REVIEW PAPER
Modeling and simulation of vibrating ore drawing process based on visual perception and model predictive control
1
Beijing General Research Institute of Mining and Metallurgy
2
BGRIMM Technology Group
3
Teacher’s College of Beijing UnionUniversity, Ling Juan Huang
4
Beijing General Research Institute of Mining and Metallurgy; Hangzhou Institute of Technology of Xidian University
5
China Nonferrous Metals Industry Technology Development Company
6
Zhongse Asset Management Co., Ltd.
Submission date: 2024-12-26
Final revision date: 2025-03-11
Acceptance date: 2025-07-11
Publication date: 2026-03-31
Gospodarka Surowcami Mineralnymi – Mineral Resources Management 2026;42(1):163-183
KEYWORDS
TOPICS
ABSTRACT
For modelling and control of the Vibrating Ore Drawing Process (VODP) in the under-mine rail transportation, a visual perception-based detection method for controlled variables in the drawing process is proposed and applied to the Model Predictive Control for achieving the adaptive draw of the chute. First, the method for estimating ore flow parameters is proposed based on a neural network visual perception method. The neural network-based target detection algorithm is constructed by the well-known DarkNet-53 structure, which is further optimized based on the YOLOv5-MINE structure. Second, the reference model of the VODP system is established by the system identification and data fitting approach. Then, based on this, we use model predictive control to control the system and give a stability analysis of the system with the input and output block diagram under the guidance of the prediction model. Finally, combined with advanced communication technology, simple simulation examples and practical industrial applications are given to illustrate the effectiveness and robustness of the proposed methodology. Field experiments conducted at an iron ore mine in China show that the application of the Visual Perception and Model Predictive Control system eliminates inefficiencies caused by human factors, resulting in a 6.8% increase in ore loading efficiency and a reduction in the need for operators by more than 50%. The proposed system provides a significant advancement in intelligent and unmanned mining operations, enhancing safety, efficiency, and resource utilization.
FUNDING
This work was jointly supported by the National Key R&D Program of China (No. 2023YFC2907400).
CONFLICT OF INTEREST
The Authors have no conflict of interest to declare.
METADATA IN OTHER LANGUAGES:
Polish
Modelowanie i symulacja procesu wibracyjnego wyciągania rudy w oparciu o percepcję wizualną i sterowanie predykcyjne
inteligentne górnictwo, proces wibracyjnego wydobycia rudy, detekcja obrazu, MPC
W celu modelowania i sterowania procesem wibracyjnego wydobycia rudy (VDOP) w podziemnym transporcie kolejowym zaproponowano metodę detekcji zmiennych kontrolowanych w procesie wydobycia, opartą na percepcji wizualnej, i zastosowano ją do sterowania predykcyjnego modelu w celu uzyskania adaptacyjnego wydobycia zsypu. Najpierw zaproponowano metodę szacowania parametrów przepływu rudy opartą na metodzie percepcji wizualnej z wykorzystaniem sieci neuronowej. Algorytm detekcji celu oparty na sieci neuronowej został skonstruowany w oparciu o znaną strukturę DarkNet-53, która została dodatkowo zoptymalizowana w oparciu o strukturę YOLOv5-
MINE. Następnie model referencyjny systemu VDOP został ustalony poprzez identyfikację systemu i dopasowanie danych. W dalszej kolejności na tej podstawie wykorzystano sterowanie predykcyjne oparte na modelu do sterowania systemem i przeprowadzono analizę stabilności systemu za pomocą schematu blokowego wejścia i wyjścia, korzystając z modelu predykcyjnego. Na koniec, w połączeniu z zaawansowaną technologią komunikacyjną, przedstawiono proste przykłady symulacji i praktyczne zastosowania przemysłowe, aby zilustrować skuteczność i solidność proponowanej metodologii. Eksperymenty terenowe przeprowadzone w kopalni rudy żelaza w Chinach pokazują, że zastosowanie systemu percepcji wizualnej i sterowania predykcyjnego opartego na modelu eliminuje nieefektywność spowodowaną czynnikiem ludzkim, co przekłada się na 6-procentowy wzrost wydajności załadunku rudy i zmniejszenie zapotrzebowania na operatorów o ponad 50%. Proponowany system zapewnia znaczący postęp w inteligentnych i bezzałogowych operacjach górniczych, zwiększając bezpieczeństwo, wydajność i wykorzystanie zasobów.
REFERENCES (21)
1.
Du et al. 2023 – Du, Y., Zhang, H., Liang, L., Zhang, J. and Song, B. 2023. Applications of machine vision in coal mine fully mechanized tunneling faces: A review. IEEE Access 11, pp. 102871–102898, https://doi.org/10.1109/ACCESS....
2.
Kong, X.B. and Liu, X.J. 2014. Efficient Nonlinear Model Predictive Control for Permanent Magnet Synchronous Motor. Acta Automatica Sinica 40(9), pp. 1958–1966, https://dx.doi.org/10.3724/SP.....
3.
Li et al. 2020 – Li, C., Feng, J., Hu, L., Li, J. and Ma, H. 2020. Review of Image Classification Method Based on Deep Transfer Learning. 16th International Conference on Computational Intelligence and Security (CIS), https://doi.org/10.1109/CIS520....
4.
Liu, X.M. et al. 2023. Development and application of fully automatic unmanned driving ofelectric locomotive in Fankou lead-zinc mine. Nonferrous Metals (Mining Section) 75(6), https://dx.doi.org/10.3969/j.i... (in Chinese).
5.
Miao, F.F. 2020. Analysis of underground trackless transportation transformation. Energy and energy conservation 5.
6.
Pu, L. and Zhang, X.J. 2021. UAV visual target detection and tracking based on deep learning. Journal of Beijing University of Aeronautics and Astronautics 1(12).
7.
Qin, S.J. and Badgwell, T.A. 2003. A survey of industrial model predictive control technology. Control Engineering Practice 11(7), pp. 733−764, https://doi.org/10.1016/S0967-....
8.
Redmon et al. 2016 – Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. 2016. You Only Look Once: Unified, Real-Time Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), https://doi.org/10.1109/CVPR.2....
9.
Shen et al. 2021 – Shen, K., Ji, L., Zhang, Y.H. and Zou, S. 2021. Research on coal and gangue detection algorithm based on improved YOLOv5s model. Industrial and Mining Automation 47(11).
10.
Song, X.N. 2021. Research on traffic sign detection technology based on YOLOv3 network. Northeast Electric Power University, https://doi.org/10.1088/1742-6....
11.
Wang et al. 2024 – Wang, J.C, Li, Y.S., Li, L.H., Zhang, J. and Wei, W. 2024. Research progress on intelligent coal caving theory and technology. Journal of Mine Automation 50(9), https://doi.org/10.13272/j.iss....
12.
Wang et al. 2022 – Wang, J.C., Pan, W.D., Zhang, G.Y., Yang, S., Yang, K. and Li, L. 2022. Principles and applications of image-based recognition of withdrawn coal and intelligent control of draw opening in longwall top coal caving face. Meitan Xuebao/Journal of the China Coal Society 47(1), https://doi.org/10.13225/j.cnk....
13.
Wei et al. 2024 – Wei, D., Wang, P., Wang, Z., Si, L., Zou, X., Gu, J., Dai, J. and Long, C. 2024. Adaptive Image Enhancement Method for Coal-Mine Underground Image Based on No-Reference Quality Evaluation. IEEE Transactions on Instrumentation and Measurement 73, https://doi.org/10.1109/TIM.20....
14.
Wu et al. 2000. Digital earth, digital China and digital mining area. Mine survey 1.
15.
Xi et al. 2013 – Xi, Y.G., Li, D.W. and Lin, S. 2013. Model Predictive Control – Current Situation and Challenges. Acta Automatica Sinica 39(3), https://doi.org/10.1016/S1874-....
16.
Yang, Y.Y. 2006. Research and Application of Model Predictive Control. Daqing: Daqing Petroleum Institute.
17.
Yang et al. 2019 – Yang, W.L., Ma, B.L. and Chen, C. 2019. A Method of Measuring the Ore Carrying Capacity of Hopper based on Depth Camera. China Tungsten Industry 34(6).
18.
Zhang et al. 2016 – Zhang, L., Lin, L., Liang, X. and He, K. 2016. Is faster R-CNN doing well for pedestrian detection? Computer Vision and Pattern Recognition, https://doi.org/10.48550/arXiv....
19.
Zhang et al. 2022 – Zhang, Y.P., Wu, F.J. and Guo,Y. 2022. Mine-Loading Measurement System of Underground Locomotive Based on Image Recognition. Gold Science and Technology 30(1), https://doi.org/10.11872/j.iss....
20.
Zheng et al. 2020 – Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R. and Ren, D. 2020. Distance-loU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence 34(7), https://doi.org/10.1609/aaai.v....
21.
Zheng et al. 2014 – Zheng, Z.D, Chen, N.N. and Li, Y.D. 2014. A novel field weakening control method for asynchronous motors based on model predictive control. Journal of Electrical Engineering 29(3), https://doi.org/10.3969/j.issn....
| eISSN: | 2299-2324 |
| ISSN: | 0860-0953 |
© 2006-2026 Journal hosting platform by Bentus
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
