基于 Vis-NIR 高光谱成像结合多种化学计量算法的山西陈醋熏蒸过程快速无损监测与

摘要：在山西老陈醋（（ SAV）的酿造过程中，熏蒸阶段谷物的质量对其风味和营养价值具有显著影响。本研究采用高光 谱成像技术（（ HSI）对熏蒸谷物的状态进行监测，并结合化学计量学方法，对三种关键理化指标——水分含量（（ MC）、总 酸度（（ TA）和氨基酸态氮（（ AAN）进行定量预测。研究首先比较了五种光谱预处理方法的降噪效果，随后通过竞争性自 适应重加权采样法筛选出最优波长。利用支持向量机分类法建立了熏蒸谷物的判别模型，其最佳识别准确率达到 100%。 进一步研究表明，偏最小二乘回归法的预测效果略优于支持向量机回归法，对MC、TA和AAN的预测相关系数（Rp） 分别达到0.9697、0.9716和0.9098。本研究证实，HSI技术可用于SAV熏蒸过程的快速无损监测与质量评估。

关键词：山西老陈醋；熏蒸工艺；高光谱成像技术；无损检测；化学计量学算法

期刊：Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy

DOI：https://doi.org/10.1016/j.saa.2024.124539

设备：GaiaSorter

Rapid non-destructive monitoring and quality assessment of the fumigation process of Shanxi aged vinegar based on Vis-NIR hyperspectral imaging combined with multiple chemometric algorithms

Abstract：The quality of the grains during the fumigation process can signiffcantly affect the ffavour and nutritional value of Shanxi aged vinegar (SAV). Hyperspectral imaging (HSI) was used to monitor the extent of fumigated grains, and it was combined with chemometrics to quantitatively predict three key physicochemical constituents: moisture content (MC), total acid (TA) and amino acid nitrogen (AAN). The noise reduction effects of ffve spectral preprocessing methods were compared, followed by the screening of optimal wavelengths using competitive adaptive reweighted sampling. Support vector machine classiffcation was employed to establish a model for discriminating fumigated grains, and the best recognition accuracy reached 100%. Furthermore, the results of partial least squares regression slightly outperformed support vector machine regression, with correlation coefffcient for prediction (Rp) of 0.9697, 0.9716, and 0.9098 for MC, TA, and AAN, respectively. The study demonstrates that HSI can be employed for rapid non-destructive monitoring and quality assessment of the fumigation process in SAV.

Keywords：Shanxi aged vinegar; Fumigation proces; Hyperspectral imaging technology; Nondestructive detection; Chemometric algorithms