近红外光谱法预测粗皮桉木材的化学成分质量分数

Prediction of Chemical Compositions of Eucalyptus pellita by Near Infrared Spectroscopy

采用近红外光谱法对粗皮桉木材中化学成分质量分数进行快速预测。用常规湿化学方法测定了粗皮桉木材样品的化学成分质量分数,结合近红外光谱仪采集相应的光谱,对原始光谱进行二阶导数预处理后,用偏最小二乘法建立相应的模型并对其进行外部验证。结果表明:粗皮桉木材综纤维素校正模型的相关系数为0.96,预测模型的相关系数为0.92,RPD为2.30。木质素校正模型的相关系数为0.91,预测模型相关系数为0.88,RPD为2.11。利用近红外光谱分析方法可以快速预测粗皮桉木材中综纤维素和木质素质量分数。

A rapid near infrared（NIR） spectroscopy method was used to predict chemical compositions of Eucalyptus pellita. The chemical compositions of wood samples were analysed using conventional wet chemical methods, and the spectra were collected by NIR. After the second derivative pretreatment of raw spectra, the models were developed using partial least- squares statistical analysis and external validation. Results showed that the correlation coefficients （r） of calibration and validation for holoeellulose were 0.96 and 0.92 ,and the ratio of performance to deviation（RPD） was 2.30. For lignin, the correlation coefficients of calibration and validation were 0.91 and 0.88, while the RPD was 2. 11. NIR spectroscopy method could be applied to the rapid prediction of the holocellulose and lignin contents in E. pellita wood.