Sustainability
AI Can Help Cut Down on Waste, Improve Quality in Dyed Fabrics
By Warren J. Jasper and Samuel M. Jasper at the Department of Textile Engineering, Chemistry & Science, North Carolina State University, Raleigh, NC
A new study finds that machine learning can help reduce textile manufacturing waste by more accurately mapping how colors will change during the dyeing process.
Fabrics are typically dyed while wet, and their colors change as they dry. This can make it challenging to know what a piece of fabric will end up looking like in its finished state, said Warren Jasper, professor in the Wilson College of Textiles and author of a paper on the study.
“The fabric is dyed while wet, but the target shade is when it’s dry and wearable. That means that, if you have an error in coloration, you aren’t going to know until the fabric is dry,” Jasper said. “While you wait for that drying to happen, more fabric is being dyed the entire time. That leads to a lot of waste, because you just can’t catch the error until late in the process.”
The amount of color change from a wet to a dry state is not uniform across different colors. This non-linear relationship means that the amount of color change between wet and dry is unique to each color, and data from one color sample cannot be easily transferred to another.
To tackle this problem, Jasper developed five machine learning models, including a neural network designed specifically to map this type of non-linear relationship. He then trained the models by inputting visual data from 763 fabric samples of various colors, both wet and dry. Each dyeing took several hours to complete, Jasper said, which made collecting data a significant undertaking. While all of these models outperformed non-machine learning models in terms of accuracy, the neural network stood out as significantly more accurate than any other option. The neural network demonstrated an error as low as 0.01 and a median error of 0.7 using CIEDE2000, a standardized formula for color difference. The other machine learning models showed CIEDE2000 error ranges of anywhere between 1.1 to 1.6, while the baseline went as high as 13.8. In the textile industry, CIEDE2000 values exceeding 0.8 to 1.0 are generally considered to be outside acceptable limits.
This neural network has the potential to significantly reduce waste caused by color errors, as it would enable fabric manufacturers to better predict the end result of the dyeing process before large amounts of fabric are incorrectly dyed. Jasper said that he hopes to see similar machine learning tools adapted more broadly in the textile industry.
“We’re a bit behind the curve in textiles. The industry has started to move more toward machine learning models, but it’s been very slow,” he said. “These types of models can offer powerful tools in cutting down on waste and improving productivity in continuous dyeing, which accounts for over 60% of dyed fabrics.” The paper, “A Controlled Study on Machine Learning Applications to Predict Dry Fabric Color from Wet Samples: Influences of Dye Concentration and Squeeze Pressure,” is published in Fibers.
“We’re a bit behind the curve in textiles. The industry has started to move more toward machine learning models, but it’s been very slow,” he said. “These types of models can offer powerful tools in cutting down on waste and improving productivity in continuous dyeing, which accounts for over 60% of dyed fabrics.” The paper, “A Controlled Study on Machine Learning Applications to Predict Dry Fabric Color from Wet Samples: Influences of Dye Concentration and Squeeze Pressure,” is published in Fibers.