In an industrial park located in Zhangjiagang, a small city on China's east coast, a large machine hums and hisses as it processes piles of used clothing. This innovative equipment, powered by artificial intelligence, sorts textiles by composition at remarkable speeds, offering a promising solution to reduce the environmental impact of synthetic textile waste.
Revolutionising Textile Recycling with AI Technology
The Fastsort-Textile machine, recognised as one of Time magazine's Best Inventions of 2025, was developed by DataBeyond, a Chinese AI recycling company established in 2018. Mo Zhuoya, the CEO of DataBeyond, emphasised the machine's potential, stating, "We can make full use of textile waste and reduce the amount that is incinerated, which will be a great help to recycling resources."
The Global Challenge of Synthetic Textiles
Synthetic textiles, derived from fossil fuels, are a low-cost and popular choice in fashion production, accounting for approximately 70% of global textile output according to a report from the Amsterdam-based nonprofit Circle Economy. Textile waste is a significant global pollutant, with China being the leading contributor. The World Trade Organization's 2025 Key Insights and Trends report highlighted that China led global textile exports at $142 billion, more than double that of the European Union.
How the AI Machine Works
Currently, the Fastsort-Textile machine is operational at only one location in China: Shanhesheng Environmental Technology Ltd., a textile recycling facility in Zhangjiagang that installed it in 2025. The equipment features an AI scanner measuring 5-by-2 meters (16-by-6.5 feet) and works with a series of conveyor belts. Workers load stacks of textiles onto the belts, which move them through the scanner. The scanner emits a sharp hiss while reading the textiles' composition, with a live video feed displaying the results on its side. It takes less than one second to accurately determine each item's material composition based on customer-defined benchmarks.
Efficiency and Accuracy Gains
The machine sorts through 100 kilograms (220 pounds) of clothes in just two to three minutes, a task that would take one worker about four hours. It can process two tons per hour, whereas two people would require two days and achieve lower accuracy, according to analysis by Shanhesheng. After scanning, textiles are transported to sorting areas for nylon and polyester recycling. Items below the benchmark are directed to a different area primarily for incineration or landfill, where textile pollution causes the most damage.
Economic and Environmental Benefits
Cui Peng, Sales Manager at Shanhesheng, noted, "This sort of thing saves money on labor costs, it saves time. When people sort materials, they can't tell accurately if it's 80 or 90% polyester. This machine rarely makes mistakes." Previously, up to 50% of processed textiles were deemed unrecyclable and sent to landfills or incinerated. With the Fastsort-Textile machine, that number has decreased to 30%, as reported by Sales Director Li Bin.
Future Prospects and Automation Goals
Li Bin added, "Now, though machines are already capable of sorting, people's energy is limited. People can't work for 24 hours straight, so robots may take over the roles in the end. The ultimate goal is a 'dark factory' with the robots running 24 hours." This vision underscores the potential for AI and automation to transform the textile recycling industry, enhancing sustainability and efficiency on a global scale.
