THERMAL SCIENCE

International Scientific Journal

Xiuzhuang Mei

,

Xingtan Wang

,

Gang Xu

,

Ying Wang

ENHANCED YOLOV8-BASED DETECTION OF SURFACE DAMAGES ON CONVEYOR BELTS WITH IMPROVED ACCURACY AND EFFICIENCY

ABSTRACT
Damage to the surface of composite conveyor belts is a prevalent issue that can lead to functional failure. In this study, the YOLOv8 algorithm is enhanced. The convolutional block attention module attention mechanisms and deformable convolutions are introduced, and a small-object detection layer is added. The Focaler-CIoU loss function is also employed. These enhancements are designed to enhance the recognition of damage. In the context of complex operational conditions, the findings indicate a mean recognition accuracy of 93.8% for conveyor belt surface damage, thereby substantiating the efficacy of the enhanced algorithm.
KEYWORDS
conveyor belt, surface damage, YOLOv8, attention mechanism
PAPER SUBMITTED: 2024-10-26
PAPER REVISED: 2025-03-28
PAPER ACCEPTED: 2025-04-01
PUBLISHED ONLINE: 2026-04-12
DOI REFERENCE: https://doi.org/10.2298/TSCI2602919M
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2026, VOLUME 30, ISSUE No. 2, PAGES [919 - 927]
REFERENCES
[1] Mei, L. S., et al., An On-Line Detection Method for Conveyor Belt Deviation Faults, Thermal Science, 27 (2023), 3A, pp. 2099-2107
[2] Mei, M. Y., et al., On-Line Intelligent Evaluation of the Fatigue State of a Composite Conveyor Belt, Thermal Science, 25 (2021), 3B, pp. 2191-2198
[3] Zhang, M., et al., Deep Learning-Based Damage Detection of Mining Conveyor Belt, Measurement, 175 (2021), Apr., pp. 109-130
[4] Wang, G. L., et al., Multi-View Detection Method for Longitudinal Tear of Conveyor Belt Based on Improved YOLOv3, Journal of Hefei University of Technology (Natural Science), 46 (2023), 1, pp. 28-35+80
[5] Guo, X., et al., Damage Detection for Conveyor Belt Surface Based on Conditional Cycle Generative Adversarial Network, Sensors (Basel), 22 (2022), 9, pp. 1-17
[6] Zhang, et al., Damage Detection Method for Mine Conveyor Belt Based on Deep Learning, Industry and Mine Automation, 47 (2021), 6, pp. 51-56
[7] Qing, L., et al., Longitudinal Tear Detection Based on Improved YOLOv4 for Conveyor Belt, Computer System Applications, 32 (2023), 3, pp. 186-194
[8] Wang, Y. M., et al., Longitudinal Tear Detection of Conveyor Belt Based on Improved YOLOv7, Ieee Access, 12 (2024), Feb., pp. 24453-24464
[9] Li, et al., YOLOv8 Ship Target Detection Algorithm Based on CCA and Transformer, Control Engineering of China, 31 (2024), 5, pp. 1-12
[10] Yang, L. J., et al., Wear State Detection of Conveyor Belt in Underground Mine Based on Retinex-YOLOv8-EfficientNet-NAM, Ieee Access, 12 (2024), Feb., pp. 25309-25324
[11] Wang, et al., Research on Pedestrian Detection Algorithm Based on Mixed Attention Mechanism and C2f, Software Guide, 23 (2024), 1, pp. 135-142
[12] Woo, S., et al. CBAM: Convolutional Block Attention Module, Proceedings, 15th European Conference on Computer Vision (ECCV), Munich, Germany, Vol. 11211, 2018, pp. 3-19
[13] He, J. H. Transforming Frontiers: The Next Decade of Differential Equations and Control Processes. Advances in Differential Equations and Control Processes, 32 (2025), 1, 2589
[14] Nosonovsky, M., Aglikov, A. S., Triboinformatics: Machine Learning Methods for Frictional Instabilities, Facta Universitatis, Series Mechanical Engineering 22 (2024), 3, pp. 423-433
[15] Cao, Y. J., et al. Study of Friction Compensation Model for Mobile Robot's Joints, Facta Universitatis, Series Mechanical Engineering, 22 (2024), 4, pp. 721-740
[16] Karim, F. K., et al., Innovative Mathematical Modelling Approaches to Diagnose Chronic Neurological Disorders with Deep Learning, Thermal Science, 28 (2024), 6B, pp. 5217-5229
[17] Chen, Z. P., et al., Multi-Role Collaborative Framework for Structural Damage Identification Considering Measurement Noise Effect, Measurement, 250 (2025), 117106
[18] Guan, Y. Z., et al., Variational Formulations for a Coupled Fractal-Fractional KdV System, Fractals, 32 (2024), 2450054
[19] Li, X. X., et al., Elucidating the Fractal Nature of the Porosity of Nanofiber Members in the Electrospinning Process, Fractals, 32 (2024), 2450109
[20] Liu, Y. P., et al., Leveraging Lotus Seeds' Distribution Patterns for Fractal Super-Rope Optimization, Fractals, 33 (2025), 2450143
[21] Liu, Y. P., et al., Clover-Inspired Fractal Architectures: Innovations in Flexible Folding Skins for Sustainable Buildings, Fractals, 33 (2025), 2550041
PDF VERSION [DOWNLOAD]
Enhanced YOLOv8-based detection of surface damages on conveyor belts with improved accuracy and efficiency

© 2026 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence