According to a study by the BDE Bundesverband der Deutschen Entsorgungs-, Wasser- und Kreislaufwirtschaft e.V., more than 10,000 fires occur in waste sorting plants in Germany every year. In around 80 percent of cases, the cause is lithium-ion batteries and cells built into smartphones, electric toothbrushes, or singing greeting cards, they frequently end up together with packaging in plastic waste. They can be damaged especially during the recycling process in sorting facilities—and catch fire. The damage is estimated at around one billion euros annually.

Using X-ray technology to isolate critical batteries early

In the DangerSort project, Johannes Leisner aims to curb the risk of fires at waste disposal sites: “We are developing a sensor-based sorting system that uses X-ray technology and artificial intelligence to detect risky lithium-ion batteries and cells and separate them early from the rest of the waste stream,” explains the head of the Sorting and Laboratory Systems group at the Development Center for X-ray Technology at Fraunhofer IIS. Until now, there have been no preventive measures against battery-related fires, only downstream solutions such as improved extinguishing systems. In addition, sensor-based technology enables better recycling of batteries and cells—helping to close their product cycle.

In the X-ray sorting system at Fraunhofer IIS, a high-speed conveyor belt moving at up to three meters per second transports the waste stream. Above the belt is an X-ray source that functions like an airport baggage scanner and scans the material flow. Thanks to the X-rays, it identifies batteries and cells that are built into devices or hidden among other waste. An X-ray detector mounted beneath the belt captures images at the belt’s speed, producing a continuous series of X-ray images.

This sequence is then evaluated: »For this we use an AI system that is particularly fast in image processing and is normally employed in autonomous driving, « says Johannes Leisner. »We adapted and retrained it so that it can analyze X-ray images and specifically detect electronic devices with lithium-ion batteries and cells. «

Sorting is triggered based on the collected data: special compressed-air valves separate the critical electronic devices from the rest of the waste stream, with a row of air nozzles about five millimeters in size blowing them off the belt into a separate chamber. Precise timing between image evaluation and nozzle activation is crucial.

»Capturing and isolating different battery sizes during the separation process is challenging—from a ten-kilogram e-bike battery to a button cell, anything can appear, « says Leisner.

The sorting system is currently still in test operation at Fraunhofer IIS; in early June, the plant is scheduled to be delivered to the waste management company LOBBE and tested in practice for the first time. The project, funded by the Federal Ministry of Education and Research, runs until the end of August this year. The development of the prototype system is part of the KI Hub Plastics Packaging: in the KIOptiPack and K3I-Cycling labs, a total of 51 partners from industry, science, and society work closely together. The goal is to advance the application of AI methods for a resource-efficient circular economy in the field of plastic packaging in Germany.