Araştırma Makalesi
BibTex RIS Kaynak Göster

Robustness Classification by Machine Learning from Vehicle Tire Surface Abrasions

Yıl 2023, Cilt: 9 Sayı: 4, 151 - 157, 31.12.2023

Remzi Gürfidan Oğuzhan Kilim Tuncay Yiğit Bekir Aksoy

Öz

The safety and durability of vehicle tires is an important variable in terms of driving safety and cost effectiveness. Different methods such as visual inspection, tire air pressure control, pattern depth measurements, rotation and balancing can be used to evaluate these factors. In this study, different machine learning algorithms such as ResNET50, DenseNET121, AlexNET, CNN, which are image-based, are used to analyse the images of the tire surface to determine the surface wear of the vehicle tires and to perform robustness classification. For the training of the models, 1447 vehicle tire surface images of different categories (very good, good, bad, very bad) were used. The dataset containing the images belongs to the authors of this study and is unique. In the future, it is aimed to make the dataset available for copyrighted use on an open platform. The results obtained from the trained models are compared. The CNN algorithm, which showed the most successful results, was selected as the final algorithm. In conclusion, this paper represents an important step towards solving safety and efficiency issues in the automotive industry by introducing a machine learning approach to detect surface wear and robustness classification of vehicle tires. This technology has the potential to optimize tire management and maintenance.

Anahtar Kelimeler

Tire wear tire durability durability classification machine learning CNN

Kaynakça

  • [1] P. Behroozinia, S. Taheri, and R. Mirzaeifar, “Tire health monitoring using the intelligent tire concept,” Structural Health Monitoring vol. 18, no. 2, pp. 390–400, Feb. 2018, doi:10.1177/1475921718756602.
  • [2] Y. Zhang, T. Li, and Q. Li, “Defect detection for tire laser shearography image using curvelet transform based edge detector,” Optics & Laser Technology, vol. 47, pp. 64–71, Apr. 2013, doi:10.1016/J.OPTLASTEC.2012.08.023.
  • [3] F. Braghin, M. Brusarosco, F. Cheli, A. Cigada, S. Manzoni, and F. Mancosu, “Measurement of contact forces and patch features by means of accelerometers fixed inside the tire to improve future car active control,” Vehicle System Dynamics, vol. 44, no. SUPPL. 1, pp. 3–13, 2006, doi:10.1080/00423110600867101.
  • [4] H. Zhang, S. Zhang, Y. Zhang, X. Huang, and Y. Dai, “Abrasion status prediction with BP neural network based on an intelligent tire system,” 2020 4th CAA International Conference on Vehicular Control and Intelligence, CVCI 2020, pp. 619–622, Dec. 2020, doi:10.1109/CVCI51460.2020.9338547.
  • [5] J. Zhu, K. Han, and S. Wang, “Automobile tire life prediction based on image processing and machine learning technology,” Advances in Mechanical Engineering, vol. 13, no. 3, Mar. 2021, doi: 10.1177/16878140211002727
  • [6] H. Bhanare and A. Khachane, “Quality Inspection of Tire using Deep Learning based Computer Vision,” International Research Journal of Engineering and Technology vol. 6, no.11 pp.3555-3558, 2019, [Online]. Available: www.irjet.net [Accessed: Oct. 08, 2023].
  • [7] X. Cui, Y. Liu, Y. Zhang, and C. Wang, “Tire Defects Classification with Multi-Contrast Convolutional Neural Networks,” International Journal of Pattern Recognition and Artificial Intelligence vol. 32, no. 4, Dec. 2017, doi:10.1142/S0218001418500118.
  • [8] X. Cui, Y. Liu, and C. Wang, “Defect automatic detection for tire X-ray images using inverse transformation of principal component residual,” 2016 3rd International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2016, pp. 18–25, Oct. 2016, doi:10.1109/ICAIPR.2016.7585205.
  • [9] V. H. Nguyen, D. Zheng, F. Schmerwitz, and P. Wriggers, “An advanced abrasion model for tire wear,” Wear, vol. 396–397, pp. 75–85, Feb. 2018, doi:10.1016/J.WEAR.2017.11.009.
  • [10] X. Chen, N. Xu, and K. Guo, “Tire wear estimation based on nonlinear lateral dynamic of multi-axle steering vehicle,” International Journal of Automotive Technology, vol. 19, no. 1, pp. 63–75, Feb. 2018, doi:10.1007/S12239-018-0007-2/METRICS.
  • [11] J. Siegel, R. Bhattacharyya, S. Sarma, and A. Deshpande, “Smartphone-based vehicular tire pressure and condition monitoring,” Lecture Notes in Networks and Systems, vol. 15, pp. 805–824, 2018, doi:10.1007/978-3-319-56994-9_56/COVER.
  • [12] K. Kim, H. Park, and T. Kim, “Comparison of Performance of Predicting the Wear Amount of Tire Tread Depending on Sensing Information,” Sensors 2023, Vol. 23, Page 459, vol. 23, no. 1, p. 459, Jan. 2023, doi:10.3390/S23010459.
  • [13] B. Li, Z. Quan, S. Bei, L. Zhang, and H. Mao, “An estimation algorithm for tire wear using intelligent tire concept,” Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering vol. 235, no. 10–11, pp. 2712–2725, Feb. 2021, doi:10.1177/0954407021999483.
  • [14] Y.-J. Kim, H.-J. Kim, J.-Y. Han, and S. Lee, “Classification of Tire Tread Wear Using Accelerometer Signals through an Artificial Neural Network,” Journal of the Korean Society of Industry Convergence, vol. 23, no. 2_2, pp. 163–171, 2020, doi:10.21289/KSIC.2020.23.2.163.
  • [15] T. Poloni and J. Lu, “An Indirect Tire Health Monitoring System Using On-board Motion Sensors,” SAE Technical Papers, vol. 2017-March, no. March, Mar. 2017, doi:10.4271/2017-01-1626.

Araç Lastiği Yüzey Aşınmalarından Makine Öğrenmesi ile Sağlamlık Sınıflandırması

Yıl 2023, Cilt: 9 Sayı: 4, 151 - 157, 31.12.2023

Remzi Gürfidan Oğuzhan Kilim Tuncay Yiğit Bekir Aksoy

Öz

Araç lastiklerinin güvenliği ve dayanıklılığı, sürüş güvenliği ve maliyet etkinliği açısından önemli bir değişkendir. Bu faktörleri değerlendirmek için görsel inceleme, lastik hava basıncı kontrolü, desen derinliği ölçümleri, rotasyon ve balans ayarı gibi farklı yöntemler kullanılabilmektedir. Bu çalışmada, araç lastiklerinin yüzey aşınmasını belirlemek için lastik yüzeyine ait görüntüleri analiz etmek ve sağlamlık sınıflandırması yapmak için görüntü tabanlı olan ResNET50, DenseNET121, AlexNET, CNN gibi farklı makine öğrenmesi algoritmaları kullanılmıştır. Modellerin eğitimi için farklı kategorilerde (çok iyi, iyi, kötü, çok kötü) 1447 araç lastik yüzey görüntüsü kullanılmıştır. Görüntüleri içeren veri kümesi bu çalışmanın yazarlarına aittir ve özgündür. Gelecekte veri setinin açık bir platformda telifli olarak kullanıma sunulması hedeflenmektedir. Eğitilen modellerden elde edilen sonuçlar karşılaştırılmıştır. En başarılı sonuçları gösteren CNN algoritması nihai algoritma olarak seçilmiştir. Sonuç olarak, bu makale, araç lastiklerinin yüzey aşınmasını ve sağlamlık sınıflandırmasını tespit etmek için bir makine öğrenimi yaklaşımı sunarak otomotiv endüstrisindeki güvenlik ve verimlilik sorunlarını çözmeye yönelik önemli bir adımı temsil etmektedir. Bu teknoloji, lastik yönetimi ve bakımını optimize etme potansiyeline sahiptir.

Anahtar Kelimeler

Lastik aşınması lastik dayanıklılığı dayanıklılık sınıflandırması makine öğrenmesi CNN

Kaynakça

  • [1] P. Behroozinia, S. Taheri, and R. Mirzaeifar, “Tire health monitoring using the intelligent tire concept,” Structural Health Monitoring vol. 18, no. 2, pp. 390–400, Feb. 2018, doi:10.1177/1475921718756602.
  • [2] Y. Zhang, T. Li, and Q. Li, “Defect detection for tire laser shearography image using curvelet transform based edge detector,” Optics & Laser Technology, vol. 47, pp. 64–71, Apr. 2013, doi:10.1016/J.OPTLASTEC.2012.08.023.
  • [3] F. Braghin, M. Brusarosco, F. Cheli, A. Cigada, S. Manzoni, and F. Mancosu, “Measurement of contact forces and patch features by means of accelerometers fixed inside the tire to improve future car active control,” Vehicle System Dynamics, vol. 44, no. SUPPL. 1, pp. 3–13, 2006, doi:10.1080/00423110600867101.
  • [4] H. Zhang, S. Zhang, Y. Zhang, X. Huang, and Y. Dai, “Abrasion status prediction with BP neural network based on an intelligent tire system,” 2020 4th CAA International Conference on Vehicular Control and Intelligence, CVCI 2020, pp. 619–622, Dec. 2020, doi:10.1109/CVCI51460.2020.9338547.
  • [5] J. Zhu, K. Han, and S. Wang, “Automobile tire life prediction based on image processing and machine learning technology,” Advances in Mechanical Engineering, vol. 13, no. 3, Mar. 2021, doi: 10.1177/16878140211002727
  • [6] H. Bhanare and A. Khachane, “Quality Inspection of Tire using Deep Learning based Computer Vision,” International Research Journal of Engineering and Technology vol. 6, no.11 pp.3555-3558, 2019, [Online]. Available: www.irjet.net [Accessed: Oct. 08, 2023].
  • [7] X. Cui, Y. Liu, Y. Zhang, and C. Wang, “Tire Defects Classification with Multi-Contrast Convolutional Neural Networks,” International Journal of Pattern Recognition and Artificial Intelligence vol. 32, no. 4, Dec. 2017, doi:10.1142/S0218001418500118.
  • [8] X. Cui, Y. Liu, and C. Wang, “Defect automatic detection for tire X-ray images using inverse transformation of principal component residual,” 2016 3rd International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2016, pp. 18–25, Oct. 2016, doi:10.1109/ICAIPR.2016.7585205.
  • [9] V. H. Nguyen, D. Zheng, F. Schmerwitz, and P. Wriggers, “An advanced abrasion model for tire wear,” Wear, vol. 396–397, pp. 75–85, Feb. 2018, doi:10.1016/J.WEAR.2017.11.009.
  • [10] X. Chen, N. Xu, and K. Guo, “Tire wear estimation based on nonlinear lateral dynamic of multi-axle steering vehicle,” International Journal of Automotive Technology, vol. 19, no. 1, pp. 63–75, Feb. 2018, doi:10.1007/S12239-018-0007-2/METRICS.
  • [11] J. Siegel, R. Bhattacharyya, S. Sarma, and A. Deshpande, “Smartphone-based vehicular tire pressure and condition monitoring,” Lecture Notes in Networks and Systems, vol. 15, pp. 805–824, 2018, doi:10.1007/978-3-319-56994-9_56/COVER.
  • [12] K. Kim, H. Park, and T. Kim, “Comparison of Performance of Predicting the Wear Amount of Tire Tread Depending on Sensing Information,” Sensors 2023, Vol. 23, Page 459, vol. 23, no. 1, p. 459, Jan. 2023, doi:10.3390/S23010459.
  • [13] B. Li, Z. Quan, S. Bei, L. Zhang, and H. Mao, “An estimation algorithm for tire wear using intelligent tire concept,” Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering vol. 235, no. 10–11, pp. 2712–2725, Feb. 2021, doi:10.1177/0954407021999483.
  • [14] Y.-J. Kim, H.-J. Kim, J.-Y. Han, and S. Lee, “Classification of Tire Tread Wear Using Accelerometer Signals through an Artificial Neural Network,” Journal of the Korean Society of Industry Convergence, vol. 23, no. 2_2, pp. 163–171, 2020, doi:10.21289/KSIC.2020.23.2.163.
  • [15] T. Poloni and J. Lu, “An Indirect Tire Health Monitoring System Using On-board Motion Sensors,” SAE Technical Papers, vol. 2017-March, no. March, Mar. 2017, doi:10.4271/2017-01-1626.
Toplam 15 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Bilgisayar Yazılımı
Bölüm Araştırma Makalesi
Yazarlar

Remzi Gürfidan 0000-0002-4899-2219

Oğuzhan Kilim 0000-0003-3365-7327

Tuncay Yiğit 0000-0001-7397-7224

Bekir Aksoy 0000-0001-8052-9411

Yayımlanma Tarihi 31 Aralık 2023
Gönderilme Tarihi 17 Kasım 2023
Kabul Tarihi 29 Kasım 2023
Yayımlandığı Sayı Yıl 2023 Cilt: 9 Sayı: 4

Kaynak Göster

IEEE R. Gürfidan, O. Kilim, T. Yiğit, ve B. Aksoy, “Robustness Classification by Machine Learning from Vehicle Tire Surface Abrasions”, GMBD, c. 9, sy. 4, ss. 151–157, 2023.
 Kapak Resmi İndir

Gazi Journal of Engineering Sciences (GJES) publishes open access articles under a Creative Commons Attribution 4.0 International License (CC BY) 1366_2000-copia-2.jpg