Kiln muddy water prediction model establishment method based on hyperspectral image technology

A hyperspectral image and predictive model technology, applied in the field of solid-state fermentation index detection, can solve the problems of easily missing important information and single modeling methods

Active Publication Date: 2019-11-12
SICHUAN UNIVERSITY OF SCIENCE AND ENGINEERING
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The shortcomings of the above patents are: only images and spectral information in the visible light region are collected, but the pre-test and data query found that water has obvious absorption in both visible light and near-infrared bands, and the absorption of the latter is stronger; Without comparison between the full spectrum and the characteristic spectrum, the spectral information corresponding to the characteristic wavelength is directly selected as the input variable of the model, which is easy to miss important information; without preprocessing and denoising, it is easy to include non-sample signals into the calculation; the modeling method is single

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Kiln muddy water prediction model establishment method based on hyperspectral image technology
  • Kiln muddy water prediction model establishment method based on hyperspectral image technology
  • Kiln muddy water prediction model establishment method based on hyperspectral image technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The process flow for establishing the quantitative prediction model of pit mud moisture is as follows: figure 1 Shown.

[0036] (1) Pit mud sample collection: The samples were collected from a well-known winery in Yibin City, Sichuan Province. When sampling, the workers dig out the missing lees and use yellow water as the dividing line to collect the pit mud around the same level with a shovel and use it. The sampling bag is sealed to form a sample. The sampling location of the same pit includes three layers of pit cap, yellow water and bottom mud, totaling 3 samples. A total of 108 pieces of pit mud of different ages were obtained in this way.

[0037] (2) Hyperspectral acquisition system: use Finnish SPECIM FX17 series hyperspectral cameras, 2 sets of 160W Y-type fiber halogen lamps as the light source, use LUMO Scanner software to control the camera and precision electronic control stage for spectral data acquisition.

[0038] (3) Parameter setting and spectral data collec...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a kiln muddy water optimal prediction model establishment method based on a hyperspectral image technology; the method comprises the steps of acquiring hyperspectral image information of near-infrared and visible light wave bands, performing black-and-white correction to eliminate errors caused by uneven illumination, extracting the average spectral information of the region of interest, estimating the average spectral reflectivity of each pixel point in the image, and separately establishing quantitative prediction models based on the full-wave band and the characteristic spectrum through unprocessed and SNV and different modeling methods. According to the method, the optimal model for the kiln muddy water quantitative prediction is screened out through a comparison training set, a test set quantitative prediction and the value of the root-mean-square error; the quality of the kiln mud is quickly evaluated for each large liquor brewing enterprise, a theoretical basis and technical support are provided for manual kiln protection and kiln protection, and technical guarantee is provided for transformation upgrading and digital and intelligent on-line real-time monitoring of the fermentation state of the kiln mud for wine brewing industrialization.

Description

Technical field [0001] The invention relates to a method for establishing a pit mud moisture prediction model based on hyperspectral image technology, and belongs to the technical field of solid fermentation index detection. Background technique [0002] Solid-state fermentation technology has a long history in my country, and it is also a unique brewing process in my country. In the liquor brewing industry, pit mud is the basis of fermentation. Among them, the beneficial microbial flora, mainly caproic acid bacteria, uses the nutrients in the fermented grains to produce acid and esters. Ethyl caproate is the main body of Luzhou-flavor liquor. Fragrance components, so pit mud plays a decisive role in the quality of Luzhou-flavor liquor in the production process, and it is more important to evaluate the quality of pit mud. Without good pit mud, you cannot produce good quality wine. [0003] Water is the basis for the survival of beneficial microorganisms in pit mud. At present, t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/31G01N21/3554G01N21/3577G01N21/359G06K9/00G06K9/20G06K9/32G06K9/62
CPCG01N21/31G01N21/3554G01N21/3577G01N21/359G06V10/143G06V10/25G06F2218/08G06F18/2113G06F18/214
Inventor 田建平朱敏罗惠波黄丹陈平叶建秋
Owner SICHUAN UNIVERSITY OF SCIENCE AND ENGINEERING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products