The present paper presents a new NIR multi-component analysis method with Artificial Neural Network (ANN) and Partial Least Square Regression (PLS).
提出了一种神经网络(ANN)和偏最小二乘法(PLS)结合的新的近红外(N IR)多组分分析法。
PLS algorithm was applied in the establishment of analytical models showing the relationships between the 2nd derivatives of NIR spectra with the contents of the respective components mentioned above.
用PLS计算法建立了表示上述组分的二阶导数近红外光谱与其含量间关系的分析模型。
The NIR quantitative analysis models of 5 detection indexes in validation set was established using partial least squares(PLS) method.
采用偏最小二乘法分别建立校正集样本中5个检测指标的NIR定量分析模型，并对验证集样本进行预测。
The results showed that the model of PLS was better than that of standard algorithm. Depending on the collected NIR data of 59 tea samples with different regions, assortment and manufact…
结果表明，基于提取的茶叶近红外光谱数据，利用偏最小二乘法（PLS）的甄别效果优于标准法，可以直观地将59个来自不同产地、品种和加工工艺的茶叶样品进行准确的分类判定。
The results showed that the model of PLS was better than that of standard algorithm. Depending on the collected NIR data of 59 tea samples with different regions, assortment and manufact…
结果表明，基于提取的茶叶近红外光谱数据，利用偏最小二乘法（PLS）的甄别效果优于标准法，可以直观地将59个来自不同产地、品种和加工工艺的茶叶样品进行准确的分类判定。
应用推荐