提出将近红外光谱(NIR)检测技术用于成品纸张质量参数快速检测的方法,主要包括原始光谱预处理、光谱特征提取和检测建模几部分,并比较了采用基于支持向量机方法和采用基于偏最小二乘方法建模的检测性能。实验结果表明:近红外光谱预处理后,采用基于支持向量机建模检测的性能普遍优于采用基于偏最小二乘建模的性能。 A method of near infrared spectroscopy (NIR) detection technology for rapid detection of finished paper quality parameters is proposed. The methods include the preprocessing of original spectra, the extraction of spectral features and the detection modeling. Several methods based on support vector machine (SVM) Detection Performance of Least Squares Method Modeling. The experimental results show that the performance of SVM-based modeling and detection is generally better than that based on partial least squares after NIR pretreatment.