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

Printing ink presetting method based on artificial neural network algorithm

An artificial neural network and ink technology, applied in the field of ink presets based on artificial neural network algorithms, can solve problems such as running counter to each other, and achieve the effects of improving accuracy, improving printing quality and efficiency, and improving preset and prediction accuracy

Pending Publication Date: 2022-06-28
TIANJIN HAISHUN PRINTING & PACKAGING
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Sometimes the preset results even run counter to the real results, and the difference is far

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
  • Printing ink presetting method based on artificial neural network algorithm
  • Printing ink presetting method based on artificial neural network algorithm
  • Printing ink presetting method based on artificial neural network algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Below, in conjunction with the accompanying drawings and specific embodiments, the invention is further described:

[0050] see Figure 3-4 , according to an embodiment of the present invention, an ink preset method based on an artificial neural network algorithm includes the following steps:

[0051] Step S1: establish a three-layer neural network ink preset model;

[0052] Step S2: Input layer x 1 is the average ink coverage of the corresponding ink area on each color printing plate, the value range is [0,1]; x 2 Describes the viscosity and fluidity of printing ink, the value range is [0,1], the larger the value, the higher the ink viscosity; x 3 Describes the glossiness of the substrate surface. The value range is [0,1]. The smoother the substrate surface, the larger the value.

[0053] Step S3: The hidden layer is the fully connected layer of the input layer. The calculation formula of the hidden layer neurons is: i =w i X+b i , where w i is the weight coef...

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 printing ink presetting method based on an artificial neural network algorithm. The printing ink presetting method comprises the following steps: S1, establishing a three-layer neural network printing ink presetting model; s2, the content of the input layer comprises the average ink coverage rate, the viscosity and fluidity of printing ink and the surface glossiness of a printing stock; s3, the hidden layer is a full connection layer of the input layer; s4, the input of the output layer comes from the calculation result of the hidden layer through the activation function g (z); s5, using empirical data to initialize model parameters; s6, arranging a model training data set; s7, substituting the sorted training data into the established three-layer neural network ink preset model; s8, optimizing the eight model parameters according to the error between the model output y value and the true value Y; and S9, substituting the three parameters corresponding to the new movable part into the optimized model in the step S8 to calculate the corresponding ink tooth opening degree. The device has the beneficial effects that the printing ink presetting accuracy is improved, and the printing quality and efficiency are improved.

Description

technical field [0001] The invention relates to the field of printing, in particular to an ink presetting method based on an artificial neural network algorithm. Background technique [0002] In the offset printing process, the depth of the final print is adjusted by controlling the ink opening of the offset press to achieve accurate reproduction and printing effects. Therefore, according to the depth distribution of the printed graphics, adjusting the opening of each ink tooth of the printing press is a key part of the printing process. The size of the opening of the ink teeth directly affects the quality of the printed matter. [0003] The traditional method is to rely on the captain of the printing press to adjust a relatively reasonable opening based on his own experience, start the test, and then iteratively optimize according to the test results until the printed effect reaches the expected or proof effect. This process is called the color correction process of the p...

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): G06N3/04G06N3/08B41F33/00
CPCG06N3/084B41F33/0036G06N3/044G06N3/045
Inventor 张宗祥李冠达
Owner TIANJIN HAISHUN PRINTING & PACKAGING
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