偏最小二乘法在傅里叶变换红外光谱中的应用及进展

Application and Improvement of Partial-Least-Squares in Fourier Transform Infrared Spectroscopy

偏最小二乘法(PLS)是一种应用非常广泛的化学计量方法,它综合了多元线性回归法(MLR)和主成分回归法(PCR)的优势,具有预测能力强和模型相对简单等优点。PLS使傅里叶变换红外光谱的应用范围不断扩大,同时算法也得到了改进和完善。文章介绍了偏最小二乘法在傅里叶变换红外光谱中的应用,对改进算法,如移动窗口PLS(MWPLS)、稳健PLS(RPLS)、加权PLS(WPLS)和非线性PLS等进行了介绍。同时,对应用PLS时数据的预处理、变量的选择、噪声的处理和非线性模型的建立进行了综述。

Partial least squares（PLS） algorithm is an effective chemometric tool. It takes the advantages of multipal linear regression （MLR） and principal component regression （PCR）, which makes Fourier transform infrared spectrometry （FTIR） more powerful and useful. Accompanied with increasing use of FTIR, the algorithm is modified and corrected under different circumstances. The applications of PLS to FTIR were mentioned. Improved algorithms were presented, such as moving windows PLS（MWPLS）, robust PLS （RPLS）, weighted PLS（WPLS）, and non-linear PLS. Data pre-processing, selection of variable, noise elimination and non-linear model of PLS were introduced.