Non-destructive detection of ceramic ball surface defects based on improved YOLOv8

• Autorzy: Gu Guo-Qing , Wang Han-Lei , Miao Xu-Yi , Yan Jing-Yi , Du Jian-Zhou

Identyfikatory

DOI

10.24425/mms.2025.152777

• Języki publikacji: EN

Abstrakty

EN

To address issues such as severe specular reflection, low detection accuracy, and large model parameters in ceramic ball detection, an improved YOLOv8 model, named YOLOv8-AP, is proposed for ceramic ball surface defects detection. Firstly, the coaxial light source is employed to reduce the specular reflection effect and an efficient image acquisition platform is established to obtain defect samples. Additionally, various data augmentation techniques are utilized to expand the dataset, and both the ADown module and an improved Powerful-IoU loss function are introduced to optimize the YOLOv8 network, significantly enhancing the detection efficiency for small target defects. Experimental results show that the proposed improved YOLOv8-AP model can achieve a mean average precision of 96.1% for the detection of the ceramic ball surface defects, which greatly enhances the defect detection accuracy compared to the traditional models and can hope to meet the intelligent and automatic detection requirements of ceramic ball detection online applications.

Słowa kluczowe

EN

defect detection; ceramic ball; YOLOv8-AP model; Powerful-IoU loss function

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2025
• Tom: Vol. 32, nr 1
• Strony: 1--18
• Opis fizyczny: Bibliogr. 32 poz., rys., tab., wykr., wzory

Twórcy

autor

Gu Guo-Qing

• School of Civil Engineering, Yancheng Institute of Technology, Yancheng 224051, China

autor

Wang Han-Lei

• School of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, China

autor

Miao Xu-Yi

• School of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, China

autor

Yan Jing-Yi

• Jiangsu Dongpu Fine Ceramic Technology Co. Ltd, Lianyungang 222000, China

autor

Du Jian-Zhou

• School of Materials Science and Engineering, Yancheng Institute of Technology, Yancheng 224051, China

Bibliografia

• [1] Wu, C., Liu, Z., Zhao, H., Yang, H., Li, X., & Ni, J. (2023). Effect of the grease thickener on tribological properties of Si3N4/GCr15 contact interface and the performance in hybrid ceramic ball bearing. Ceramics International, 49(10), 16857-16867. https://doi.org/10.1016/j.ceramint.2023.02.047
• [2] Wen, D. S., Wang, S. R., Wang, G. Q., Guo, P. Q., Yang, L. Y., & Yang, X. F. (2018). Fabrication processing and mechanical properties of Si3N4 ceramic turbocharger wheel. Ceramics International, 44(8), 10596-10603. https://doi.org/10.1016/j.ceramint.2018.03.084
• [3] Liang, H. Q., Zeng, Y. P., Zuo, K. H., Xia, X. F., Yao, D. X., & Yin, J. W. (2017). The effect of oxidation on the mechanical properties and dielectric properties of porous Si3N4 ceramic. Ceramics International, 43(6), 5517-5523. https://doi.org/10.1016/j.ceramint.2017.01.074
• [4] Fekri-Ershad, S., & Tajeripour, F. (2017). Multi-Resolution and Noise-Resistant Surface Defect Detection Approach Using New Version of Local Binary Patterns. Applied Artificial Intelligence, 31(5-6), 395-410. https://doi.org/10.1080/08839514.2017.1378012
• [5] Xing, H., Zou, B., Liu, X., Wang, X., Huang, C., & Hu, Y. (2020). Fabrication strategy of complicated Al2O3-Si3N4 functionally graded materials by stereolithography 3D printing. Journal of the European Ceramic Society, 40(15), 5797-5809. https://doi.org/10.1016/j.jeurceramsoc.2020.05.022
• [6] Yu, D., Zhu, Z., Min, J., Fang, C., Liao, D., & Wu, N. (2020). Multi-scale decomposition enhancement algorithm for surface defect images of Si3N4 ceramic bearing balls based on stationary wavelet transform. Advances in Applied Ceramics, 120(1), 47-57. https://doi.org/10.1080/17436753.2020.1858010
• [7] Ding, Y., Zhang, X., & Kovacevic, R. (2016). A laser-based machine vision measurement system for laser forming. Measurement, 82, 345-354. https://doi.org/10.1016/j.measurement.2015.10.036
• [8] Deneuville, F., Duquennoy, M., Ouaftouh; Ourak, M., Jenot, F., & Desvaux, S. (2009). High frequency ultrasonic detection of C-crack defects in silicon nitride bearing balls. Ultrasonics, 49(1), 89-93. https://doi.org/10.1016/j.ultras.2008.06.010
• [9] Li, X., Chen, L., Liu, S., Shao, M., Hu, R., Li, R., Li, Y., & An, D. (2024). A method for multi-view surface defect detection of Si3N4 ceramic bearing balls integrating features enhanced by the Gabor salient domain. Measurement Science and Technology, 35(7), 085205. https://doi.org/10.1088/1361-6501/ad4812
• [10] Zhang, K., Fu, L., Wang, Z., Sun, Y., & Liu, C. (2017). Research on surface defect detection of ceramic ball based on fringe reflection. Optical Engineering, 56(9), 1. https://doi.org/10.1117/1.oe.56.10.104104
• [11] Yu, D., Zhang, H., Zhang, X., Liao, D., & Wu, N. (2021). Si3N4 Ceramic Ball Surface Defects’ Detection Based on SWT and Nonlinear Enhancement. Mathematical Problems in Engineering, 2021, 1-9. https://doi.org/10.1155/2021/4922315
• [12] Chen, S., Wang, D.-G., & Wang, F.-B. (2022). Detecting aluminium tube surface defects by using faster region-based convolutional neural networks. Journal of Computational Methods in Sciences and Engineering, 22(4), 1711-1720. https://doi.org/10.3233/jcm-226107
• [13] Liao, D., Cui, Z., Zhu, Z., Jiang, Z., Zheng, Q., & Wu, N. (2023). A nondestructive recognition and classification method for detecting surface defects of Si3N4 bearing balls based on an optimized convolutional neural network. Optical Materials, 136, 113401. https://doi.org/10.1016/j.optmat.2022.113401
• [14] Fan, Y. B., Mao, S. J., Li, M., Wu, Z., & Kang, J. T. (2024). CM-YOLOv8: Lightweight YOLO for Coal Mine Fully Mechanized Mining Face. Sensors, 24(5), 1866. https://doi.org/10.3390/s24061866
• [15] Lv, X., Yi, H. A., Fang, R. J., Ai, S. H., & Lu, E. H. (2023). Visual detection of milling surface roughness based on improved YOLOv5. Metrology and Measurement Systems, 30(3), 531-548. https://doi.org/10.24425/mms.2023.146425
• [16] Zhu, F., Chang, C., Li, Z. H., Li, B. Q., & Li, L. (2024). A generic optimization-based enhancement method for trajectory data: Two plus one. Accident Analysis & Prevention, 200, 107532. https://doi.org/10.1016/j.aap.2024.107532
• [17] Katsampiris-Salgado, K., Dimitropoulos, N., Gkrizis, C., Michalos, G., & Makris, S. (2024). Advancing human-robot collaboration: Predicting operator trajectories through AI and infrared imaging. Journal of Manufacturing Systems, 74, 980-994. https://doi.org/10.1016/j.jmsy.2024.05.015
• [18] Wu, X., Ouyang, G., Li, B., Cui, L., & Zhou, G. (2020). Determining Line-Crossing Sequences Between Laser Printing and Writing Pen Using Coaxial Light. Journal of Forensic Sciences, 65(4), 1242-1246. https://doi.org/10.1111/1556-4029.14316
• [19] Chen, S. (2016). Inspecting lens collars for defects using discrete cosine transformation based on an image restoration scheme. IET Image Process., 10(5), 474-482. https://doi.org/10.1049/iet-ipr.2015.0780
• [20] Hejazi, A. S., Al-Hunaiti, A. H., Bsoul, I., Mohaidat, Q., & Mahmood, S. H. (2024). Optimizing the synthesis of ZnFe2O4 through chemical and physical methods: effects of the synthesis route on the phase purity, inversion, and magnetic properties of spinel zinc ferrite. Physica Scripta, 99(5), 065029. https://doi.org/10.1088/1402-4896/ad4746
• [21] Sokhan’, S. V., Maystrenko, A. L., Borimsky, A. I., Voznyy, V. V., Sorochenko, V. G., Hamaniuk, M. P., & Zubaniev, E. M. (2021). Changing the Performance of Diamond Finishing of Ceramic Balls of Boron Carbide and Silicon Nitride. Journal of Superhard Materials, 43(2), 135-144. https://doi.org/10.3103/s106345762102009x
• [22] Dua, M., Nalawade, S., & Dua, S. (2024). Underwater image enhancement by using amalgamation of colour correction, contrast-enhancing and dehazing. Physica Scripta, 99(4), 046002. https://doi.org/10.1088/1402-4896/ad2d9c
• [23] He, Z., Mo, H., Xiao, Y., Cui, G., Wang, P., & Jia, L. (2024). Multi-scale fusion for image enhancement in shield tunneling: a combined MSRCR and CLAHE approach. Measurement Science and Technology, 35(4), 056112. https://doi.org/10.1088/1361-6501/ad25e4
• [24] Ding, P., Zhan, H., Yu, J., & Wang, R. (2024). A bearing surface defect detection method based on multi-attention mechanism Yolov8. Measurement Science and Technology, 35(7), 086003. https://doi.org/10.1088/1361-6501/ad4386
• [25] Li, A. J., Xu, G. P., Yue, W. P., Xu, C. Y., Gong, C. P., & Cao, J. P. (2024). Object Detection in Hazy Environments, Based on an All-in-One Dehazing Network and the YOLOv5 Algorithm. Electronics, 13(9), 1862. https://doi.org/10.3390/electronics13101862
• [26] Xiao, B., Nguyen, M., & Yan, W. Q. (2023). Fruit ripeness identification using YOLOv8 model. Multimedia Tools and Applications, 83(8), 28039-28056. https://doi.org/10.1007/s11042-023-16570-9
• [27] Liu, C., Wang, K., Li, Q., Zhao, F., Zhao, K., & Ma, H. (2024). Powerful-IoU: More straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism. Neural Networks, 170, 276-284. https://doi.org/10.1016/j.neunet.2023.11.041
• [28] Sharen, H., Jawahar, M., Jani Anbarasi, L., Ravi, V., Saleh Alghamdi, N., & Suliman, W. (2024). FDUM-Net: An enhanced FPN and U-Net architecture for skin lesion segmentation. Biomedical Signal Processing and Control, 91, 106037. https://doi.org/10.1016/j.bspc.2024.106037
• [29] Sun, S., Mo, B., Xu, J., Li, D., Zhao, J., & Han, S. (2024). Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle. Neurocomputing, 588, 127685. https://doi.org/10.1016/j.neucom.2024.127685
• [30] Lei, D., Dong, C., Guo, H., Ma, P., Liu, H., Bao, N., Kang, H., Chen, X., & Wu, Y. (2024). A fused multi-subfrequency bands and CBAM SSVEP-BCI classification method based on convolutional neural network. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-59348-1
• [31] Huo, Y., Gang, S., Dong, L., & Guan, C. (2024). An Efficient Semantic Segmentation Method for Remote-Sensing Imagery Using Improved Coordinate Attention. Applied Sciences, 14(9), 4075. https://doi.org/10.3390/app14104075
• [32] Yang, B., Zhang, B., Han, Y., Liu, B., Hu, J., & Jin, Y. (2024). Vision transformer-based visual language understanding of the construction process. Alexandria Engineering Journal, 99, 242-256. https://doi.org/10.1016/j.aej.2024.05.015

Uwagi

This work was supported by Jiangsu Provincial Market Regulation Administration Science and Technology Project (No. KJ2024092) and Lianyungang Major Technology Research Project of Open Bidding for Selecting the Best Candidates (No. CGJBGS2202).