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

Colored spun yarn color matching method based on neural network

A neural network and BP neural network technology, applied in the field of textile color matching, can solve problems such as poor applicability and poor generalization ability

Active Publication Date: 2016-07-20
JIAXING UNIV
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional model is limited by the assumptions in the derivation process, and its applicability is poor when it is applied to different fibers or processes used in the derivation. The artificial neural network has excellent nonlinear mapping capabilities, but when it is completely dependent on the free fitting of the neural network, Often poor generalization ability

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
  • Colored spun yarn color matching method based on neural network
  • Colored spun yarn color matching method based on neural network
  • Colored spun yarn color matching method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] This embodiment relates to a method for color-spun yarn color matching based on a neural network. The main steps include: (1) measuring the reflectance of the standard sample (R5B95) and converting it into a model reflectance; the measurement uses a Datacolor600 spectrophotometer with a wavelength range of 400 ~700nm, the wavelength interval is 10nm. use R s1 Indicates that the R s1 Substitute into the formula (1) of the color matching model, and convert it into the reflectance of the standard sample model F(R s1 ). (2) Use the BP neural network to calculate the weight-average model reflectance Fw(Rs1); take F(Rs1) as the input layer, apply the trained BP neural network to calculate, and obtain Fw(Rs1), (3) use the constrained least squares The multiplication algorithm is used to obtain the prediction scheme of formula C; the weight-average model reflectance Fw(Rs1) is fitted with the monochromatic model reflectance F(Ri), and the calculation is performed under the c...

Embodiment 2

[0052] This embodiment relates to a color-spinning color matching method based on a neural network. The main steps include: (1) measuring the reflectance of the standard sample (Y25G75) and converting it into a model reflectance; the measurement uses a Datacolor600 spectrophotometer with a wavelength range of 400 ~700nm, the wavelength interval is 10nm. It is represented by Rs2, and Rs2 is substituted into the color matching model formula (1) to convert it into the reflectance F(Rs2) of the standard sample model. (2) Use the BP neural network to calculate the weight-average model reflectance Fw(Rs2); take F(Rs2) as the input layer, apply the trained BP neural network to calculate, and obtain Fw(Rs2), (3) use the constrained least squares Multiplication algorithm to obtain the prediction scheme of formula C; use the monochrome model reflectance F(Ri) to fit the weight average model reflectance Fw(Rs2), and perform calculations under the constraint conditions to obtain formula C...

Embodiment 3

[0054] This embodiment relates to a color-matching method for color spinning yarn based on neural network. The main steps include: (1) measuring the reflectance of the standard sample (W45D55) and converting it into a model reflectance; the measurement uses a Datacolor600 spectrophotometer with a wavelength range of 400 ~700nm, the wavelength interval is 10nm. It is represented by Rs3, and Rs3 is substituted into the color matching model formula (1) to convert it into the standard sample model reflectance F(Rs3). (2) Use the BP neural network to calculate the weight-average model reflectance Fw(Rs3); take F(Rs3) as the input layer, apply the trained BP neural network to calculate, and obtain Fw(Rs3), (3) use the constrained least squares The multiplication algorithm is used to obtain the prediction scheme of formula C; the weight-average model reflectance Fw(R) is fitted with the monochrome model reflectance F(Ri), and the calculation is performed under the constraint conditio...

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 colored spun yarn color matching method based on a neural network. The method comprises the following steps of: (1) measuring a standard sample reflectivity, and converting the standard sample reflectivity into a model reflectivity; (2) utilizing a BP neural network to calculate a weight-average model reflectivity F(Rw); (3) utilizing a constraint least square method to obtain a formula C forecast scheme; (4) according to the forecasted formula, carrying out sample making, and measuring the reflectivity Rp of the sampled color; and (5) calculating the color difference between the standard sample reflectivity Rs and the reflectivity Rp of the sampled color, if the color difference meets a set requirement, completing color matching, and if not, entering a formula correcting program.

Description

technical field [0001] The invention designs a neural network-based color-matching method for melange spinning yarn, which belongs to the technical field of textile color-matching. Background technique [0002] Colored spinning is a process in which two or more dyed fibers of different colors are fully mixed and spun to form yarns with unique color effects. This production method is becoming more and more popular in the textile industry. Its advantages are mainly manifested in In the following aspects, 1) Prioritize the use of raw cotton (undyed cotton) as a basic color for color matching, which greatly reduces the amount of fiber that needs to be dyed; 2) For dyeing factories, dyeing specific colors all year round is beneficial Control and stability of color quality; 3) For dope dyed fibers with only dozens of colors, this production method can greatly enrich their colors; 3) For blended products, using this production method, different types of fibers are dyed separately ...

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): G06N3/08
CPCG06N3/082
Inventor 沈加加
Owner JIAXING UNIV
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