A Classification Method of Coal and Gangue Based on XGBoost and
Visible-Near Infrared Spectroscopy
LI Rui1, LI Bo1*, WANG Xue-wen1, LIU Tao1, LI Lian-jie1，2, FAN Shu-xiang2
1. College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China
2. Beijing Research Center of Intelligent Equipment for Agriculture, Beijing 100097, China
Abstract：Intelligent recognition of coal and gangue is a new technology that needs to be developed urgently to realize the intelligentization of fully mechanized caving mining. Visible-near infrared spectroscopy technology has many advantages such as environmental friendly and real-time, which meets the requirements of intelligent separation of coal and gangue. The Extreme Gradient Boosting Tree (XGBoost) algorithm which performed well in data science competitions, was introducedto achieve the recognition of coal and gangue based on visible-near infrared spectroscopy. Firstly, a visible-near infrared spectroscopy experimental platform was built to collect the reflectance spectra of lump coal and gangue samples from Shanxi Ximing, Shaanxi Shenmu, and Inner Mongolia Balongtu coal mines in the range of 370~1 049 nm. The collected original spectra were preprocessed through black and white correction, method of removing the start and end bands, Savitzky-Golay (SG) smoothing and standard normal variable transformation (SNV) to reduce the effects of uneven illumination, noise and optical path difference. Secondly, the experimental group and test group were divided according to the difference of reflection spectrum of samples from different mines. The experimental group had a minor difference, which was used to compare the performance of different models and select the best algorithm; the difference of test groups was obvious, which was used to test the performance of the best algorithm in other coal mines and verified the applicability of the algorithm to different coal mines. In the experiment of the experimental group, the coal and gangue classification model was established based on the XGBoost algorithm, and the commonly used machine learning classification algorithms k-nearest neighbor method (KNN), random forest (RF), support vector machine (SVM), which were introduced for comparison. The results showed XGBoost performed best. The average accuracy of 10-fold cross-validation (ACC10), classification accuracy (ACC), and AUC values respectively reached 0.957 2, 0.970 5, and 0.971 6, showing strong stability and classification capabilities. Then in order to reduce the data dimension and calculations, recursive feature elimination (RFE), successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were used to select the characteristic wavelength and combined with the above four classification algorithms to construct a simplified classification model, respectively. The simplified model of the combination of RFE and XGBoost(RFE-XGB) performed best in the test. The ACC10, ACC, AUC was 0.965 7, 0.980 3, 0.980 3, respectively, and the data dimension reduced to 9. Simplified model improved the stability and classification ability of the model while reducing the data dimension. In the experiment of the test group, the model based on XGBoost and RFE-XGB algorithms can also achieve stable and accurate recognition of coal and gangue in other coal mines, and the simplified model performed better, which was consistent with the results of the experimental group.
Key words：XGBoost; Visible and near-infrared; Coal and gangue separation; Black background; Nondestructive detection
李 瑞，李 博，王学文，刘 涛，李廉洁，樊书祥. 基于XGBoost与可见-近红外光谱的煤矸识别方法[J]. 光谱学与光谱分析, 2022, 42(09): 2947-2955.
LI Rui, LI Bo, WANG Xue-wen, LIU Tao, LI Lian-jie, FAN Shu-xiang. A Classification Method of Coal and Gangue Based on XGBoost and
Visible-Near Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2947-2955.
[1] YU Bin, XU Gang, HUANG Zhi-zeng, et al（于 斌，徐 刚，黄志增，等）. Journal of China Coal Society（煤炭学报）, 2019, 44(1): 42.
[2] Zhang N, Liu C. Scientific Reports, 2018, 8(1): 190.
[3] LI Bo, WANG Xue-wen, GAO Xin-yu, et al（李 博，王学文，高新宇，等）. China Powder Science and Technology（中国粉体技术）, 2021, 27(4): 77.
[4] Wang S H, Zhao Y, Hu R, et al. Chinese Journal of Analytical Chemistry, 2019, 47 (4): E19034.
[5] SONG Liang, LIU Shan-jun, MAO Ya-chun, et al（宋 亮，刘善军，毛亚纯，等）. Journal of Northeastern University·Natural Science（东北大学学报·自然科学版）, 2017, 38(10): 1473.
[6] YANG En, WANG Shi-bo, GE Shi-rong, et al（杨 恩，王世博，葛世荣，等）. Industry and Mine Automation（工矿自动化）, 2017, 45(3): 46.
[7] Yang E, Ge S, Wang S, et al. Journal of Spectroscopy, 2018, 2018: 2754908.
[8] Mao Y, Le B T, Xiao D, et al. Optics and Laser Technology, 2019, 114: 10.
[9] Xiao D, Li H, Sun X. ACS Omega, 2020, 5(40): 25772.
[10] Hu F, Zhou M, Yan P, et al. IEEE Access, 2019, 7: 169697.
[11] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016, 785.
[12] HUANG Qing, XIE He-liang（黄 卿，谢合亮）. Mathematics in Practice and Theory（数学的实践与认识）, 2018, 48(8): 297.
[13] TAO Meng-qi, LIU Jia-xiang, WU Yue, et al（陶孟琪，刘家祥，吴 越，等）. Acta Optica Sinica（光学学报）, 2020, 40 (7): 0730002.
[14] JI Hui-jie, NI Feng, LIU Jiang, et al（冀慧杰，倪 枫，刘 姜，等）. Computer Technology and Development（计算机技术与发展）, 2021, 31(5): 21.
