Reviewed by Lexie CornerMay 6 2025
Researchers at the Fraunhofer Institute for Integrated Circuits (IIS) are developing a sensor-based sorting system, as part of the DangerSort project, to detect hazardous materials and enhance safety in recycling facilities.
At Fraunhofer IIS, waste streams are screened by a prototype sorting system using artificial intelligence and X-ray technology to separate hazardous batteries in good time. Image Credit: Fraunhofer IIS/Paul Pulkert
Electronic waste is increasingly being improperly discarded with plastic waste, posing a serious fire risk at sorting facilities when embedded batteries are damaged.
In Germany alone, waste sorting plants report over 10,000 fires each year, according to the BDE (Federal Association of the German Waste, Water, and Raw Materials Management Industry).
Lithium-ion batteries are responsible for around 80 % of these incidents. Common in items like smartphones, electric toothbrushes, and even musical greeting cards, these batteries are often mistakenly disposed of with packaging waste. They are easily damaged during sorting, and their flammability contributes to an estimated €1 billion in annual damages.
Using X-Ray Technology to Isolate Hazardous Batteries at an Early Stage
The DangerSort project aims to reduce the risk of fires in sorting plants by identifying hazardous materials before they cause damage.
We are developing a sensor-based sorting system that uses X-ray technology and artificial intelligence to detect hazardous lithium-ion batteries and separate them from the rest of the waste stream at an early stage.
Johannes Leisner, Head, Sorting and Laboratory Systems Group, Development Center X-ray Technology, Fraunhofer Institute for Integrated Circuits
Currently, the focus is largely on reactive measures, such as installing more advanced fire suppression systems, rather than prevention. Leisner notes that sensor-based technology could also help enable battery recycling, contributing to a more complete product lifecycle.
A prototype of the concept has already been demonstrated at Fraunhofer IIS. There, a high-speed conveyor system—capable of reaching speeds up to three meters per second—transports the waste stream through the institute’s X-ray sorting setup.
Functioning similarly to an airport baggage scanner, the system uses an X-ray source positioned above the belt to scan materials as they pass by. It can detect batteries, even if they are hidden inside devices or buried beneath other waste.
An X-ray detector beneath the conveyor captures a continuous series of radiographic images at the speed of the moving belt. These images are then automatically analyzed to identify potential hazards.
To do this, we are applying an AI system that is designed for particularly rapid image processing and is normally used in autonomous driving applications. We have adapted and retrained it so that it can also analyze radiographs to specifically detect electrical appliances that contain lithium-ion batteries.
Johannes Leisner, Head, Sorting and Laboratory Systems group, Development Center X-ray Technology, Fraunhofer Institute for Integrated Circuits
The sorting process begins based on the radiographic data. Compressed air valves, controlled using this information, activate air nozzles—just five millimeters in diameter—to remove hazardous electronic devices from the waste stream. These items are then diverted into a separate chamber.
Precise timing is essential to ensure the nozzles activate at the right moment following image analysis.
“It is difficult to detect and isolate different battery sizes during the separation process, as these can range from ten-kilo e-bike batteries to button batteries,” Leisner said.
The system is still undergoing testing at Fraunhofer IIS. It is scheduled to be delivered to the waste management company LOBBE in early June for initial field trials. The project, funded by the German Federal Ministry of Education and Research (BMBF), will run through August 2025.
The prototype is being developed within the AI Application Hub on Plastic Packaging. In this initiative, 51 partners from industry, research, and society are collaborating across the KIOptiPack and K3I-Cycling labs to apply AI for a more resource-efficient, circular approach to plastic packaging in Germany.