摘要
采用近红外光谱结合化学计量学的方法,对桉木和相思木及其属间6种木材的判别分类进行了研究。首先采集了尾巨桉、尾叶桉L11、尾叶桉u6、蓝桉、马占相思、厚荚相思,共计86个样本的近红外光谱图,采用偏最小二乘法判别分析(PLS-DA)建立了桉木和相思木的分类模型,校正集和验证集的预测值与实际值之间的回归线基本重合,决定系数(R^2)分别为0.99和0.97,模型效果较好,且对未知样本的识别正确率为100%。为了对属间的6种木材作进一步的判别,采用MSC和Savitzky-Golay平滑对4000~7500cm。光谱进行预处理后,结合主成分分析(PCA)建立判别模型,模型识别率和验证正确率均为100%。结果表明基于近红外光谱结合化学计量学算法可以对按木和相思木的不同属进行快速鉴别。
The identification of eucalyptus and acacia wood and classification among six kinds of wood were studied in this paper, based on near-infrared spectroscopy method combined with chemometrics algorithm. Firstly, near-infrared spectra of 86 samples, containing Eucalyptus urophylla x E. grondis ,E. urophylla L11, E. urophylla U6 ,E. globules ,Acacia mangium and A. crassicarpa. were collected, Then partial least squares discriminant analysis (PLS-DA) was used to establish a classification model of eucalyptus and acacia. The results showed that the regression lines between predicted value and actual value of calibration set'and validation set were in good agreement, and the coefficient of determination ( R2 ) were 0.99 and 0.97. This showed that the model was better. Moreover,the accuracy of the unknown samples was 100%. MSC and Savitzky-Golay smoothing method were used to pretreat the spectral of 4000 -7500 cm^- 1 , and discrimination model was established based on the principal component analysis (PCA). Results showed that the recognition rate of the calibration and validation model was 100%. Therefore, the chemometrics algorithm based on near infrared spectra could identify the eucalyptus and acacia species quickly.
出处
《林产化学与工业》
EI
CAS
CSCD
北大核心
2015年第6期96-100,共5页
Chemistry and Industry of Forest Products
基金
国家林业局948技术引进项目(2014-4-31)
关键词
近红外光谱
偏最小二乘法判别分析
主成分分析
木材
near infrared spectra(NIRS)
partial least squares discriminant analysis (PLS-DA)
principal component analysis (PCA)
wood