Zhangjiagang, China — In an industrial park in Zhangjiagang, a small city on China’s east coast, a huge humming and hissing machine eats and sorts piles of used clothes.
Novelty? It uses artificial intelligence to sort them by structure at high speed, showing how AI can play a role in reducing the impact of synthetic textile waste.
The FastSort-textile machine, named one of Time magazine’s Best Inventions of 2025, was created by DataBeyond, a Chinese AI recycling company founded in 2018.
“We can make full use of textile waste and reduce the amount of burning, which will be a great help in recycling resources,” said Mo Zhuoya, CEO of DataBeyond.
Synthetic textiles are derived from fossil fuels and are a low-cost, popular option for fashion production. Overall they account for about 70% of global textile production, according to a report by the Amsterdam-based nonprofit Circle Economy, which analyzes ways to reduce textile waste.
Textile waste is a major global pollutant, with China being the leading contributor. According to the WTO’s 2025 Key Insights and Trends Report, China leads global textile exports with $142 billion, more than double that of the EU.
FastSort-Textile is being used at only one location in China: Shanhesheng Environmental Technology Ltd., a textile recycling facility in Zhangjiagang that installed the machine in 2025.
The device uses an AI scanner to read the composition of such textiles and sort them by fiber, after which they can be recycled.
The FastSort-Textile sorts 100 kilograms (220 lb) of fabric in two to three minutes, compared to about four hours for a worker to do the same job. According to Shanhesheng’s analysis, the machine can process two tons per hour, while two people would need two days with less accuracy.
Measuring 5-by-2 meters (16-by-6.5 feet), the AI scanner works along a series of conveyor belts. Workers load stacks of clothing onto belts that carry them through the scanner, which emits a high-pitched hiss as it reads the clothing’s composition. A live video feed displays the readings on the scanner side.
It takes less than a second to accurately read the content composition of an item, which is determined according to customers’ desired benchmarks.
After the scanning process, the clothes are taken to nylon and polyester sorting areas for recycling. Items below the benchmark are sorted into a separate area, primarily for incineration or landfill, where textile pollution causes the most harm.
“This kind of thing saves money on labor costs, it saves time. When people sort the material, they can’t accurately tell whether it is 80 or 90% polyester. This machine rarely makes mistakes,” said Cui Peng, sales manager of Shanhesheng.
Previously, up to 50% of processed textiles were considered unusable and were sent to landfills or incinerated. Sales director Li Bin said that number has been reduced by 30% with the Fastsort-Textile machine.
“Now, although machines are already capable of sorting, people’s energy is limited,” he said. “People can’t work 24 hours a day, so eventually robots may take over the role. The ultimate goal is a ‘dark factory’ with robots working 24 hours a day.”
