基于PLS算法的甘蔗清糖浆转光度的近红外光谱定量分析  

A Quantitative Analysis of Near Infrared Spectroscopy of the Pol of Simple Syrup Based on PLS Algorithm

作　　者：李兆雨 张静 袁华强 LI Zhaoyu;ZHANG Jing;YUAN Huaqiang(School of Computer Science and Technology,Dongguan University of Technology,Dongguan 523808,China)

机构地区：[1]东莞理工学院计算机科学与技术学院,广东东莞523808

出　　处：《东莞理工学院学报》2022年第5期79-85,共7页Journal of Dongguan University of Technology

基　　金：国家自然科学基金:物联网中数据安全传输与检索关键技术研究(61972090)。

摘　　要：清糖浆的转光度是制糖过程中重要的质量评价指标之一。针对传统清糖浆转光度指标检测方法效率低的问题,利用近红外光谱技术结合偏最小二乘PLS(Partial Least-square Method)算法,提出了甘蔗清糖浆转光度的快速分析方法。在考虑了随机性和稳定性的基础上,建立了一个具有定标、预测和检验功能的框架,根据预测均方根误差的综合指标(SEP+)对参数进行优化。建模结果显示,优化后的5个波长组合被认为是最佳模型。模型的SEP+和相关系数Rp分别为0.676和0.950。检验过程中,模型的SEP和相关系数Rp分别是0.895和0.904,预测值和实际值具有较高的相关性。预测效果较好且模型简单,本文所建立的波长模型可以为设计小型近红外分析仪器提供依据。The Pol of simple syrup is one of the important quality evaluation indicators in the process of sugar making.Aiming at the problem of low efficiency of the traditional method for the detection of the Pol of simple syrup,this paper proposes a rapid analysis method for the optical conversion of sugarcane simple syrup by using near-infrared spectroscopy technology combined with the partial least-squares(PLS) algorithm.On the basis of considering randomness and stability,a framework with functions of calibration,prediction and inspection is established,and parameters are optimized according to the comprehensive index of prediction root mean square error(SEP+).The modeling results show that the optimized 5 wavelength combinations are considered as the best model.The SEP+and correlation coefficient Rp of the model are 0.676 and 0.950.During the testing process,the SEP and correlation coefficient Rp of the model are 0.895 and 0.904,the predicted value and the actual value have a high correlation.The prediction effect is good and the model is simple and stable.The wavelength model established in this paper can provide a basis for the design of small near-infrared analytical instruments.

关 键 词：偏最小二乘回归 清糖浆转光度 近红外光谱 波长筛选方法 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]