Namangan Institute of Engineering and Technology
nammti.uz
10.25.2023
Pg.373
Abstract. Artificial intelligence (AI) technologies are rapidly transforming the textile industry,
including in the area of quality control. AI-powered systems can be used to automate and improve
the accuracy of quality testing, leading to significant benefits for textile manufacturers.This article
reviews the use of AI technologies in the determination and analysis of quality indicators of textile
materials. It discusses the different types of AI methods that can be used, as well as the specific
applications of AI in quality control. The article also highlights the challenges and opportunities in
the use of AI for textile quality control.
Keywords: artificial intelligence, textile quality control, quality indicators, machine learning,
deep learning, image processing
Introduction.The textile industry is one of the oldest and most important industries in the
world. Textile materials are used in a wide range of products, from clothing and home furnishings
to industrial applications. The quality of textile materials is essential
for the performance and
durability of these products.
Traditional textile quality control methods are often time-consuming and labor-intensive.
They also rely on human experts to interpret the results of tests. This can lead to errors and
inconsistencies. AI technologies offer a promising solution for improving the efficiency and accuracy
of textile quality control.
There are a variety of AI technologies that can be used for textile quality control. Some of the
most common methods include:
Machine learning: Machine learning algorithms can be trained on large datasets of textile
quality data to learn to identify patterns and make predictions. For example,
machine learning
algorithms can be used to predict the tensile strength of a fabric based on its fiber composition and
weave structure.
Deep learning: Deep learning is a type of machine learning that uses artificial neural
networks to learn from data. Deep learning algorithms can be used to solve complex problems that
are difficult or impossible to solve using traditional machine learning algorithms. For example, deep
learning algorithms can be used to classify textile defects from images.
Image processing: Image processing techniques can be used
to extract information from
textile images, such as fiber orientation, yarn count, and fabric weave structure. This information
can then be used to assess the quality of the textile material.
Applications of AI in Textile Quality Control
AI technologies can be used in a variety of ways to improve textile quality control. Some of
the specific applications include:
Automated defect detection: AI-powered systems can be used to automatically detect
defects
in textile materials, such as broken yarns, holes, and stains.
This can help to reduce the
number of defective products that reach the market.
Quality prediction: AI-powered systems can be used to predict the quality of textile materials
based on their properties. This information can be used to optimize the production process and
ensure that products meet quality standards.
Process monitoring: AI-powered systems can be used to monitor
the textile production
process and identify potential quality problems. This can help to prevent defects from occurring in
the first place.
