| Author: | Liu, Senbiao |
| Title: | Systematic study of industrial scale sustainable colour fading process of cotton fabric |
| Advisors: | Kan, Chi-wai (SFT) Lo, Kwan-yu Chris (SFT) |
| Degree: | Ph.D. |
| Year: | 2023 |
| Subject: | Plasma chemistry -- Industrial applications Textile chemistry Cotton fabrics Dyes and dyeing Hong Kong Polytechnic University -- Dissertations |
| Department: | School of Fashion and Textiles |
| Pages: | xvii, 180 pages : color illustrations |
| Language: | English |
| Abstract: | Plasma treatment is an environmentally friendly fading method that requires constant adjustment to obtain accurate fading results. However, the mechanism by which variations in plasma treatment parameters affect fading results is still unclear. Through a systematic review of how artificial intelligence techniques had been applied to the textile colour fading field, it had been found that the application of artificial intelligence techniques might be able to predict well what fading results would result from different plasma treatment parameters. This study used a Bayesian Regulated Neural Network (BRNN) with 10-fold cross-validation to accurately predict the fading effect of plasma treatment on cotton fabrics for given parameters. This prediction system used a modular approach, with multiple independent models trained to avoid the effects of small sample sizes further. The inputs included plasma treatment parameters and colour measurements of the cotton fabric before fading, while the outputs included colour measurements after fading. Plasma treatment parameters included colour depth, air (oxygen) concentration, water content and treatment time. Colour measurements included CIE L*a*b*C*h values and K/S values. The datasets collected for model training in this study were divided into three categories, namely 216 datasets of reactive dye-dyed cotton fabrics, 216 datasets of sulphur-dyed cotton fabrics and 162 datasets of two-colour mixed-dyed cotton fabrics. The coefficient of determination R2 of the model fit was close to 1. Moreover, the difference between the predicted and actual colours was negligible or within acceptable limits for the different colour difference formulas for 82.35% to 95.83% of the test set samples. In addition, polynomial regression models were used in this study to investigate the relationship between the single-colour fading effect and the two-colour mixed fading effect of plasma-treated cotton fabrics. In most cases, the colour characteristics of the two-colour mixed fading effect of plasma-treated cotton fabrics might be predicted from the known single-colour fading effect of plasma-treated cotton fabrics. It was found that the relatively low R2 of the polynomial regression model on the CIE L* values might reflect the relatively poor relationship between the lightness levels of the single-colour fading effect and the two-colour mixed fading effect of plasma-treated cotton fabrics. In contrast, the R2 of the polynomial regression models for CIE a* values, CIE b* values and K/S values were all above 0.99, suggesting that the relationship between the single-colour fading effect and the two-colour mixed fading effect might be more reflected in the colour-related CIE a* and CIE b* values, or in the K/S values related to the dyeing level. |
| Rights: | All rights reserved |
| Access: | open access |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/12541