Variety Identification of Bulk Commercial Coal Based on Full-Spectrum Spectroscopy Analytical Technique
REN Yu1,2, SUN Xue-jian2*, DAI Xiao-ai1, CEN Yi2, TIAN Ya-ming1, WANG Nan2, ZHANG Li-fu2
1. College of Earth Sciences, Chengdu University of Technology, Chengdu 610059, China
2. The State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China
Abstract：To obtain the precise result, complex chemical analysis or complicated sample preparation is needed in universal coal analysis methods. In the paper, a new method to distinguish the type of bulk commercial coal using full spectroscopy which combined visible and near-infrared reflectance spectroscopy (Vis-NIRS) and short-wave infrared reflectance spectroscopy (SWIR) analytical technique and Multilayer Perceptron (MLP) classification method was advanced. The method was non-contact with no sample preparation and no chemical analysis. Besides, the classification information of coal can be quickly and efficiently obtained by this method. In the paper, the band range of original spectral data whose noise was excessive was deleted. The noise of remaining part was denoised by wavelet threshold denoising method. The spectral data pretreated was divided into three data sets: Vis-NIRS data set (500~900 nm), SWIR data set (1 000~2 350 nm) and full-spectrum data set (500~2 350 nm). Principal component analysis (PCA) was adopted in three datasets. The extracted principal components were entered in the MLP classification model. Multilayer perceptron was consist of input layer, hidden layers (two layers), softmax classifier. The contrastive study of classification accuracywas made among the three datasets. Random forest and Support Vector Machine (SVM) was used to verification analysis. The research showed: in the classification research of bulk commercial coal, because of the abundant data information of full-spectrum data, a better classification result can be obtained. When the number of training sample was 132, using the MLP classifier can achieve the highest classification accuracy which was 98.03%. The classification results of random forest and SVM verified the superiority and universality of the full spectrum dataset. The method provides reliable technical support for on-line analysis of coal and development of portable coal detecting instrument.
[1] Hel L, Melnichenko Y B, Mastalerz M, et al. Energy Fuels, 2012, 26(3): 1975.
[2] Zhang Y, Zhang X L, Jia W B, et al. Applied Spectroscopy, 2016, 70(1): 101.
[3] SHAN Qing, ZHANG Xin-lei, ZHANG Yan, et al(单 卿，张新磊，张 焱，等). Journal of Nanjing University of Aeronautics & Astronautics(南京航空航天大学学报), 2015, 47(5): 767.
[4] Tahmasebi A, Yu J, Li X, et al. Fuel Processing Technology, 2011, 92(10): 1821.
[5] CHENG Dong, WEN He, TENG Zhao-sheng, et al(程 栋，温 和，滕召胜，等). Chinese Journal of Scientific Instrument(仪器仪表学报)，2014，35(10)：2263.
[6] LEI Meng, LI Ming(雷 萌，李 明). CIESC Journal(化工学报), 2012, 63(12): 3991.
[7] LI Ming, CHEN Fan, LEI Meng, et al(李 明, 陈 凡, 雷 萌，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(9): 2793.
[8] WANG Ya-sheng, YANG Meng, LUO Zhi-yuan, et al(王雅圣, 杨 梦, 骆志远, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(6): 1685.
[9] CHU Xiao-li(褚小立). Molecular Spectroscopy Analytical Technology Combined with Chemometrics and its Applications(化学计量学方法与分子光谱分析技术). Beijing: Chemical Industry Press(北京: 化学工业出版社), 2011.
[10] Mahmoudi J, Arjomand M A, Rezaei M, et al. Civil Engineering Journal, 2016, 2(1).
[11] Chakraborty M, Ghosh A. Computer Science, 2012, 60(13): 1.
[12] FANG Kuang-nan, WU Jian-bin, ZHU Jian-ping, et al(方匡南, 吴见彬, 朱建平, 等). Statistics & Information Forum(统计与信息论坛), 2011, 26(3): 32.
[13] DING Shi-fei, QI Bing-juan, TAN Hong-yan(丁世飞, 齐丙娟, 谭红艳). Journal of University of Electronic Science and Technology of China(电子科技大学学报), 2011, 40(1): 2.
[14] Wang Y, Yang M, Wei G, et al. Sensors & Actuators B Chemical, 2014, 193(3): 723.
[15] HE Xuan-ming(何选明). Coal Chemistry(煤化学). Beijing: Metallurgical Industry Press(北京: 冶金工业出版社), 2010.
