Abstract：The amount of holocellulose, lignin, and microfibril angle of Chinese fir was predicted by using back-propagation neural network (BP-ANN) combined with near infrared (NIR) spectrometry. First, the data of original spectra were pretreated by Savitzky-Golay smoothing algorithm and the second derivative, then the data of near infrared spectrometry with 171 points were compressed to 86 points by using wavelet transform, and finally, the models were established by using BP-ANN. The models were validated using leave-n-out cross-validation approach，and the influences of the number of hidden neurons, learning rate, momentum, and epochs were discussed in the present paper. The prediction samples, which were not used in the model generation, were predicted by using the obtained models, the correlation coefficients (R2) of holocellulose, lignin and microfibril angle were 0.91, 0.90 and 0.87, respectively. The root mean square errors of prediction (RMSEP) of the established models were 0.86%, 0.33%, and 4.99%, respectively. The obtained results showed that the method is fast and nondestructive and can basically satisfy the requirement of quantitative analysis.
丁丽1,相玉红1,黄安民2,张卓勇1*. BP神经网络与近红外光谱定量预测杉木中的综纤维素、木质素、微纤丝角[J]. 光谱学与光谱分析, 2009, 29(07): 1784-1787.
DING Li1, XIANG Yu-hong1, HUANG An-min2, ZHANG Zhuo-yong1*. Quantitative Prediction of Holocellulose, Lignin, and Microfibril Angle of Chinese Fir by BP-ANN and NIR Spectrometry. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(07): 1784-1787.
[1] LU Wan-zhen, YUAN Hong-fu, XU Guang-tong, et al(陆婉珍，袁洪福，徐广通，等). Modern Near Infrared Spectroscopy Analysis Technology(现代近红外光谱分析技术). Beijing：China Petrochemical Press(北京：中国石化出版社), 2001. 73. [2] Flaten G R, Walmsley A D. Chemom. Intelligent Lab Syst., 2004, 73 (1)：55. [3] Navrátil M, Norberg A, Lembrén L. J. Biotechol., 2005, 115 (1)：67. [4] Meher L C, Sagar D V, Naik S N. Renewable and Sustainable Energy Reviews, 2006, 10 (3)：248. [5] JIANG Ze-hui, HUANG An-min, FEI Ben-hua, et al(江泽慧, 黄安民, 费本华, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26 (7)：1230. [6] QI Xiao, HAN Jian-guo, LI Man-li(齐晓, 韩建国, 李曼莉). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(10)：2022. [7] LIU Bo-ping, QIN Hua-jun, LUO Xiang, et al(刘波平, 秦华俊, 罗香, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(10)：2005. [8] Poke F S, Raymond C A. J. Wood Chem. Tech., 2006, 26(2)：187. [9] Taylor A, Lloyd J. Forest Product. J., 2007, 57(1-2)：116. [10] Acuna M A, Murphy G E. Forest Product J., 2006, 56 (11-12)：67. [11] Defo M, Taylor A M, Bond B. Forest Product J., 2007, 57(5)：68. [12] Fackler K, Schwanninger M, Gradinger C, et al. FEMS Microbiol. Lett., 2007, 271(2)：162. [13] Jones P D, Schimleck L R, Peter G F, et al. Wood Sci. Technol., 2006, 40(8)：709. [14] JIANG Ze-hui, HUANG An-min (江泽慧，黄安民). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26(8)：1464. [15] JIANG Ze-hui, LI Gai-yun, WANG Ge, et al(江泽慧，李改云，王戈，等). Chemistry and Industry of Forest Products(林产化学与工业), 2007, 27(1)：15. [16] YANG Zhong, JIANG Ze-hui, FEI Ben-hua, et al(杨忠，江泽慧，费本华，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(4)：686. [17] XU Lu, SHAO Xue-guang(许禄，邵学广). The Method of Chemometrics(化学计量学方法). Beijing：Science Press(北京：科学出版社), 2004. 281. [18] YANG Jian-gang(杨建刚). Applied Tutorial of Artificial Neural Networks(人工神经网络实用教程). Hangzhou：Zhejiang University Press(杭州：浙江大学出版社), 2001. 41. [19] Dardenne P, Sinnaeve G, Baeten V. J. Near Infrared Spec., 2000, 8(4)：229. [20] JIANG Ze-hui, FEI Ben-hua, YANG Zhong(江泽慧，费本华，杨忠). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2007, 27(3)：435.
