Coal gangue recognition based on spectral imaging combined with XGBoost

被引:13
作者
Zhou, Minghao [1 ,2 ]
Lai, Wenhao [2 ]
机构
[1] Inner Mongolia Univ Technol, Sch Sci, Hohhot, Peoples R China
[2] Anhui Univ Sci & Technol, Sch Elect & Informat Engn, Huainan, Peoples R China
关键词
IDENTIFICATION; PREDICTION; SYSTEM;
D O I
10.1371/journal.pone.0279955
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
The identification of coal gangue is of great significance for its intelligent separation. To overcome the interference of visible light, we propose coal gangue recognition based on multispectral imaging and Extreme Gradient Boosting (XGBoost). The data acquisition system is built in the laboratory, and 280 groups of spectral data of coal and coal gangue are collected respectively through the imager. The spectral intensities of all channels of each group of spectral data are averaged, and then the dimensionality is reduced by principal component analysis. XGBoost is used to identify coal and coal gangue based on the reduced dimension spectral data. The results show that PCA combined with XGBoost has the relatively best classification performance, and its recognition accuracy of coal and coal gangue is 98.33%. In this paper, the ensemble-learning algorithm XGBoost is combined with spectral imaging technology to realize the rapid and accurate identification of coal and coal gangue, which is of great significance to the intelligent separation of coal gangue and the intelligent construction of coal mines.
引用
收藏
页数:15
相关论文
共 50 条
[41]   A perspective on heavy metal(loid)s traceability in soil surrounding coal gangue areas: combined application of multiple source analysis methods [J].
Ma, Jie ;
Jiang, Yue ;
Shen, Zhijie ;
Zhang, Biaowei ;
Zhao, Hongjing ;
Yang, Xiaoxia ;
Feng, Xue ;
Sun, Dongyue .
FRONTIERS IN ENVIRONMENTAL SCIENCE, 2025, 13
[42]   Maize Seed Variety Classification Using the Integration of Spectral and Image Features Combined with Feature Transformation Based on Hyperspectral Imaging [J].
Huang, Min ;
He, Chujie ;
Zhu, Qibing ;
Qin, Jianwei .
APPLIED SCIENCES-BASEL, 2016, 6 (06)
[43]   Preparation and Properties of Expansive Backfill Material Based on Municipal Solid Waste Incineration Fly Ash and Coal Gangue [J].
Wang, Zhen ;
Liu, Honglin ;
Zhang, Yuanxin ;
Chen, Zhiwen ;
Zhao, Rumeng ;
Jia, Yongyong ;
Yong, Mingchao ;
Li, Guodong .
MINERALS, 2024, 14 (05)
[44]   Gait Recognition Algorithm of Coal Mine Personnel Based on LoRa [J].
Yin, Yuqing ;
Zhang, Xuehan ;
Lan, Rixia ;
Sun, Xiaoyu ;
Wang, Keli ;
Ma, Tianbing .
APPLIED SCIENCES-BASEL, 2023, 13 (12)
[45]   CNN coal and rock recognition method based on hyperspectral data [J].
Yang, Jianjian ;
Chang, Boshen ;
Zhang, Yuchen ;
Luo, Wenjie ;
Ge, Shirong ;
Wu, Miao .
INTERNATIONAL JOURNAL OF COAL SCIENCE & TECHNOLOGY, 2022, 9 (01)
[46]   Coal Structure Recognition Method Based on LSTM Neural Network [J].
Chen, Yang ;
Chen, Cen ;
Zhang, Jiarui ;
Hu, Fengying ;
He, Taohua ;
Wang, Xinyue ;
Cheng, Qun ;
He, Jiayi ;
Zhao, Ya ;
Zeng, Qianghao .
PROCESSES, 2024, 12 (12)
[47]   Lithological Classification by Hyperspectral Images Based on a Two-Layer XGBoost Model, Combined with a Greedy Algorithm [J].
Lin, Nan ;
Fu, Jiawei ;
Jiang, Ranzhe ;
Li, Genjun ;
Yang, Qian .
REMOTE SENSING, 2023, 15 (15)
[48]   Application of a Combined Model based on K-means plus plus and XGBoost in Traffic Congestion Prediction [J].
Duan Ran ;
Huang Jiaxin ;
Huang Yuzhe .
2020 5TH INTERNATIONAL CONFERENCE ON SMART GRID AND ELECTRICAL AUTOMATION (ICSGEA 2020), 2020, :413-418
[49]   Hyperspectral Imaging Technology Combined with the Extreme Gradient Boosting Algorithm (XGBoost) for the Rapid Analysis of the Moisture and Acidity Contents in Fermented Grains [J].
Han, Lipeng ;
Jiang, Xinna ;
Zhou, Shuyu ;
Tian, Jianping ;
Hu, Xinjun ;
Huang, Dan ;
Luo, Huibo .
JOURNAL OF THE AMERICAN SOCIETY OF BREWING CHEMISTS, 2024, 82 (03) :281-293
[50]   A Target Imaging and Recognition Method Based on Raptor Vision [J].
Xu, Bitong ;
Li, Zhengzhou ;
Cheng, Bei ;
Yang, Yuxin ;
Siddique, Abubakar .
REMOTE SENSING, 2023, 15 (08)