This page was printed from

AI’s promise for the textiles industry

Policy makers, manufacturers and end-user communities need to be engaged.

Features | February 12, 2024 | By: Seshadri Ramkumar, Ph.D.

Image: Dreamstime.

Artificial Intelligence (AI) has become a kitchen table discussion point these days in many households, and it’s gained global prominence since serious discussions on this subject surfaced in the 2017 World Economic Forum in Davos, Switzerland. While AI has been touted as an enabler of growth, concerns are surfacing regarding privacy issues and hence the need for governmental regulation. 

The pros and cons of AI have rightly been debated among those countries that are recognized as leaders in the IT field. The U.S., India, Israel and others have all pointed out the relationship between IT development and economic expansion, noting that AI enables growth in manufacturing, service and agriculture fields. 

According to the U. S. Chamber of Commerce’s AI Commission Report, AI will enable economic growth by about $13 trillion by the end of this decade. As it was during the cold war era when defense technologies were considered a nation’s main strength, in the near future, knowledge-related fields such as AI will take on this role, as well as serving as an indicator of economic strength. 

Since the 1990s, the IT revolution has opened the knowledge space which is currently at the point of harnessing the power of machine intelligence coupled with human intellect. Mohamed Suhail, an AI researcher and assistant professor in computer applications at Tiruchirappalli, India-based National College explains, “Collaboration between humans and robots is facilitated by the integration of AI technologies.”  

According to Kiran Minnasandram, chief technology officer, Cloud Business at Wipro Technologies, “The synergy between AI and human intellect pushes the boundaries of what is achievable in manufacturing, leading to products that embody both the precision of automation and the creativity of the human mind. However, this shift in the role of the human workforce necessitates a significant investment in retraining and reskilling.” 

Influencing factors

AI is the ability to harness the capacity of computer systems for estimation, compilation and the analysis of vast data sets towards future prediction and planning, made possible with the speed and capacity of computer processing—essentially, the enabler for the development of AI. As such, several factors must be taken into consideration when evaluating the influence of AI.

The quantity and quality of data, standardization of data set collection procedures, repeatability of resources, reliability of the data and accuracy of estimation all impact AI’s effectiveness. Information technology and machine learning algorithms must be refined to suit the requirements of the field, for example in relating cotton yield predictions to fashion markets influenced by consumers’ garment choices and fast fashion products. 

Additionally, ethics questions, data privacy and social aspects must be considered. In their book Tools and Weapons, Brad Smith, vice chair and president at Microsoft, and Carol Ann Browne highlight the importance of reliability, transparency, safety and accountability in enabling the acceptability and wider applicability of AI. 

AI’s adoption in textile sectors

AI-based decision making and market predictions in volatile sectors such as cotton are slowly penetrating but have not reached the same level as, for example, the medical textile field. Among the subsectors in the textile industry, design and fast fashion have been leading in the exploration and utilization of AI. 

There is much interest in fault detection in clothing as machine vision and image analysis are used. AI-enabled machine training of patterns over different seasons enables brands to develop a variety of designs and styles which can have broader appeal. In fact, fault detection in fabrics using machine vision is a much-needed necessity. However, the reliability of fault detection depends on the availability of huge data sets, which can be used to train the algorithm for good repeatability and reliability.

“Through advanced analytics, machine learning algorithms, and real-time monitoring, AI technologies can identify and rectify defects in the manufacturing process much earlier than traditional methods, significantly reducing waste and ensuring that products meet high-quality standards,” says Minnasandram. “Companies like Siemens and General Electric, for example, have leveraged AI in their manufacturing processes to improve product quality and consistency by using predictive maintenance to foresee and prevent equipment failures before they occur, thus ensuring uninterrupted, high-quality production.”

Barriers in the supply chain impact costs, as well. Suhail says, “By anticipating demand, maximizing inventory levels, and streamlining logistics and distribution procedures, artificial intelligence can improve supply chain management. As a result, the supply chain will be more efficient and enable cost savings.”

Consumer behavior and fashion forecasting

The apparel sector is seasonal and is based on consumer preferences. This field intertwines with social sciences, behavioral psychology and manufacturing. With the help of multi-year data on fashion trends and consumer preferences, AI-enabled tools can help predict the future. However, adequate information on matters regarding the optimum number of data sets and industry-wide standards are not available, which makes prediction less reliable. Fiber choices, the demand for fast-fashion goods, and acceptable price points, however, can be estimated, and AI-assisted modeling could be a money saver for the industry.

In the textile sector, as raw materials contribute to 60-70 percent of the total cost, having a good handle on inventory will be a cost saver. As fiber availability, particularly in the case of natural fibers, and its price volatility play important roles in deciding the market, proper prediction with good reliability is necessary. The IT sector and the manufacturing sector must interact to standardize data collection and analysis. 

The fashion sector has been a beneficiary of AI approaches. Bengaluru-based Stymulia founded by Ganesh Subramanian, is a fashion industry forecaster which uses proprietary AI algorithms to predict fashion trends and demand, while helping companies to increase margins via inventory control. According to Stymulia, its Demand Sessing tool can analyze huge data sets, which can be used to predict demand and future trends. 

The advanced textiles sector

As briefed above, fast fashion is an early adopter of machine learning with support from human intelligence. The advanced textiles sector has been slower in realizing the potential of AI tools for its development and growth. While the development of new fabrics and functional chemistries is frequently related to new fibers, AI could be especially useful in this important area. The industry has been insisting on the need to develop a portfolio of high-performance fibers that find applications in defense and medicine. AI can be coupled with genetic engineering to synthesize new fibers with new applications and functionalities.

More importantly, sustainable technologies can be developed. Worth noting are efforts to incorporate the Tandem Repeat Technologies’ concept with AI and synthetic biology to develop self-healing fibers. For example, by understanding the genetic information of the protein in the squid ringed teeth (as reported in several science publications), biomanufacturing of squid protein at mass level is possible using bacteria. The required high-performance properties, such as superior elasticity, can be modeled using AI technologies and they can be tailored to develop sustainable protein-based fibers.

AI can also be used to develop next generation defense, medical and protective clothing. In these fields, obtaining a balance between protection and comfort is an issue. By examining data of the relationship among different users, performance and requirements, optimum functional, physical and chemical attributes can be optimized. It is, however, important that the data set is vast to have a reliable prediction. 

Other areas in technical textiles where AI can be supportive are the trend forecasts in the use of sustainable single-use wipes, use of flushable wipes in hygiene, load-bearing ability prediction in geotextiles, and additional niche areas. 

The future of AI

As the advanced textiles sector and the textiles industry in general are just beginning to realize the potential of AI, experts in machine learning and those in the textile sector must interact. As AI depends on the availability of quality information, including reliable and very large data sets, the collaboration between AI and manufacturing sectors will help to understand privacy requirements, the amount of data required and standardization of data needs, which are important in having dependable forecasting models. 

Forecasts can be accurate if “noises” in data can be minimized, and that requires more standardization and standard protocols. Experts in AI accept that in the case of weather prediction, it will be useful to have about 40 years of data while in the medical fields, ten years of data is sufficient. In the textile sector, standards such as these are not readily available.

How can AI-assisted modeling be beneficial over standard surveys? In standard direct survey approaches by marketing agencies, data points may be limited due to cost, time and the availability of subjects. Using such past surveys, AI-assisted modeling will be able to generate more accurate trends. 

Regarding the positive aspects of AI, Minnasandaram says, “Global surveys show that after integrating AI-driven systems, some manufacturers have reported up to a 20 percent reduction in production costs and a 50 percent decrease in downtime due to predictive maintenance. AI algorithms are exceptionally good at scheduling maintenance only when needed, preventing unexpected breakdowns and unnecessary check-ups.” 

Commenting on the future of AI in manufacturing as a researcher in the field, Mohamed Suhail advises, “It’s crucial to remember that adoptability of AI in manufacturing may differ depending on the sector, size of the organization, customer preferences and requirements. Businesses that successfully adopt and integrate AI technologies are expected to acquire a competitive edge in terms of efficiency, cost-effectiveness and innovation.”

The information technology discipline is growing at a faster rate. The textile sector needs to have cross disciplinary approaches and forums must be engaged where seamless flow of new technological advancements can be exchanged with manufacturing and textile sectors. Industry organizations, such as the Advanced Textiles Association, need to establish working groups to look at the merits, demerits and the effect of regulations on AI technologies. More importantly, the immediate need is to engage in broader outreach with the policy makers, manufacturers and end-user communities. 

Dr. Seshadri Ramkumar is a professor in the Department of Environmental Toxicology and The Institute of Environmental and Human Health, Texas Tech University, and a regular contributor to Textile Technology Source. 

Share this Story