Abstract:Forest bio-fuel, a new type renewable energy, has attracted increasing attention as a promising alternative. In this study, a new method called Sparse Partial Least Squares Regression(SPLS) is used to construct the proximate analysis model to analyze the fuel characteristics of sawdust combining Near Infrared Spectrum Technique. Moisture, Ash, Volatile and Fixed Carbon percentage of 80 samples have been measured by traditional proximate analysis. Spectroscopic data were collected by Nicolet NIR spectrometer. After being filtered by wavelet transform, all of the samples are divided into training set and validation set according to sample category and producing area. SPLS, Principle Component Regression (PCR), Partial Least Squares Regression (PLS) and Least Absolute Shrinkage and Selection Operator (LASSO) are presented to construct prediction model. The result advocated that SPLS can select grouped wavelengths and improve the prediction performance. The absorption peaks of the Moisture is covered in the selected wavelengths, well other compositions have not been confirmed yet. In a word, SPLS can reduce the dimensionality of complex data sets and interpret the relationship between spectroscopic data and composition concentration, which will play an increasingly important role in the field of NIR application.
Key words:Near infrared spectrum technique;Sparse least square regression;Proximate analysis
姚 燕*,王常玥,刘辉军,汤建斌,蔡晋辉,汪静军 . 基于近红外光谱和稀疏偏最小二乘回归的生物质工业分析 [J]. 光谱学与光谱分析, 2015, 35(07): 1864-1869.
YAO Yan*, WANG Chang-yue, LIU Hui-jun, TANG Jian-bin, CAI Jin-hui, WANG Jing-jun . Biomass Compositional Analysis Using Sparse Partial Least Squares Regression and Near Infrared Spectrum Technique. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(07): 1864-1869.
[1] LI Feng-rui, TANG Yu-guo, XIAO Bao-lan(李凤瑞, 唐玉国, 肖宝兰). Journal of Engineering for Thermal Energy and Power(热能动力工程), 2003, 18(6): 582. [2] Andres J M, Bona M T. Analytical Chimica Acta, 2005, (535): 123. [3] Sensoz S, Kaynar I. Industrial Crops and Products, 2006, 23(1): 99. [4] Burns D A,Ciurczak E W. Handbook of Near-Infrared Analysis. Revised and Expanded, Chapter 28,2001. [5] Kaihara Mikio. Report of the ISIJ Meeting, 2005,18(3):652. [6] HUANG Cai-jin(皇才进). J. Infrared Millim. Waves(红外与毫米波学报), 2009, 28(3): 184. [7] Hyonho Chun. J. R. Statist. Soc., 2010, 72(1): 3. [8] Hui Zou, Trevor Hastie. J. R. Statist. Soc. B, 2005, 67(2): 301. [9] Robert Tibshiani. J. R. Statist. Soc. B, 1996, 58(1): 267. [10] Chun H. Genetics, 2009, 182: 79. [11] Jolliffe I T, Trendafilov N T, Uddin M. Computnl Graph. Statist.,2003, 12: 531. [12] GBT 28731—2012. Proximate Analysis of Solid Biofules(固体生物质燃料工业分析方法). [13] Wang Changyue, Yao Yan, Liu Huijun. Rapid Compositional Analysis of Sawdust Using Sparse Method and Near Infrared Spectroscopy. The 26th Chinese Control and DecisionConference. [14] YAN Yan-lu(严衍禄). Basic and Application of Near Infrared Spectroscopy Analysis(近红外光谱分析基础与应用). Beijing: Chinese Light Industry Press(北京: 中国轻工业出版社), 2005. 169. [15] Alsberg B K, Woodward A M,Kell D B. Chemometr Intell LabSyst, 1997, 37: 215. [16] ZHU Xiao-li, YUAN Hong-fu, LU Wan-zhen(褚小立, 袁洪福, 陆婉珍). Progress in Chemistry(化学进展), 2004, 16(4): 534.