摘要
以欧美杨的木质素含量为研究对象,给出了建立近红外光谱分析模型的一种多模型方法。所建模型可用于快速预测欧美杨中的木质素含量,其预测值与实验值之间的相关系数为0.9702,预测结果的平均相对误差为0.0100,模型的拟合优度为0.9126。将所建模型与用偏最小二乘法建立的欧美杨木质素含量预测模型进行了对比,前者的预测效果优于后者。
A near-infrared spectral analysis model is established by using a multi-model method. The model can be used to rapidly determine the lignin content in populus euramericana. The correlation coefficient between the predicted value and the experimental value is 0.9702. The mean relative error of the prediction is 0.0100. The goodness of the fit model is 0.9126. Compared with the determination model established by using the partial least squares （PLS） method, the prediction of this model is better.
出处
《红外》
CAS
2012年第11期39-43,共5页
Infrared
关键词
近红外光谱
多模型
木质素
欧美杨
near-infrared spectroscopy
multi-model
lignin
populus
