Analysis of the Conditions of Luzhou-Flavor Liquor Based on Information Fusion

Haijiao Luo, Ge Li, Yi YaoOALib 2019 · DOI

Abstract

The fermentation process of Luzhou-flavor liquor is almost uncontrollable, and at the same time, in his production process, the fermentation method is utilized. Therefore, eel conditions are an important reference indicator for liquor fermentation. In the study of the conditions for the emergence of Luzhou-flavor liquor, the quantitative evaluation of the conditions of liquor discharge was achieved by the cloud model and the improved D-S (Dempater-Shafer) evidence theory. There are five main factors that have a profound influence on the sputum conditions, namely temperature, moisture, acidity, starch content and reducing sugar. The membership degree cloud model is established by Matlab simulation for the out-of-the-box condition, so that each parameter has its corresponding membership function. The collected sample parameters are used to realize the membership degree of each evaluation standard through the cloud model, and the sample data are analyzed by using the improved D-S evidence theory. Through experimental analysis, the outburst condition of liquor can reach a more accurate quantitative analysis, so as to guide the fermentation process of Luzhou-flavor liquor, and then improve its yield and quality.

Introduction

The production of Luzhou-flavor liquor relies on a complex, anaerobic, solid-state fermentation process that has historically been treated as a "black box." Traditionally, master brewers have relied on "artificial experience"—subjective sensory inputs like touch, smell, and sight—to evaluate the state of the fermentation cellar. However, this reliance on intuition makes it difficult to standardize quality and optimize yields.

Fermentation is influenced by five volatile and interacting factors: temperature, moisture, acidity, starch content, and reducing sugar. Because these variables are inherently "fuzzy" (e.g., the boundary between "suitable" and "more suitable" is not discrete), traditional rigid mathematical models often fail. This paper proposes a quantitative framework that combines Cloud Models and an improved Dempster-Shafer (D-S) evidence theory to transform qualitative brewing expertise into precise, data-driven evaluations.

Methodology

The Cloud Model for Qualitative-Quantitative Transformation

The first stage of the proposed approach involves the Cloud Model, which is designed to handle the dual challenges of fuzziness (ambiguity in definitions) and randomness (stochastic data variance). Unlike standard fuzzy logic, the Cloud Model uses three specific parameters to define a membership function: Expectation ($Ex$), Entropy ($En$), and Super-entropy ($He$).

By simulating these parameters in Matlab, the researchers mapped sensor readings to suitability grades ranging from "Not Suitable" to "Suitable."

Cloud model distribution for reducing sugar content, mapping quantitative values to qualitative suitability grades.

Information Fusion via Improved D-S Evidence Theory

Once the five key factors are quantified via the Cloud Model, their individual "evidence" must be fused to reach a final diagnostic verdict. Standard D-S theory often struggles when different sensors provide conflicting information—a common occurrence in the harsh environment of a fermentation cellar.

The authors improved the D-S theory by implementing a weighting system that calculates an average mass function and determines the deviation of each piece of evidence. This assigns a "Credibility Rating Factor" so that outlier data or conflicting evidence has a reduced influence on the final result, ensuring the model remains robust even if a single sensor malfunctions.

Cloud model distribution for moisture content, illustrating the fuzzy boundaries between suitability levels.

Experimental Results and Discussion

The framework was validated using a real-world dataset of five samples (Sample 0 through Sample 4) collected from a Luzhou-flavored winery. Sample 0 represented optimal "suitable" conditions, while Samples 1-4 represented various deviations (e.g., high moisture or low acidity).

The system demonstrated high precision in categorizing the cellar states:

  • Optimal Conditions (Sample 0): The model achieved a 97.23% certainty rating for the "Suitable" classification at the highest reliability level.
  • Minor Deviations (Sample 1): Correctly identified as "More Suitable" with 98.34% certainty, effectively flagging high moisture levels.
  • Suboptimal Conditions (Sample 3): Successfully categorized as "Not Suitable" with 98.25% certainty due to low acidity and high starch content.

Conclusion

This research provides a mathematical bridge between traditional brewing intuition and modern industrial control. By quantifying the "gray areas" of fermentation using Cloud Models and resolving data conflicts through improved D-S theory, the system offers a reliable preliminary judgment for brewers. While future work is needed to integrate these algorithms into real-time hardware, this framework represents a significant step toward the intelligent, data-driven production of Luzhou-flavor liquor.

Summary updated

Abstract

The fermentation process of Luzhou-flavor liquor is almost uncontrollable, and at the same time, in his production process, the fermentation method is utilized. Therefore, eel conditions are an important reference indicator for liquor fermentation. In the study of the conditions for the emergence of Luzhou-flavor liquor, the quantitative evaluation of the conditions of liquor discharge was achieved by the cloud model and the improved D-S (Dempater-Shafer) evidence theory. There are five main factors that have a profound influence on the sputum conditions, namely temperature, moisture, acidity, starch content and reducing sugar. The membership degree cloud model is established by Matlab simulation for the out-of-the-box condition, so that each parameter has its corresponding membership function. The collected sample parameters are used to realize the membership degree of each evaluation standard through the cloud model, and the sample data are analyzed by using the improved D-S evidence theory. Through experimental analysis, the outburst condition of liquor can reach a more accurate quantitative analysis, so as to guide the fermentation process of Luzhou-flavor liquor, and then improve its yield and quality.
BibTeX
@inproceedings{luo2019analysis,
  author = {Haijiao Luo and Ge Li and Yi Yao},
  title = {{Analysis of the Conditions of Luzhou-Flavor Liquor Based on Information Fusion}},
  booktitle = {OALib},
  year = {2019},
  doi = {10.4236/oalib.1105754},
}
Figure