SavedAdd your journal

Journals / Firat University Journal of Experimental and Computational Engineering / 2026 / Cilt: 4 Sayı: 1

Fault Detection in Steel Belts of Tires Using Magnetic Sensors and Different Deep Learning Models

Manyetik Sensörler ve Farklı Derin Öğrenme Modelleri Kullanarak Lastiklerin Çelik Kayışlarındaki Arıza Tespiti

Sercan Yalçın(ADIYAMAN ÜNİVERSİTESİ)0000-0003-1420-2490
Pages
85–99
Publication Date
2025-02-18
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Experimental results demonstrate that all models exhibit strong performance, with the Transformer model achieving the highest accuracy of 96.12%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Tire failures pose significant safety risks, necessitating advanced inspection techniques.
📊
Key Findings & Data:It was aim to develop a robust and accurate fault detection system by measuring magnetic field variations caused by defects.
💡
Conclusion & Impact:Experimental results demonstrate that all models exhibit strong performance, with the Transformer model achieving the highest accuracy of 96.12%.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Derin öğrenme · Çelik kayışlar · Manyetik sensör

Abstract

Tire failures pose significant safety risks, necessitating advanced inspection techniques. This research investigates the application of magnetic sensors and deep learning for detecting defects in steel belts of the tires. It was aim to develop a robust and accurate fault detection system by measuring magnetic field variations caused by defects. In this study, the magnetic image sensor circuit had been designed and then the images obtained from it have been classified as none, crack, and delamination type steel belt errors. Various deep learning models and their hybrid architectures, were explored and compared. Experimental results demonstrate that all models exhibit strong performance, with the Transformer model achieving the highest accuracy of 96.12%. The developed system offers a potential solution for improving tire safety and reducing maintenance costs in industries.

Özet

Lastik arızaları önemli güvenlik riskleri oluşturur ve ileri seviye inceleme tekniklerini gerektirir. Bu araştırma, lastiklerin çelik kuşaklarındaki kusurları tespit etmek için manyetik sensörlerin ve derin öğrenmenin uygulanmasını incelemektedir. Kusurların neden olduğu manyetik alan değişimlerini yakalayarak, sağlam ve doğru bir arıza tespit sistemi geliştirilmesi amaçlanmaktadır. Bu çalışmada, manyetik görüntü sensör devresi tasarlanmış ve daha sonra ondan elde edilen görüntüler, hata olmayan, çatlak ve delaminasyon tipi çelik kuşak hataları olarak sınıflandırılmıştır. Çeşitli derin öğrenme modelleri ve bunların hibrit mimarileri araştırılmış ve karşılaştırılmıştır. Deneysel sonuçlar tüm modellerin güçlü bir performans sergilediğini, Transformatör modelinin %96.12'lik en yüksek doğruluğa ulaştığını göstermektedir. Geliştirilen sistem, endüstrilerde lastik güvenliğini iyileştirmek ve bakım maliyetlerini düşürmek için potansiyel bir çözüm sunmaktadır.

🔖

Cite This Article

Yalçın, S. (2025). Fault Detection in Steel Belts of Tires Using Magnetic Sensors and Different Deep Learning Models. Firat University Journal of Experimental and Computational Engineering, Cilt: 4 Sayı: 1, 85–99. https://doi.org/10.62520/fujece.1527246

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (20)

  1. Y. Zhang, D. Lefebvre, and Q. Li, "Automatic detection of defects in tire radiographic images," IEEE Trans. Autom. Sci. Eng., vol. 14, no. 3, pp. 1378–1386, Jul. 2017.
  2. S. L. Lin, "Research on tire crack detection using image deep learning method," Sci. Rep., vol. 13, p. 8027, 2023.
  3. Z. Zhang, M. Zhou, H. Wan, M. Li, G. Li, and D. Han, "IDD-Net: Industrial defect detection method based on deep learning," Eng. Appl. Artif. Intell., vol. 123, pt. B, p. 106390, 2023.
  4. B. Wang, D. Dou, and N. Shen, "An intelligent belt wear fault diagnosis method based on deep learning," Int. J. Coal Prep. Util., vol. 43, no. 4, pp. 708–725, 2022.
  5. S. Brol and J. Warczek, "Utilization of magnetic signature of automotive tire for exploitational wear assessment," Diagnostyka, vol. 23, no. 4, p. 2022412, 2022.
  6. Y. Zhang, D. Lefebvre, Q. Li, "Automatic Detection of Defects in Tire Radiographic Images," in IEEE Trans. Autom. Sci. Eng., vol. 14, no. 3, pp. 1378-1386, July 2017.
  7. Z. Zheng, J. Shen, Y. Shao, J. Zhang, C. Tian, B. Yu, and Y. Zhang, "Tire defect classification using a deep convolutional sparse-coding network," Meas. Sci. Technol., vol. 32, no. 5, p. 055401, 2021.
  8. M. Liu, Q. Zhu, Y. Yin, Y. Fan, Z. Su, and S. Zhang, "Damage detection method of mining conveyor belt based on deep learning," IEEE Sens. J., vol. 22, no. 11, pp. 10870–10879, Jun. 2022.
  9. L. Xie, X. Xiang, H. Xu, L. Wang, L. Lin, and G. Yin, "FFCNN: A deep neural network for surface defect detection of magnetic tile," IEEE Trans. Ind. Electron., vol. 68, no. 4, pp. 3506–3516, Apr. 2021.
  10. R. Martínez-Parrales and A. C. Téllez-Anguiano, "Vibration-based fault detection system with IoT capabilities for a conveyor machine," Acta Polytech. Hung., vol. 19, no. 9, pp. 7–24, 2022.
  11. Y. Sedaghat, N. Parhizgar, and A. Keshavarz, "Automatic defects detection using neighborhood windows features in tire X-ray images," Int. J. Nonlinear Anal. Appl., vol. 12, spec. iss., pp. 2493–2508, 2021.
  12. A. Ş. Şener, I. F. Ince, H. B. Baydargil, I. Garip, and O. Ozturk, "Deep learning-based automatic vertical height adjustment of incorrectly fastened seat belts for driver and passenger safety in fleet vehicles," Proc. Inst. Mech. Eng., Part D: J. Automob. Eng., vol. 236, no. 4, pp. 639–654, 2022.
  13. G. Sun, R. Zhang, Z. Liu, L. Wu, Q. Yu, and X. Tan, "EMD-based noise reduction study of steel-cored conveyor belt containing slag signal," Alexandria Eng. J., vol. 98, pp. 56–67, 2024.
  14. A. Hamdi, Y. F. Yapan, A. Uysal, and H. Abderazek, "Multi-objective analysis and optimization of energy aspects during dry and MQL turning of unreinforced polypropylene (PP): An approach based on ANOVA, ANN, MOWCA, and MOALO," Int. J. Adv. Manuf. Technol., vol. 128, no. 11, pp. 4933–4950, 2023.
  15. T. Nguyen-Da, P. Nguyen-Thanh, and M.-Y. Cho, "Real-time AIoT anomaly detection for industrial diesel generator based on efficient deep learning CNN-LSTM in Industry 4.0," Internet Things, vol. 27, p. 101280, 2024.
  16. P. N. Thanh and M.-Y. Cho, "Advanced AIoT for failure classification of industrial diesel generators based on hybrid deep learning CNN-BiLSTM algorithm," Adv. Eng. Inf., vol. 62, pt. A, p. 102644, 2024.
  17. Y. Tian, G. Wang, H. Li, Y. Huang, F. Zhao, Y. Guo, J. Gao, J. Lai, "A novel deep learning method based on 2-D CNNs and GRUs for permeability prediction of tight sandstone," Geoenergy Sci. Eng., vol. 238, p. 212851, 2024.
  18. X. Qin, W. Zhu, Q. Hu, Z. Zhou, Y. Ding, X. Gao, R. Gu, "DenseNet-Transformer: A deep learning method for spatial–temporal traffic prediction in optical fronthaul network," Comput. Netw., p. 110674, 2024.
  19. V. V. N. S. Kumar, G. H. Reddy, and M. N. GiriPrasad, "A novel glaucoma detection model using Unet++-based segmentation and ResNet with GRU-based optimized deep learning," Biomed. Signal Process. Control, vol. 86, pt. A, p. 105069, 2023.
  20. E. Ozbay and F. A. Ozbay, "Derin öğrenme ve sınıflandırma yaklaşımları ile BT görüntülerinden Covid-19 tespiti," Dicle Univ. Muhendislik Fak. Muhendislik Derg., vol. 12, no. 2, pp. 211–219, 2021