The Spectral Characterizing Model Based on Optimized RBF Neural Network for Digital Textile Printing

Fan

et al. 2021

Sensors

Nonwoven fiber materials are materials with multifunctional purposes, and are widely used to make masks for preventing the new Coronavirus Disease 2019. Because of the complexity and particularity of their structure, it becomes difficult to model the penetration and flow characteristics of liquid in nonwoven fiber materials. In this paper, a novel seepage time soft sensor model of nonwoven fabric, based on Monte Carlo (MC), integrating extreme learning machine (ELM) (MCELM) is proposed. The Monte Carlo method is used to expand data samples. Then, an ELM method is used to establish the prediction model of the dyeing time of the nonwoven fiber material overlaps with the porous medium, as well as the insertion degree and height of the different quantity of hides. Compared with the back propagation (BP) neural network and radial basis function (RBF) neural network, the results show that the prediction model based on the MCELM method has significant power in terms of accuracy and prediction speed, which is conducive to the precise and rapid manufacture of nonwoven fiber materials in practical applications between liquid seepage characteristics and structural characteristics of porous media. Furthermore, the relationship between the proposed models has certain value for predicting the behavior and use of nonwoven fiber materials with different structural characteristics and related research processes.

Section: Related Workmentioning

confidence: 99%

Seepage Time Soft Sensor Model of Nonwoven Fabric Based on the Extreme Learning Machine Integrating Monte Carlo

Fan

et al. 2021

Sensors

“…Here, the literature on characterizing the color of print on fabrics presents a variety of approaches, with different levels of color accuracy. Early solutions were attempted via linear models 1,2 , followed by a direct application of ICC color management 3 (with 95 th percentiles of ∆E2000 errors above 6) and the use of neural networks 4 (yielding prediction errors with a mean of 1.89 ∆E00, 90 th percentile of 2.8 ∆E00 and a maximum of 8.5 ∆E00), already well established for recipe formulation when dyeing fabrics 5 . Also, relevant here is the rich and extensive literature on print color prediction on non-textile materials 6,7 , where Neugebauer-based approaches 8 , the Kubelka-Munk equations 9 , the use of polynomials, and that of neural networks are all common, as are combinations of such basic predictive components 10 .…”

Section: Introductionmentioning

confidence: 99%

Color printing on pre-colored textiles

Morovic¹,

Morovič²,

Etchebehere³

2021

cic

Managing color on a particular imaging system is a wellunderstood challenge with a wealth of existing models, methods and techniques. In the case of printing systems, these tend to operate in the context of a single substrate, where managing color on every additional substrate is approach as a separate, detached problem. While such a mind-set works reasonably well in general, it breaks down when it comes to printing onto precolored textiles, such as pre-dyed fabrics. The present paper therefore introduces a family of approaches that support the use of multiple pre-colored textiles on a given printing system that also allow for a balance between characterization effort and color match accuracy. This, in turn provides solutions that can fit a variety of practical working patterns to maximize overall efficiency and performance.

Color Research & Application

“…Artificial neural network technique has received much attention in color imaging, printer characterization, color matching of dyeing and printing, and modeling of nonlinear problems in recent years . A neural network can be trained to solve complex problems such as transformation between the color spaces, color prediction, halftone dot prediction model and printer characterization . A common neural network has at least three layers.…”

Section: Introductionmentioning

confidence: 99%

“…15 A neural network can be trained to solve complex problems such as transformation between the color spaces, color prediction, halftone dot prediction model and printer characterization. 13,[15][16][17][18][19] A common neural network has at least three layers. The first layer is the input layer that gives the inputs from an external source.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improve neural network‐based color matching of inkjet textile printing by classification with competitive neural network

Hajipour

Shams‐Nateri

2018

Nowadays, with increasing use of digital printing in the textile industry, characterization and color matching are very much considered. There is a very complicated relationship between pixel values of input digital image and colorimetric parameters of printed textile samples. One of the most important used methods for inverse characterization of printer and prediction of CMYK digital values is neural network. In this study, the prediction accuracy of CMYK digital values were improved by dividing the training samples into 2, 4, 6, 8, and 10 subgroups using creating a competitive neural network. For classification of samples, L*a*b* or XYZ were introduced to a competitive neural network as input parameters. Then, the classification of test samples was performed by trained competitive neural network. To predict the of CMYK digital values of input digital image, a cascade‐forward back propagation neural network is trained by L*a*b* of each subgroup. The results obtained show that the prediction accuracy of CMYK digital values were improved by suggested method. The best result was obtained by classification of samples with L*a*b* into eight subgroups and using a cascade‐forward back propagation neural network with 4, 4, and 4 neurons in hidden layers.