基于近红外光谱的大豆油质量快速检测技术应用研究  

Application research of rapid detection technology of soybean oil quality based on near infrared spectroscopy

作　　者：罗淑年 张理博 邹汶蓉 李忠华 朴仁官 王立琦[5] 于殿宇[2] Luo Shunian;Zhang Libo;Zou Wenrong;Li Zhonghua;Piao Rengong;Wang Liqi;Yu Dianyu(Jiu San Group Harbin Huikang Food Co.,Ltd.,Harbin 150010;Northeast Agricultural University,Harbin 150030;Suihua Jinlong Oil Co.,Ltd.,Suihua 152000;Zhejiang ChuangpuTechnologyCo.,Ltd.,Taizhou 318001;Harbin University of Commerce,Harbin 150028)

机构地区：[1]九三集团哈尔滨惠康食品有限公司,哈尔滨150010 [2]东北农业大学,哈尔滨150030 [3]绥化金龙油脂有限责任公司,绥化152000 [4]浙江创谱科技有限公司,台州318001 [5]哈尔滨商业大学,哈尔滨150028

出　　处：《粮食与食品工业》2020年第1期68-72,共5页Cereal & Food Industry

基　　金：黑龙江省教育厅省属高校研发项目（TSTAUR2018010）

摘　　要：利用近红外光谱快速检测大豆油脂的过氧化值和酸值,分析发现大豆油脂的过氧化值和酸值在近红外光谱区域有特征吸收峰,通过对比分析,优选出大豆油脂过氧化值特征波段为4500~9000 cm^-1,大豆油脂酸值的特征波段为4500~5000 cm^-1,采用小波变换对光谱去噪并利用PLS建立了预测模型,大豆油脂过氧化值和酸值模型的相对标准偏差RSD分别为3.513%和3.629%,准确度与化学方法相近,说明利用近红外光谱分析技术快速检测大豆油脂主要指标是可行的。The near-infrared spectroscopy was used to rapidly detect the peroxide value and acid value of soybean oil.It was found that the peroxide value and acid value of soybean oil had characteristic absorption peaks in the near-infrared region.Through comparative analysis,it is preferred that the characteristic band of the peroxide value of soybean oil is 4500~9000 cm^-1,and the characteristic band of the acid value of soybean oil is 4500~5000 cm^-1.The wavelet transform is used to denoise the spectrum and the prediction model is established by PLS.The relative standard deviation(RSD)of soybean oil peroxide and acid value models were 3.513%and 3.629%,respectively.The accuracy is similar to the chemical method,indicating that it is feasible to use the near-infrared spectroscopy to quickly detect the main indicators of soybean oil.

关 键 词：大豆油脂 近红外光谱 特征波段 模型 快速检测 

分 类 号：TS207.3[轻工技术与工程—食品科学]