Research on ore fragmentation recognition method based on deep learning

• Autorzy: Jing Hongdi , He Wenxuan , Yu Miao , Li Xin , Zhang Xingfan , Liu Xiaosong , Cui Yang , Wang Zhijian

Identyfikatory

DOI

10.24425/ams.2024.151445

• Języki publikacji: EN

Abstrakty

EN

The degree of ore fragmentation in mining sites is closely related to crushing efficiency, equipment safety, beneficiation efficiency, and mining costs. Aiming to address the challenges of high labour intensity and low accuracy during manual ore fragmentation measurement at the mine site, this paper proposes a method for ore fragmentation recognition based on deep learning. This method not only uses the residual neural network structure to form the backbone feature extraction network of CSPDarkNet21 under the Darknet framework but also selects the simple two-way fusion feature PANet as the feature extraction network under the condition of only needing to identify large ore. PANet is simplified from three feature layers to one feature layer, which speeds up model training and prediction. The research results show that with a 6% decrease in accuracy, the model training time is reduced by 13 times, and the model running efficiency is improved by 21.2 times, significantly shortening the model development time. At the same time, CIOU calculates the loss value to make model training more stable. After the ore identification is completed, the real size of the ore can be obtained by calculating the pixel area of the prediction frame using the ore fragmentation judgement method.

Słowa kluczowe

EN

underground mines; ore fragmentation; visual identity; recognition; deep learning

PL

ruda żelaza; pękanie skały; wysadzanie skał

• Wydawca: Instytut Mechaniki Górotworu PAN
• Czasopismo: Archives of Mining Sciences
• Rocznik: 2024
• Tom: Vol. 69, no. 3
• Strony: 447--459
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Jing Hongdi

• Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang 110016, China
• Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Shenyang 110169, China

• https://orcid.org/0000-0001-8893-1923

autor

He Wenxuan

• Ansteel Group Mining Corporation Limited, Anshan 114001, China

autor

Yu Miao

• Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang 110016, China
• Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Shenyang 110169, China

• https://orcid.org/0000-0003-1346-6638

autor

Li Xin

• Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang 110016, China
• Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Shenyang 110169, China

autor

Zhang Xingfan

• Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang 110016, China
• Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Shenyang 110169, China

autor

Liu Xiaosong

• Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang 110016, China
• Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Shenyang 110169, China

autor

Cui Yang

• Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang 110016, China
• Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Shenyang 110169, China

autor

Wang Zhijian

• Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang 110016, China
• Chinese Academy of Sciences, Institutes for Robotics and Intelligent Manufacturing, Shenyang 110169, China

Bibliografia

• [1] M. Mohebbi, A.R. Yarahmadi Bafghi, M. Fatehi Marji, J. Gholamnejad, Rock mass structural data analysis using image processing techniques (Case study: Choghart iron ore mine northern slopes). Journal of Mining and Environment8 (1), 61-74 (2017). DOI: https://doi.org/10.22044/JME.2016.629.
• [2] H. Haeri, K. Shahriar, M.F. Marji, P. Moarefvand, A coupled numerical – experimental study of the breakage process of brittle substances. Arabian Journal of Geosciences 8, 809-825 (2015).DOI: https://doi.org/10.1007/s12517-013-1165-1.
• [3] M. Fatehi Marji, Modelling of cracks in rock fragmentation with a higher order displacement discontinuity method.PhD Thesis 1 (1), METU, Ankara, Turkey (1996).
• [4] M. Lak, M.F. Marji, A.Y. Bafghi, A. Abdollahipour, Analytical and numerical modelling of rock blasting operationsusing a two-dimensional elasto-dynamic Green’s function. International Journal of Rock Mechanics and MiningSciences 114, 208-217 (2019). DOI: https://doi.org/10.1016/j.ijrmms.2018.12.022.
• [5] H.C. Bazame, J.P. Molin, D. Althoff, et al., Detection, classification, and mapping of coffee fruits during harvestwith computer vision. Computers and Electronics in Agriculture 183 (2021).DOI: https://doi.org/10.1016/j.compag.2021.106066.
• [6] K. Chen, Z. Zeng, J. Yang, A deep region-based pyramid neural network for automatic detection and multiclassification of various surface defects of aluminium alloys. Journal of Building Engineering 43, 102523 (2021).
• [7] W. Chen, X. Zhong, J. Zhang, Optimization Research and Defect Object Detection of Aeroengine Blade BossBased on YOLOv4. Journal of Physics: Conference Series 1746 (1), 012076 (2021).DOI: https://doi.org/10.1088/1742-6596/1746/1/012076.
• [8] R . Cheng, X. He, Z. Zheng, et al., Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny. Applied Sciences 11 (8), 3652 (2021). DOI: https://doi.org/10.3390/app11083652.
• [9] X . Cui, C. Zou, Z. Wang, Remote sensing image recognition based on dual-channel deep learning network. MultimediaTools and Applications 80 (18), 27683-27699 (2021). DOI: https://doi.org/10.1007/s11042-021-11079-5.
• [10] H. Deng, J. Cheng, T. Chen, et al., Research on Iron Surface Crack Detection Algorithm Based on Improved YOLOv4Network. Journal of Physics: Conference Series (2020). DOI: https://doi.org/10.1088/1742-6596/1631/1/012081.
• [11] N.J. Francis, N.S. Francis, S.V. Axyonov, et al., Diagnostic of Cystic Fibrosis in Lung Computer Tomographic Images using Image Annotation and Improved PSPNet Modelling. Journal of Physics Conference Series 1611,012062 (2020). DOI: https://doi.org/10.1088/1742-6596/1611/1/012062.
• [12] D. Jiang, G. Li, C. Tan, et al., Semantic segmentation for multiscale targets based on object recognition using theimproved Faster-RCNN model. Future Generation Computer Systems 123 (2021).DOI: https://doi.org/10.1016/j.future.2021.04.019.
• [13] C. Liu, M. Li, Y. Zhang, et al., An Enhanced Rock Mineral Recognition Method Integrating a Deep Learning Model and Clustering Algorithm. Minerals 9 (9), 516 (2019). DOI: https://doi.org/10.3390/min9090516.
• [14] H. Liu, K. Fan, Q. Ouyang, et al., Real-time small drones detection based on pruned yolov4. Sensors 21 (10), 3374(2021). DOI: https://doi.org/10.3390/s21103374.
• [15] X . Liu, Y. Zhang, H. Jing, et al., Ore image segmentation method using U-Net and Res_Unet convolutional networks.The Royal Society of Chemistry 16, (2020). DOI: https://doi.org/10.1039/C9RA05877J.
• [16] S.A. Magalhães, L. Castro, G. Moreira, et al., Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse 21 (10), 3569 (2021).DOI: https://doi.org/10.48550/arXiv.2109.00810.
• [17] M. Młynarczuk, A. Górszczyk, B. Ślipek, The application of pattern recognition in the automatic classification of microscopic rock images. Computers & Geosciences 60, 126-133 (2013).DOI: https://doi.org/10.1016/j.cageo.2013.07.015.
• [18] B. Nigam, A. Nigam, R. Jain, et al., COVID-19: Automatic detection from X-ray images by utilising deep learningmethods. Expert Systems with Applications 176, 114883 (2021).
• [19] S.T. Ishikawa, V.C. Gulick, An automated mineral classifier using Raman spectra. Computers & Geosciences 54,259-268 (2013). DOI: https://doi.org/10.1016/j.cageo.2013.01.011.
• [20] H. Wang, M. Lei, Y. Chen, et al., Intelligent Identification of Maceral Components of Coal Based on Image Segmentation and Classification. Applied Sciences 9 (16), 3245 (2019). DOI: https://doi.org/10.3390/app9163245.
• [21] Y. Zhang, M. Li, S. Han, et al., Intelligent Identification for Rock-Mineral Microscopic Images Using Ensemble Machine Learning Algorithms. Sensors 19 (18), 3914 (2019). DOI: https://doi.org/10.3390/s19183914.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025)