Full
Outline
Aiming at the problems of spatial information loss in traditional 2D images and the one-sidedness of single-cell data during the identification of coal slime flotation froth, a multi-cell feature fusion method based on 3D point cloud data was proposed. The Percipio Infrared Binocular FM855-E1 industrial camera was used to collect the 3D point cloud data of the froth surfaces from each flotation cell. Preprocessing and data augmentation techniques were adopted to optimize the dataset. A PointNet network with non-shared weights was utilized to extract the high-dimensional features of each cell. After dimensionality reduction by a multi-layer perceptron, these features were fused into multi-cell forth features through a concatenation function. Finally, the working condition categories were determined by a combination of a multi-layer perceptron and the Softmax function. The experimental results show that the classification accuracy of the multi-cell network reaches 94.89%, which is higher than other networks, the loss value is reduced to 0.216 9, with excellent robustness and generalization ability. It is proved that the multi-cell forth feature fusion method can significantly improve the recognition accuracy of flotation conditions, and provide a high-reliability three-dimensional visual solution for the intelligent flotation of coal slime.
51
16
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
