp. 187–190.
8. [8] C. Yang, Y. Sun, C. Ladubec, and Y. Liu, “Developing Machine Learning-Based Models for Railway Inspection,” Appl. Sci., vol. 11, no. 1, p. 13, Dec. 2020.

9. [9] E. Hovad et al., “Deep Learning for Automatic Railway Maintenance,” 2021, pp. 207–228.
10. [10] M. Sysyn, U. Gerber, O. Nabochenko, D. Gruen, and F. Kluge, “Prediction of Rail Contact Fatigue on Crossings Using Image Processing and Machine Learning Methods,” Urban Rail Transit, vol. 5, no. 2, pp. 123–132, 2019.
11. [11] M. Rajagopal, M. Balasubramanian, S. Palanivel, “An Efficient Framework to Detect Cracks in Rail Tracks Using Neural Network Classifier,” Computacion y Sistemas, vol. 22, no. 3, pp. 943–952, 2018.
12. [12] S. I. Eunus, “Railway Track Fault Detection,” Kaggle, 2021. [Online]. Available: https://www.kaggle.com/salmaneunus/railway-track-fault-detection. [Accessed: 28-Nov-2021].
13. [13] H. Selçuk, T. Ç. Akıncı, and Ş. S. Şeker, “Derin Evrişimli Sinir Ağı Modellerinin Açık Kaynak Kodlu Yazılım Platformlarında Tasarımının Değerlendirilmesi,” İstanbul Sabahattin Zaim Üniversitesi Fen Bilim. Enstitüsü Derg., Apr. 2021.
14. [14] T.-C. Lu, “CNN Convolutional Layer Optimisation Based On Quantum Evolutionary Algorithm,” Conn. Sci., vol. 33, no. 3, pp. 482–494, Jul. 2021.
15. [15] C. F. G. dos Santos, T. P. Moreira, D. Colombo, and J. P. Papa, “Does Removing Pooling Layers from Convolutional Neural Networks Improve Results?,” SN Comput. Sci., vol. 1, no. 5, p. 275, Sep. 2020.
16. [16] P. Sperl, C.-Y. Kao, P. Chen, X. Lei, and K. Böttinger, “DLA: Dense-Layer-Analysis for Adversarial Example Detection,” in 2020 IEEE European Symposium on Security and Privacy (EuroS&P), 2020, pp. 198–215.
17. [17] C. Garbin, X. Zhu, and O. Marques, “Dropout vs. Batch Normalization: An Empirical Study of Their Impact to Deep Learning,” Multimed. Tools Appl., vol. 79, no. 19, pp. 12777–12815, 2020.
18. [18] S. Maharjan, A. Alsadoon, P. W. C. Prasad, T. Al-Dalain, and O. H. Alsadoon, “A novel enhanced softmax loss function for brain tumour detection using deep learning,” J. Neurosci. Methods, vol. 330, p. 108520, 2020.
19. [19] N. P. Jouppi et al., “In-Datacenter Performance Analysis Of A Tensor Processing Unit,” in 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA), 2017, pp. 1–12.
20. [20] S. Khirirat, H. R. Feyzmahdavian, and M. Johansson, “Mini-Batch Gradient Descent: Faster Convergence Under Data Sparsity,” in 2017 IEEE 56th Annual Conference on Decision and Control (CDC), 2017, pp. 2880–2887.
21. [21] X. Ying, “An Overview Of Overfitting And Its Solutions,” J. Phys. Conf. Ser., vol. 1168, p. 022022, Feb. 2019.
22. [22] Z. Cömert, “Fusing Fine-Tuned Deep Features For Recognizing Different Tympanic Membranes,” Biocybern. Biomed. Eng., vol. 40, no. 1, pp. 40–51, Jan. 2020.
23. [23]E. Başaran, Z. Cömert, A. Şengür, Ü. Budak, Y. Çelik, and M. Toğaçar, “Chronic Tympanic Membrane Diagnosis based on Deep Convolutional Neural Network,” in 2019 4th International Conference on Computer Science and Engineering (UBMK), 2019, pp. 1–4.
24. [24]S. Boughorbel, F. Jarray, and M. El-Anbari, “Optimal Classifier For Imbalanced Data Using Matthews Correlation Coefficient Metric,” PLoS One, vol. 12, no. 6, p. e0177678, Jun. 2017.