Driven by the global energy transition and industrial intelligence, the mining industry is evolving towards smarter and more efficient methods. In mineral processing, particularly flotation, traditional techniques rely heavily on human experience, facing challenges due to complexity and variability. This study proposes an intelligent control system based on machine vision for spodumene flotation. It introduces an improved YOLOv11-M model with real-time foam detection and decision optimization, enhancing flotation efficiency. The research utilizes a dataset of over 100000 foam images and deep learning to detect foam states. Innovations include using EfficientNetV2 for feature extraction, the C3k2_LGP module for enhanced frequency perception, and the Saga-PIoU loss function for better robustness under complex conditions. Experimental results show improvements in mean average precision (mAP) (by 1.9%), precision (0.3%), and recall (2.5%). YOLOv11-M outperforms other models, with a significant frames per second (FPS) increase (135.3) and improved accuracy. A semi-industrial trial demonstrated YOLOv11-M’s ability to enhance flotation recovery and grade. Not only did the grade improve, but the flotation process’s stability was also significantly enhanced. The foam velocity distribution became more reasonable, and the fluctuations in grade and recovery were significantly reduced, with standard deviations decreasing by 65% and 90%, respectively. These findings indicate that YOLOv11-M not only improves the efficiency and stability of the flotation process but also provides an intelligent, automated solution for the industry, with the potential for widespread application in large-scale mining flotation processes. The open-source code and dataset will be released at: https://github.com/users/ytyyty368-arch.
| [1] |
Cao KZ, Wang ST, He YN, Ma JH, Yue ZW, Liu HQ. Constructing Al@C–Sn pellet anode without passivation layer for lithium-ion battery. Int. J. Miner. Metall. Mater., 2024, 313552
|
| [2] |
Yu HJ, Wang DX, Rao S, et al. . Selective leaching of lithium from spent lithium-ion batteries using sulfuric acid and oxalic acid. Int. J. Miner. Metall. Mater., 2024, 314688
|
| [3] |
Zhang D, Lv PF, Qin W, He X, He YH. Recent progress in constructing fluorinated solid–electrolyte interphases for stable lithium metal anodes. Int. J. Miner. Metall. Mater., 2025, 322270
|
| [4] |
L.M. Song, T.L. Zheng, Y.P. Li, S.P. Deng, Y.G. Yang, and X.J. Zhu, A large capacity expansion and robust recognition method of dot-dispersing coded targets with binary step-response serial encoding, Measurement, 225(2024), art. No. 114038.
|
| [5] |
Moolman DW, Aldrich C, Van Deventer JSJ. The monitoring of froth surfaces on industrial flotation plants using connectionist image processing techniques. Miner. Eng., 1995, 81–223
|
| [6] |
Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016
|
| [7] |
C. Korbel, I.V. Filippova, and L.O. Filippov, Froth flotation of lithium micas–A review, Miner. Eng., 192(2023), art. No. 107986.
|
| [8] |
W.N. Wang, M. Pan, C.L. Duan, H.S. Jiang, Y.M. Zhao, and H.D. Lu, Dry deep screening of spodumene and its mineral processing technology, Miner. Eng., 179(2022), art. No. 107445.
|
| [9] |
R.P. Wang, Y.L. Li, G.L. Zhu, and Y.J. Cao, Effects of dissolution by alkali treatment on anisotropic surface properties and flotation behavior of spodumene, Colloids Surf. A, 675(2023), art. No. 132088.
|
| [10] |
Zhang J, Tang ZH, Ai MX, Gui WH. Nonlinear modeling of the relationship between reagent dosage and flotation froth surface image by Hammerstein–Wiener model. Miner. Eng., 2018, 12019
|
| [11] |
Cao WY, Wang RF, Fan MQ, Fu X, Wang HR, Wang YL. A new froth image classification method based on the MRMR–SSGMM hybrid model for recognition of reagent dosage condition in the coal flotation process. Appl. Intell., 2022, 52732
|
| [12] |
F.Y. Hu, Y.P. Fan, X.M. Ma, et al., Niu, 3D feature characterization of flotation froth based on a dual-attention encoding volume stereo matching model and binocular stereo vision extraction, Miner. Eng., 217(2024), art. No. 108903.
|
| [13] |
C. Tian, Z.H. Tang, H. Zhang, Y.F. Xie, and Z.E. Dai, Reagent dosage inference based on graph convolutional memory perception network for zinc roughing flotation, Control Eng. Pract., 146(2024), art. No. 105882.
|
| [14] |
Wang ZS, Shao WY, Chen YL, Xu JW, Zhang L. A cross-scale iterative attentional adversarial fusion network for infrared and visible images. IEEE Trans. Circuits Syst. Video Technol., 2023, 3383677
|
| [15] |
Zafar MR, Khan N. Attentional feature fusion for few-shot learning. 2024 International Joint Conference on Neural Networks (IJCNN). 20241
|
| [16] |
Cai F, Qu Z, Yin XH. A feature fusion network with multiscale adaptively attentional for object detection in complex traffic scenes. IEEE Trans. Intell. Veh., 2025, 1084217
|
| [17] |
J. Fu, H.K. Yuan, R.Q. Zhao, Z. Chen, and L.Q. Ren, Peeling damage recognition method for corn ear harvest using RGB image, Appl. Sci., 10(2020), No. 10, art. No. 3371.
|
| [18] |
W.J. Zhang, W. Sun, M.J. Zheng, et al., Prediction of collector flotation performance based on machine learning and quantum chemistry: A case of sulfide minerals, Sep. Purif. Technol., 342(2024), art. No. 126954.
|
| [19] |
J.F. Wei, L.Y. Ni, L. Luo, et al., GFS-YOLO11: A maturity detection model for multi-variety tomato, Agronomy, 14(2024), No. 11, art. No. 2644.
|
| [20] |
C. Lartey, R.K. Asamoah, C. Greet, M. Zanin, and J.X. Liu, An interpretable and generalised machine learning model for predicting flotation performance, Miner. Eng., 232(2025), art. No. 109492.
|
| [21] |
Warman C, Sullivan CM, Preece J, et al. . A cost-effective maize ear phenotyping platform enables rapid categorization and quantification of kernels. Plant J., 2021, 1062566
|
| [22] |
A. Wang, H. Chen, L.H. Liu, et al., YOLOv10: Real-time end-to-end object detection, Comput. Vision Pattern Recognit., 2024. https://doi.org/10.48550/arXiv.2405.14458.
|
| [23] |
Dang ZC, Wang XS. FD-YOLO11: A feature-enhanced deep learning model for steel surface defect detection. IEEE Access, 2025, 1363981
|
| [24] |
Szmigiel A, Apel DB, Skrzypkowski K, Wojtecki L, Pu YY. Advancements in machine learning for optimal performance in flotation processes: A review. Minerals, 2024, 144331
|
| [25] |
Y.Z. Zhang, W.J. Wang, Z.M. Li, et al., Development of a cross-scale weighted feature fusion network for hot-rolled steel surface defect detection, Eng. Appl. Artif. Intell., 117(2023), art. No. 105628.
|
| [26] |
Yu JL, Shi XN, Wang WH, Zheng YC. LCG-YOLO: A real-time surface defect detection method for metal components. IEEE Access, 2024, 1241436
|
| [27] |
You CZ, Kong HZ. Improved steel surface defect detection algorithm based on YOLOv8. IEEE Access, 2024, 1299570
|
| [28] |
R. Cook, K.C. Monyake, M.B. Hayat, A. Kumar, and L. Alagha, Prediction of flotation efficiency of metal sulfides using an original hybrid machine learning model, Eng. Rep., 2(2020), No. 6, art. No. e12167.
|
| [29] |
P. Quintanilla, D. Navia, S. Neethling, and P. Brito-Parada, Experimental implementation of an economic model predictive control for froth flotation, [in] Computer Aided Chemical Engineering, Elsevier, Amsterdam, p. 1759.
|
| [30] |
González RA, Quintanilla P. Grey-box recursive parameter identification of a nonlinear dynamic model for mineral flotation. 2024 10th International Conference on Control, Decision and Information Technologies (CoDIT). 2024art. No. 2967
|
| [31] |
Chen HT, Huang B. Fault-tolerant soft sensors for dynamic systems. IEEE Trans. Control Syst. Technol., 2023, 3162805
|
| [32] |
Yao L, Ge ZQ. Industrial big data modeling and monitoring framework for plant-wide processes. IEEE Trans. Ind. Inform., 2021, 1796399
|
| [33] |
Yuan XF, Ou C, Wang YL, Yang CH, Gui WH. A layer-wise data augmentation strategy for deep learning networks and its soft sensor application in an industrial hydrocracking process. IEEE Trans. Neural Netw. Learn. Syst., 2021, 3283296
|
| [34] |
Y.Q. Chu, X.Y. Yu, and X.W. Rong, A lightweight strip steel surface defect detection network based on improved YOLOv8, Sensors, 24(2024), No. 19, art. No. 6495.
|
RIGHTS & PERMISSIONS
University of Science and Technology Beijing
PDF
