基于近红外光谱的成品纸张质量参数快速检测

Rapid detection of paper quality based on near infrared spectrometry

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 rapid detection method for the quality of the finished paper parameters based on near infrared（NIR） spectrometry is proposed.After the spectrum preprocessing such as NIR spectral smoothing,baseline correction,standard normal variation,abnormal samples removed and spectral feature selection,support vector machine（SVM） and partial least squares（PLS） were respectively used to model the calibration model.The experiment for detecting paper moisture,ash,thickness and weight for a group of finished paper samples show the model performance based on SVM is generally better than those based on PLS.