Method for quickly detecting quality stability of tobacco essence based on similarity learning algorithm

Abstract

The invention discloses a method for quickly detecting quality stability of tobacco essence based on a similarity learning algorithm. The method comprises the following steps: acquiring spectra of a plurality of to-be-tested tobacco essence samples and standard tobacco essence as to-be-tested spectra and standard sample spectra; obtaining a distance matrix between the plurality of to-be-detected tobacco essence samples and the standard sample spectrum; and according to the distance matrix, obtaining the similarity between the comprehensive quality of the plurality of to-be-detected tobacco essence samples and the standard tobacco essence, and taking the similarity as the quality stability of the plurality of to-be-detected tobacco essence samples. According to the invention, the mass of the solid essence is judged on the whole based on the distance similarity and the spectral analysis method, calculation is carried out according to the essence spectrum characteristics, the obtained distance difference does not change along with the change of the range and the number of samples under the condition that the standard sample spectrum is fixed, the algorithm is simple and easy to implement, the obtained mass parameter data value is constant, the defects of the existing near-infrared quality detection are overcome, and the quality fluctuation reflected by the detection result is intuitive and clear.

Description

technical field [0001] The invention relates to the technical field of cigarette manufacturing, and more particularly relates to a method for quickly checking the quality stability of tobacco flavorings based on a similarity learning algorithm. Background technique [0002] In the production process of cigarettes, in order to improve the smoking quality of cigarettes, it is necessary to use various flavors for tobacco. Tobacco flavor is a mixture made of various spices and an appropriate amount of solvent. Due to the influence of various factors such as raw material origin and processing technology, the product quality has certain fluctuations. Therefore, essence for tobacco plays an important role in improving the quality of tobacco products. [0003] At present, most cigarette manufacturers mainly evaluate the quality of tobacco flavors through spectral analysis based on the principal component analysis (PCA) method, but the correlation coefficient in the PCA analysis met...

AI Technical Summary

Problems solved by technology

[0003] At present, most cigarette manufacturers mainly evaluate the quality of tobacco flavors through spectral analysis based on the principal component analysis (PCA) method, but the correlation coefficient in the PCA analysis method comes from the linear addition of all sample spectra involved in the calculation. And, the correlation coefficient will change with the change of the sample range, and the composition of most tobacco flavors is very complex, so it is difficult to reflect the comprehensive quality of tobacco flavors by analyzing some of the chemical components

In addition, the existing detection methods for the quality of tobacco flavors are cumbersome and require many instruments

Images