基于同步荧光光谱与化学计量学快速分析花生油氧化规律

Application of Synchronous Fluorescence Spectroscopy and Chemometric Models for Rapid Evaluating Peanut Oil Oxidative Stability

目前传统氧化稳定性评价方法无法提供油脂氧化历程和不同产物变化动态信息等特点,因而不能成为理想评价方法。同步荧光光谱技术具有一定灵敏度和准确度,且适合较长时间的固定检测。以不同工艺花生油作为研究对象,采用OXITEST油脂氧化稳定性仪进行加速氧化试验,获取氧化诱导曲线,同时采集氧化期间油脂三维同步荧光光谱数据与理化指标,通过同步荧光光谱结合平行因子法(PARAFAC)和人工神经网络(ANN)等化学计量学快速分析油脂氧化进程。结果表明,以诱导期作为油脂稳定性评价指标,冷榨花生油氧化稳定性较热榨花生油差,主要原因在于热榨方式的高温焙炒,使得其具有抗氧化物质,进而提高了油脂的氧化稳定性。氧化曲线清晰地表明氧化进程存在诱导期(IP)、氧化期和静止期三个阶段,结合三维荧光光谱图,明显得出在氧化过程中花生油原油激发波长在300~400 nm的荧光峰强度在进入诱导期后,荧光强度减弱,荧光波长出现红移现象;进入氧化期后,在400~450 nm之间有新的荧光峰生成,然后荧光峰强度呈现增强状态,直至静止期。现象的产生主要是由于油脂氧化过程中生成的小分子氧化产物,致使荧光光谱产生斯托克位移(Stocks shift)。运用PARAFAC法对同步荧光光谱数据进行降维处理,显示当组分数为6,Δλ为70 nm时载荷值最大,不同样品间差异最显著。选定该波段二维荧光光谱数据作为ANN模型输入值,分别以酸价和过氧化值作为模型输出值,对不同工艺花生油的氧化过程数据进行建模训练。结果显示训练集、测试集模型相关系数R均接近1.0,均方根误差均较小,说明该模型能较好地反映油脂氧化过程状态。本研究结果表明同步荧光光谱结合化学计量学能快速实时监控食用油在氧气影响下贮藏过程中的氧化历程,为油质控制提供理论依据。

At present,the tradition way to detect the oxidative stability could not provide information about a variety of chemical species and simultaneously in real time,and so on.Synchronous fluorescence spectroscopy is considered to be an ideal method,because it is sensitive and reproducible,and should be amenable to longer periods.Combined methods of synchronous fluorescence spectrometer with chemometrics were to monitor the oxidation of peanut oil,which were stored under OXITEST oil oxidation stabilizer to carry out accelerated oxidation test.There was the oxidation induction curve in the accelerated oxidation test,and meanwhile,the 3D synchronous fluorescence spectral data and physical and chemical indexes were collected.The results showed that the Induction Period(IP)of cold pressed peanut oil was worse than that of hot-pressed peanut oil.The hot-pressed peanut oil was roasted at high temperature,which made antioxidant substances to improve the oxidation stability.It was clearly showed induction period,oxidation period and the static period from the oxidation curve.The fluorescence peak of Ex shifted from 300~400 to 400~450 nm.With the increment of oxidation time,the fluorescence peak changed significantly,and the red shift appeared in the fluorescence wavelength.Data multidimensional was reduced by the parallel factor analysis(PARAFAC)method.It was used to select an optimizedΔλof 70 nm on 6 components with the adequate loading score.Then the artificial neural network(ANN)was used to build a regression model for both synchronous fluorescence and the acid value and peroxide value respectively to evaluate the degree of the oil oxidation.The peanut oil exhibited a high regression coefficient(R=0.99)between fluorescence intensity and acid value in the training and the testing.The overall results suggested that synchronous fluorescence spectroscopy combined with chemometrics was useful for rapidly monitoring oil oxidation process in time,and could provide a theoretical basis for the formation of oxidation products and evolution of fluorescence spectra.