Woody Nathaniel A, Feudale Robert N, Myles Anthony J, Brown Steven D
Department of Chemistry and Biochemistry, University of Delaware, Newark, Delaware 19716, USA.
Anal Chem. 2004 May 1;76(9):2595-600. doi: 10.1021/ac035382g.
The transfer of partial least squares (PLS) calibration models among four near-infrared spectrometers was investigated for the quantitative analysis of thermoset resin polymers. A comparative study of second derivatives, multiplicative scatter correction, finite impulse response filtering, slope and bias correction, model updating (MU), and orthogonal signal correction (OSC) was conducted to determine which processing methods achieved model transferability. It is shown that OSC and MU were superior to the other calibration transfer methods, leading to very robust PLS models with enhanced predictive ability. It is also shown that the transfer results obtained with OSC were not significantly different from those obtained with model updating.
为了对热固性树脂聚合物进行定量分析，研究了偏最小二乘（PLS）校准模型在四台近红外光谱仪之间的传递情况。对二阶导数、多元散射校正、有限脉冲响应滤波、斜率和偏差校正、模型更新（MU）以及正交信号校正（OSC）进行了对比研究，以确定哪些处理方法能够实现模型的可传递性。结果表明，OSC和MU优于其他校准传递方法，能够得到预测能力增强且非常稳健的PLS模型。还表明，OSC得到的传递结果与模型更新得到的结果没有显著差异。
