Tarım Makinelerinde Korozyon Tespiti için Derin Öğrenme Yöntemleri: Sistematik Derleme

Abstract

Tarım makinelerinde operasyonel verimlilik elzemdir, ancak zorlu ortamlara sürekli maruz kalmaları onları korozyona karşı oldukça hassas hale getirir. Bu bozulma, ekipman ömrünü kısaltır, bakım maliyetlerini artırır ve önemli ekonomik kayıplara yol açabilir. Geleneksel denetim yöntemleri genellikle öznel ve erken aşamadaki hasarı yakalamak için çok yavaşken, başta Evrişimli Sinir Ağları (CNN'ler) olmak üzere derin öğrenme yaklaşımları güçlü bir alternatif olarak ortaya çıkmaktadır. Bu derleme, korozyon tespiti için kullanılan bu otomatikleştirilmiş yöntemlerin mevcut durumunu incelemektedir. Mevcut literatür, CNN tabanlı sistemlerin hem kontrollü hem de endüstriyel ortamlarda %78 ile %99 arasında değişen doğruluk oranlarıyla korozyonu tespit edip sınıflandırabildiğini göstermektedir. Bu çalışmada, yaygın olarak kullanılan derin öğrenme mimarileri araştırılmakta, görsel belirsizlik ve sınırlı veri setleri gibi süregelen zorluklar tartışılmakta ve insansız hava araçları (dronlar) ve hiperspektral görüntüleme ile entegrasyon gibi gelecekteki araştırma yönelimlerine değinilmektedir. Nihai hedefin, tarım sektöründe gerçek anlamda kestirimci bakım için bir temel oluşturmak olduğu görülmektedir.

Keywords

• korozyon
• derin öğrenme
• tarım makinesi
• kestirimci bakım

Deep Learning Methods for Corrosion Detection on Agricultural Machinery: A Review

Abstract

Agricultural machinery is essential for operational efficiency, but its constant exposure to harsh environments makes it highly susceptible to corrosion. This degradation shortens equipment lifespan, drives up maintenance costs, and can lead to significant economic losses. While traditional inspection methods are often subjective and too slow to catch early-stage damage, deep learning approaches, particularly Convolutional Neural Networks (CNNs), are emerging as a powerful alternative. This review examines the current state of these automated methods for corrosion detection. The existing literature suggests that CNN-based systems can indeed detect and classify corrosion, with reported accuracy rates often falling between 78% and 99% in both controlled and industrial settings. We explore the deep learning architectures commonly used, discuss persistent challenges like visual ambiguity and limited datasets, and look ahead to future research directions, including integration with drones and hyperspectral imaging. The ultimate goal, it seems, is to build a foundation for truly predictive maintenance in the agricultural sector.

Keywords

• Corrosion
• Deep Learning
• Agricultural Machinery
• PdM

References

1. Achouch, M., Dimitrova, M., Ziane, K., Sattarpanah Karganroudi, S., Dhouib, R., Ibrahim, H., Adda, M., 2022. On predictive maintenance in Industry 4.0: Overview, models, and challenges. Applied Sciences. 12(16), 8081. https://doi.org/10.3390/app12168081
2. Alsaeed, T., Alajmi, A.E., Alotaibi, J.G., Yousif, B.F., Abdo, H., 2023. Investigation on three-body abrasion resistance of mild steel soil slurry condition simulating agricultural condition. Advances in Materials Science and Engineering. 2023, 5616909. https://doi.org/10.1155/2023/5616909
3. Bhowmik, S., 2021. Digital twin for offshore pipeline corrosion monitoring: a deep learning approach. Offshore Technology Conference. https://doi.org/10.4043/31296-ms
4. Çınar, Z.M., Abdussalam Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., Safaei, B., 2020. Machine learning in predictive maintenance towards sustainable smart manufacturing in Industry 4.0. Sustainability. 12(19), 8211. https://doi.org/10.3390/su12198211
5. Dalal, M., Mittal, P., 2025. A systematic review of deep learning-based object detection in agriculture: Methods, challenges, and future directions. Computers, Materials & Continua. 84(1), 57-91. https://doi.org/10.32604/cmc.2025.066056
6. Effendi, M., Atmaja, B., Wahjudi, A., Purwanto, D., 2023. Automated corrosion detection on steel structures using convolutional neural network. The International Journal of Mechanical Engineering and Sciences. 7(1), 36. https://doi.org/10.12962/j25807471.v7i1.15881
7. Ferguson, M., Ak, R., Lee, Y.T.T., Law, K.H., 2018. Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning. Smart and Sustainable Manufacturing Systems. 2(1), 137-164. https://doi.org/10.1520/SSMS20180033
8. Forkan, A.R.M., Kang, Y.B., Jayaraman, P.P., Liao, K., Kaul, R., Morgan, G., Ranjan, R., Sinha, S., 2022. CorrDetector: A framework for structural corrosion detection from drone images using ensemble deep learning. Expert Systems with Applications. 193, 116461. https://doi.org/10.1016/j.eswa.2021.116461

9. Idusuyi, N., Samuel, O., Olugasa, T., Ajide, O., Abu, R., Ajayi, O., 2022. Corrosion classification study of mild steel in 3.5% NaCl using convolutional neural networks. Fuoye Journal of Engineering and Technology. 7(1). https://doi.org/10.46792/fuoyejet.v7i1.773
10. Khayatazad, M., Honhon, M., De Waele, W., 2022. Detection of corrosion on steel structures using an artificial neural network. Structure and Infrastructure Engineering. 19(12), 1860-1871. https://doi.org/10.1080/15732479.2022.2069272
11. Kofoed, M., Jepsen, J.S., Jensen, R.L., Moeslund, T.B., 2019. Investigating deep learning architectures towards autonomous inspection for marine classification. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 3749-3756. https://doi.org/10.1109/IROS40897.2019.8968536
12. Lavadiya, D.N., Sajid, H.U., Yellavajjala, R.K., Sun, X., 2022. Hyperspectral imaging for the elimination of visual ambiguity in corrosion detection and identification of corrosion sources. Structural Health Monitoring. 21(4), 1678-1693. https://doi.org/10.1177/14759217211041690
13. Malashin, I., Tynchenko, V., Nelyub, V., Borodulin, A., Gantimurov, A., Krysko, N.V., Shchipakov, N.A., Kozlov, D.M., Kusyy, A.G., Martysyuk, D., Galinovsky, A., 2024. Deep learning approach for pitting corrosion detection in gas pipelines. Sensors. 24(11), 3563. https://doi.org/10.3390/s24113563
14. Nash, W., Zheng, L., Birbilis, N., 2022. Deep learning corrosion detection with confidence. NPJ Materials Degradation. 6(1). https://doi.org/10.1038/s41529-022-00232-6
15. Pacal, I., Kunduracioglu, I., Alma, M.H., Deveci, M., Kadry, S., Nedoma, J., Slany, V., Martinek, R., 2024. A systematic review of deep learning techniques for plant diseases. Artificial Intelligence Review. 57, 304. https://doi.org/10.1007/s10462-024-10944-7
16. Revie, R.W., Uhlig, H.H., 2008. Corrosion and corrosion control: An introduction to corrosion science and engineering. 4th ed. John Wiley & Sons, New Jersey.
17. Saeed, F., Olmeda, D., Al-Hmouz, R., Al-Hmouz, A., 2025. A scoping review of texture analysis techniques for corrosion detection and monitoring. World Journal of Advanced Research and Reviews. 25(2), 2269-2284. https://doi.org/10.30574/wjarr.2025.25.2.2524
18. Thomas, D., Gündel, M., Noel, S., Zehn, M., 2023. Hyperspectral imaging systems for corrosion detection from remotely operated vehicles. ce/papers. 6(5), 542-547. https://doi.org/10.1002/cepa.2132
19. Yang, X., Guo, R., Li, H., 2023. Comparison of multimodal RGB-thermal fusion techniques for exterior wall multi-defect detection. Journal of Infrastructure Intelligence and Resilience. 2(2), 100029. https://doi.org/10.1016/j.iintel.2023.100029
20. Yu, J., 2025. Binary classification of marine corrosion using deep learning: a benchmark study on the full marine_corrosion_dataset. Preprint. https://doi.org/10.21203/rs.3.rs-7190234/v1
21. Yu, L., Yang, E., Luo, C., Ren, P., 2021. AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection. Journal of Ambient Intelligence and Humanized Computing. 14(7), 8087-8098. https://doi.org/10.1007/s12652-021-03580-4