Liu Bo-Ping, Qin Hua-Jun, Luo Xiang, Cao Shu-Wen, Wang Jun-De
College of Chemical Engineering, Nanjing University of Science and Technology, Nanjing 210014, China.
Guang Pu Xue Yu Guang Pu Fen Xi. 2007 Nov;27(11):2216-20.
The present paper introduces an application of near infrared spectroscopy(NIRS) multi-component quantitative analysis by building partial least squares (PLS)-generalized regression neural networks (GRNN) model. The PLS-GRNN prediction model for chlorine, fibre and fat in 45 feedstuff samples was established with good veracity and recurrence. Eight peak values in principal components compressed from original data by PLS and four in original spectra were taken as inputs of GRNN while 4 predictive targets as outputs. 0.1 was chosen as smoothing factor for its good approximation and prediction with the lowest error compared with 0.2, 0.3, 0.4 and 0.5. Predictive correlation coefficient and Standard error of the estimate of three components by the model are 0.984 0, 0.987 0 and 0.983 0, and 0.015 89, 0.154 1 and 0.115 1, while the Standard deviations of an unknown sample scanned 8 times are 0.003 26, 0.065 5 and 0.031 4. The results show that PLS-GRNN used in NIRS is a rapid, effective means for measuring chlorine, fibre in the fat in feedstuff powder, and can also be used in quantitative analysis of other samples. A settlement in the high error of prediction of other samples with lower contents was also shown.
本文通过建立偏最小二乘法（PLS）-广义回归神经网络（GRNN）模型，介绍了近红外光谱（NIRS）多组分定量分析的一种应用。建立了45个饲料样品中氯、纤维和脂肪的PLS-GRNN预测模型，具有良好的准确性和重现性。将PLS从原始数据压缩得到的主成分中的8个峰值和原始光谱中的4个峰值作为GRNN的输入，4个预测目标作为输出。选择0.1作为平滑因子，因为与0.2、0.3、0.4和0.5相比，它具有良好的逼近性和预测性，误差最低。该模型对三种成分的预测相关系数和估计标准误差分别为0.984 0、0.987 0和0.983 0，以及0.015 89、0.154 1和0.115 1，而对一个未知样品扫描8次的标准偏差分别为0.003 26、0.065 5和0.031 4。结果表明，NIRS中使用的PLS-GRNN是一种快速、有效的测定饲料粉末中氯、纤维和脂肪的方法，也可用于其他样品的定量分析。还显示了对其他低含量样品预测误差高的一种解决方法。
