DIAGNOSIS OF CONVEYOR EQUIPMENT USING NEURAL NETWORK ALGORITHMS
In the context of the widespread implementation of intelligent monitoring and diagnostic systems, computer vision becomes one of the leading tools, enabling effective solutions for optimizing maintenance and enhancing the reliability of industrial equipment. This article explores the main methods and approaches for using computer vision to assess the technical condition of conveyor equipment, analyzes the advantages and disadvantages of existing diagnostic systems, and suggests possible directions for further research.
The operation of belt conveyors determines the functioning of the entire production process. Conveyors ensure the continuous supply of raw materials to the next production stage, thus moving materials to subsequent processing stages or the finished product warehouse. Most conveyor equipment in the metallurgy industry features conveyors with rubber belts. The average lifespan of a conveyor belt is one to two years. The durability of the belt depends on the response time of the maintenance team to emerging surface damage. Considering the high failure rate of conveyor equipment for the transportation and processing of petroleum coke, enhancing the reliability of the conveyor belt is a priority and especially pertinent task in production.
The methods discussed in the article, based on computer vision algorithms, address the challenges of classification, detection, and segmentation of various conveyor belt defects.
Krinitsin P.G., Chentsov S.V. Diagnosis of conveyor equipment using neural network algorithms // Research result. Information technologies. – Т.10, №2, 2025. – P. 84-92. DOI: 10.18413/2518-1092-2025-10-2-0-8
While nobody left any comments to this publication.
You can be first.
1. AC-SNGAN: Multi-class data augmentation for damage detection of conveyor belt surface using improved ACGAN / G. Wang, Z. Yang, H. Sun [et al.] // Measurement. – 2024. – Vol. 224. – P. 113814.
2. Computational approaches to Explainable Artificial Intelligence: Advances in theory, applications and trends / J. M. Górriz, I. Álvarez-Illán, A. Álvarez-Marquina [et al.] // Information Fusion. – 2023. – Vol. 100. – P. 101945.
3. Ivanov K.V. Advantages of computer vision / K.V. Ivanov, N. D. Astafiev // Current Problems of Aviation and Cosmonautics: Proceedings of the 8th International Scientific and Practical Conference dedicated to Cosmonautics Day: in 3 volumes, Krasnoyarsk, April 11–15, 2022. Volume 2. – Krasnoyarsk: Federal State Budgetary Educational Institution of Higher Education "Siberian State University of Science and Technology named after academician M. F. Reshetnev", 2022. – P. 401-403 (in Russian).
4. Bozma H.I., Yalçın H. Visual processing and classification of items on a moving conveyor: a selective perception approach Robot. Comput.-Integr. Manuf. – 2002. – Vol. 18 (2). – P. 125-133.
5. Zhang M., Shi H., Zhang Y., Yu Ya., Zhou M. Deep learning-based damage detection of mining conveyor belt // Measurement. – 2021. – Vol. 175. – P. 109-130.
6. Proactive measures to prevent conveyor belt failures: deep learning-based faster foreign object detection / M. Zhang, Yu. Cao, K. Jiang et al. // Engineering Failure Analysis. – 2022. – Vol. 141. – P. 106 - 653.
7. Lyakhovich V.A. Dust suppression and anti-freeze composition for coke from secondary processing products of petroleum raw materials / V.A. Lyakhovich, Yu.A. Bulavka // Science. Technology. Production – 2019: Materials of the International Scientific and Technical Conference dedicated to the 100th anniversary of the Republic of Bashkortostan, Salavat, April 15–19, 2019. – Salavat: Ufa State Petroleum Technological University, 2019. – P. 59-61 (in Russian).
8. Koroleva A.M. Characterization of the role of the human factor in the analysis of accident causes at hazardous production facilities / A.M. Koroleva, K.I. Drobinin, L.B. Khayrullina // Economics and Entrepreneurship. – 2021. – No. 11(136). – P. 1399-1404 (in Russian).
9. Kabanova V.V., Logunova O.S. Application of artificial intelligence in working with multimedia information // Herald of Cherepovets State University. 2022. No. 6 (111). P. 23–41 (in Russian).
10. Augmentation of image datasets for training neural networks in semantic segmentation tasks / I.A. Lozhkin, M.E. Dunaev, K.S. Zaitsev, A.A. Garmash // International Journal of Open Information Technologies. – 2023. –
Vol. 11, No. 1. – P. 109-117 (in Russian).
11. PyTorch: An Imperative Style, High Performance Deep Learning Library / Paszke A., Gross S., Massa F. and others. // Advances in Neural Information Processing Systems 32, Curran Associates, Inc., 2019. – P. 8024-8035.
12. Chernikov A.D. Forecasting and recognizing objects in video streams using deep learning / A.D. Chernikov // Science Bulletin. – 2023. – Vol. 2, No. 9(66). – P. 209-215 (in Russian).
13. Review of modern tools for marking digital diagnostic images / Yu.A. Vasiliev, E.F. Savkina, A.V. Vladzimirskiy et al. // Kazan Medical Journal. – 2023. – Vol. 104, No. 5. – P. 750-760 (in Russian).
14. Neural network algorithm for real-time full-frame recognition of surface objects / V.A. Bondarenko, V.A. Pavlova, V.A. Tupikov, N. G. Kholod // Southern Federal University Proceedings. Technical Sciences. – 2020. – No. 1(211). – P. 188-199 (in Russian).
15. Object segmentation with a retraining function / I.D. Nenakhov, K. Artemov, S. Zabihifar, A.N. Semochkin, S.A. Kolyubin // Proceedings of Higher Educational Institutions. Instrumentation. 2022. Vol. 65, No. 3. P. 194 – 203 (in Russian).
16. He K, Gkioxari G, Dollár P, Girshick R. MaskR-CNN Electronic resource. URL: https://arxiv.org/abs/1703.06870 (Access date:15.08.2024)
17. Andrianov N.A. Object detection in images: from Bayes and Neyman-Pearson criteria to neural network-based detectors EfficientDet / N.A. Andrianov, V.E. Dementiev, A.G. Tashlinsky // Computer Optics. – 2022. –
Vol. 46, No. 1. – P. 139-159 (in Russian).
18. Streltsov, D.N. Algorithm for object detection in video images with calculation of the areas of detected contours / D.N. Streltsov // Proceedings of Tula State University. Technical Sciences. – 2012. – No. 11-2. –
P. 116-122.19.
19. Tien N.T. A literature review of ERP system, challenges and opportunities of ERP implementation on organization / N.T. Tien, T.T. Tâm // TẠP CHÍ KHOA HỌC TRƯỜNG ĐẠI HỌC QUỐC TẾ HỒNG BÀNG. – 2023. – Vol. 4. – P. 35-44.
20. Martell F., López J.M., Sánchez I.Yo., Paredes C.A., Pisano E. Evaluation of the degree of automation and digitalization using a diagnostic and analysis tool for a methodological implementation of Industry 4.0 / Computers & Industrial Engineering Volume 177, March 2023, 109097.