Discrimination method of Maotai-flavor liquor brewing process based on support vector machine
A sauce-flavored liquor and support vector machine technology, which is applied in manufacturing computing systems, computer components, character and pattern recognition, etc., can solve the problems of strong subjectivity of sensory evaluation, limited experience of evaluators, and long time spent , to achieve the effect of maintaining word of mouth and quality, low instrument price, and simple sample preparation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0050] 1. Collect samples of Maotai liquor from different manufacturers in Maotai Town, Guizhou Province (30 authentic Daqu Maotai liquor, 37 non-authentic Daqu Maotai liquor), and collect infrared spectra. Instrument: Bruker Tensor 27 Fourier transform infrared spectrometer, ATR crystal is Ge, 17 reflections. Acquisition parameters: 4000-650cm -1 , resolution 8cm -1 , scan 32 times. The scanning background was absolute ethanol, and the washing solution was absolute ethanol.
[0051] Table 1 Sample Details
[0052]
[0053]
[0054] 2. Hotelling's T 2 After analysis, no abnormal sample points were found, and all data entered the next step of modeling.
[0055] 3. SVM model establishment
[0056] (1) Import the data into The Unscrambler 10.4, keep 650cm -1 and 4000-700cm -1 Spectral preprocessing, including the following processing (single or superimposed): no processing (RAW), smoothing (Smoothing), normalization (Normalize), first-order derivative (1st Derivativ...
Embodiment 2
[0071] 1. Collect 18 broken sand wines and 30 Kunsha wines from different manufacturers in Maotai Town, Guizhou Province, and collect infrared spectra. Instrument: Bruker Tensor 27 Fourier transform infrared spectrometer, ATR crystal is Ge, 17 reflections. Acquisition parameters: 4000-650cm -1 , resolution 8cm -1 , scan 32 times. The scanning background was absolute ethanol, and the washing solution was absolute ethanol.
[0072] 2. Hotelling's T 2 After analysis, no abnormal sample points were found, and all data entered the next step of modeling operation (the comparison step is only for data verification, not every experiment needs to eliminate samples).
[0073] 3. Spectral data processing
[0074] (1) Import the data into The Unscrambler 10.4, for 4000-700cm -1 Spectral preprocessing, including the following processing (individually or superimposed): no processing (RAW), smoothing (Smoothing), normalization (Normalize), first-order derivative (1stDerivative), second...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com