白酒糟醅中酸度值的高光谱检测方法

酸度值是评价白酒糟醅质量的重要指标之一,为进一步提高糟醅酸度值的检测精度,提出了一种应用高光谱成像技术检测糟醅酸度值的方法.采用高光谱成像系统,在900～1700 nm内采集糟醅样本的光谱信息,并提取全部样本的平均光谱数据.采用3种预处理方法对原始光谱进行预处理,得到多元散射校正(multiplica-tive sca...

Hyperspectral detection method for the acidity detection of Baijiu fermented grains

Acidity value is one of the important indexes to evaluate the quality of fermented grains.In order to further improve the detection accuracy of the acidity value of fermented grains,a hyperspectral imaging method has been proposed to detect the acidity value of fermented grains.A hyperspectral imaging system was used to collect the spectral information of fermented grains samples in the range of 900-1700 nm and the average spectral data of all samples was extracted.Multiple scattering correction(MSC)was identified as the best pretreatment method of three tested pretreatment methods.On the basis of ensuring the detection accuracy and improving the detection efficiency,the competitive adaptive reweighted sampling(CARS)algorithm adopted to select feature bands was developed as the optimization method,and the PLSR and LS-SVM prediction models were established.The results showed that the LS-SVM prediction model,based on 38 characteristic wavelengths selected by CARS algorithm presented good prediction effect.The correlation coefficient of the prediction set R_p² was 0.9618,and the root mean square error of the prediction set was 0.0580 g/kg.The results indicated that hyperspectral imaging had better accuracy than other techniques in detecting the acidity of fermented grains.At the same time,an effective way to detect the content of other ingredients in liquor process was explored.