1. 东北大学信息科学与工程学院,辽宁 沈阳 110004
2. 东北大学资源土木与工程学院,辽宁 沈阳 110004
3. Control Technology College, Le Quy Don Technical University, Hanoi 100000, Vietnam
Coal Classification Based on Visible, Near-Infrared Spectroscopy and CNN-ELM Algorithm
LE Ba Tuan1, 3, XIAO Dong1*, MAO Ya-chun2, SONG Liang2, HE Da-kuo1, LIU Shan-jun2
1. College of Information Science and Engineering, Northeastern University, Shenyang 110004, China
2. School of Resources and Civil Engineering, Northeastern University, Shenyang 110004, China
3. Control Technology College, Le Quy Don Technical University, Hanoi 100000, Vietnam
Abstract:Coal serves as the main energy in industrial field, the quality of which has a decisive effect on industry and environment. In the using process of coal, if the category of the coal fails to be identified correctly, it will result in great harm to production efficiency, environmental pollution and economical loss. The traditional way of classifying coal mainly depends on artificial classification as well as chemical analysis, which however entails high cost and consumes too much time. Therefore, it becomes more and more important to identify the quality of coal quickly and correctly. Hence, this essay comes up with the idea of combining deep learning, ELM arithmetic and visible, infrared spectra to construct coal classification model. Firstly, we collected different coal samples from Fushun, Yimin and Henan Jiajinkou coal mining area, and used the American Spectra Vista SVC HR-1024 spectrometer for the measurement of the spectral data. Then we used the deep learning of convolutional neural network-CNN to extract spectral characteristics, and adopted ELM arithmetic to construct classification model for spectral data. Finally, in order to further improve the classification accuracy, this article made use of particle swarm optimization algorithm by using a range of newly defined inertia weight and acceleration factor values to improve the particle swarm optimization algorithm. Then, we used the improved particle swarm optimization to optimize CNN-ELM networks. Experimental results from comparison between PCA and CNN network reveal CNN network as a better feature extraction method for the spectrum. The results also show that CNN-ELM classification model has a good classification effect. The improved ELM classification model accuracy is higher than that of the basic ELM and SVM classification model. Compared with the traditional chemical methods and artificial methods, this method has the advantage of being unparalleled in economy, speed and accuracy.
作者简介: LE Ba Tuan,1990年生,东北大学信息科学与工程学院博士研究生 e-mail:
lebatuan@qq.com
引用本文:
LE Ba Tuan,肖 冬,毛亚纯,宋 亮,何大阔,刘善军. 可见、近红外光谱和深度学习CNN-ELM算法的煤炭分类[J]. 光谱学与光谱分析, 2018, 38(07): 2107-2112.
LE Ba Tuan, XIAO Dong, MAO Ya-chun, SONG Liang, HE Da-kuo, LIU Shan-jun. Coal Classification Based on Visible, Near-Infrared Spectroscopy and CNN-ELM Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2107-2112.
[1] GUO Juan, LI Wei-ming, YAO Xiao-ying(郭 娟,李维明,么晓颖). China Coal(中国煤炭), 2015, 41(12): 124.
[2] Li A P, Li Z Y, Jia J P, et al. Spectroscopy Letters, 2016, 49(3): 217.
[3] Becker J R, Skrodzki P J, Diwakar P K, et al. Spectroscopy Letters, 2016, 49(4): 276.
[4] MAO Ya-chun, XIAO Dong, CHENG Jin-fu(毛亚纯,肖 冬,程锦甫,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(1): 89.
[5] Niu X, Suen Y. Pattern Recognition, 2012, 45(4): 1318.
[6] Huang G B, Zhu Q Y, Siew C K. Neurocomputing, 2006, 70(1): 489.
[7] Xiao D, Le B T, Mao Y C, et al. Journal of Sensors, 2016, 2016(1): 1.
[8] Cao J, Chen T, Fan J. Multimedia Tools and Applications, 2016, 75(5): 2839.
[9] YU Dan, WU Xiao-jun(余 丹,吴小俊). Journal of Data Acquisition and Processing(数据采集与处理), 2016, 31(5): 996.
[10] Eberhart R C, Kennedy J. IEEE International Conference on Neural Network. Perth, Australia, 1995, 4: 1942.
[11] HUANG Shao-rong(黄少荣). Journal of Chongqing Normal University(重庆师范大学学报), 2013, 30(6): 123.
[12] Li S Z, Yu B, Wu W. Neurocomputing, 2015, 151(Part 2): 565.
[13] Zhang H G, Yin Y X, Zhang S. Neurocomputing, 2016, 174(Part A): 232.
[14] Zhao L, Li X G, Wang J. IEEE Sensors Journal, 2016, 16(15): 6081.
[15] Vapnik V, Cortes C. Machine Learning, 1995, 20(3): 273.