Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Moisture Content Prediction Method Based on Damping Factor Adaptive lm Algorithm

A technology of damping factor and LM algorithm, which is applied in the direction of adaptive control, weighing by removing certain components, and analyzing materials, can solve the problems of complex algorithm, high equipment cost, unfavorable prediction algorithm design and popularization and application, etc.

Active Publication Date: 2020-06-09
NINGXIA UNIVERSITY +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the mathematical models of the existing prediction methods are empirical or semi-empirical drying models, which only target the drying process of samples with a certain moisture content, and the universality verification of the models is not mentioned. The analysis and research of the mechanism, the realization algorithm of the prediction fusion algorithm is relatively complicated, and the equipment cost is high, which is not conducive to the design and promotion of the prediction algorithm in the single-chip computer system.

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
  • A Moisture Content Prediction Method Based on Damping Factor Adaptive lm Algorithm
  • A Moisture Content Prediction Method Based on Damping Factor Adaptive lm Algorithm
  • A Moisture Content Prediction Method Based on Damping Factor Adaptive lm Algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0053] Specific implementation mode 1: This implementation mode is a method for estimating moisture content based on the damping factor adaptive LM algorithm, such as figure 1 shown, including the following steps:

[0054] 1) Before implementing the moisture content estimation and determination, judge the initial moisture content of the tested sample, consider the moisture distribution uniformity and particle size of the sample, and based on the analysis of the infrared drying mechanism and characteristics of solid materials, different The solid material infrared drying process selects the corresponding prediction fusion mathematical model; the described moisture content prediction fusion mathematical model is divided into two categories:

[0055] One type of model is suitable for the tested samples with medium and low moisture content and uniform moisture distribution, the expression is:

[0056]

[0057] The second type of model is suitable for the tested samples with hi...

specific Embodiment approach 2

[0073] Specific embodiment two: this embodiment is a limitation of embodiment one, wherein the damping factor λ in step 4) is updated in an adaptive iterative manner, as image 3 As shown, the steps are as follows:

[0074] (1) Initialize the parameters and thresholds of the algorithm: the estimated model parameter vector is used Indicates that the calculation situation is given according to the derivation of the mathematical model The initial value of , set the number of iteration steps to 1, and set the lower limit threshold of the adaptive factor ω min = 0.0001, classification threshold ω 1 = 0.85, ω 2 =0.95, satisfying 0min 1 2 0 = 0.0001;

[0075] (2) Calculate the damping factor and substitute it into the calculation iteration step size d l :

[0076]

[0077] (3) Judging the value range of the selection index θ, when the selection index θ l ≤ 0 hold parameter vector At the same time, increase the adaptive adjustment factor ζ l+1 =10ζ l To increase the da...

specific Embodiment approach 3

[0081] Specific embodiment three: this embodiment is a limitation to embodiment one or two, and the initial value setting of the parameter k in the step 4) adopts M ∞ =0.1%, η=1.23, a=0.01, ρ=0.01.

[0082] The present invention will be further described in detail through specific examples below. It should be understood that the specific examples described here are only used to explain the present invention, and are not intended to limit the present invention.

[0083] The moisture content was estimated by using corn flour purchased from China Resources Vanguard Supermarket in Yinchuan City and fresh pork samples purchased from farmers’ markets. Corn flour was prepared according to the provisions of "GB / T 10362 Method for Determination of Moisture Content in Corn and Oil Determination of Corn", and fresh pork samples were prepared according to the provisions of "GB / T 9695.19-2008 Determination of Moisture Content in Meat and Meat Products". Pork tenderloin of fat, sinew and t...

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 discloses a damping factor self-adaptive LM (Levenberg-Marquardt) algorithm based moisture content prediction method. The damping factor self-adaptive LM algorithm based moisture contentprediction method comprises the steps of selecting a mathematical model, calculating and predicating a starting point, predicating and fusing the moisture content, predicating a terminal point, self-adaptively judging and the like. A predicating and fusing model is established to adapt to different samples, the adaptability of the method is strengthened, and the robustness and the fast convergence of the method are strengthened through the adaptive control of a damping factor. The method can accurately predicate the moisture content effectively when the sample is not completely dried, the calculated quantity is small, the efficiency is high, the practicality is high, and the embedded realization of the method is easy.

Description

technical field [0001] The invention relates to the field of moisture content detection methods, in particular to a moisture content estimation method based on a damping factor adaptive LM algorithm. Background technique [0002] Moisture content is an important indicator to determine the physical, chemical and biological characteristics of substances. The moisture distribution in substances is complex and greatly affected by external factors, making it difficult to achieve rapid and accurate determination. The determination of the moisture content of substances is widely used in enterprises and measurement departments in the fields of food, grain, medicine, and chemical industry. It has positive social significance and huge economic value for the construction of the national economy. There is a strong demand for rapid moisture determination methods in the market. [0003] At present, the common moisture detection methods are mainly the drying weight loss method and the ind...

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
IPC IPC(8): G01N5/04G05B13/04
CPCG01N5/045G05B13/042
Inventor 凌菁滕召胜
Owner NINGXIA UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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