Page 56 - Plastics News Issue May 2025
P. 56
TECHNOLOGY NEWS
Sensor-based waste sorting reduces
number of battery fires in recycling plants
of fire in sorting plants. »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«, explains Johannes Leisner, head
of the Sorting and Laboratory Systems group at
the Development Center X-ray Technology at
Fraunhofer IIS. So far, there have been no pre-
ventive measures against fires caused by bat-
teries, only solutions to combat them, such as
improved fire extinguishing systems. The sen-
sor-based technology could also make it easier
n increasing number of electronic waste to recycle batteries, closing their product cycle,
is not being properly disposed of but Leisner says.
Aoften discarded together with plas-
tic waste, for example. If the batteries in these A prototype system set up at Fraunhofer IIS
products are damaged, they can cause fires demonstrates the potential of the idea. A high-
at sorting plants. In the DangerSort project, speed conveyor belt in the X-ray sorting system
researchers at the Fraunhofer Institute for In- at Fraunhofer IIS, which moves at speeds up to
tegrated Circuits IIS are using a sensor-based three meters per second, transports the waste
sorting system to remove hazardous items and stream. An X-ray source above the conveyor
make recycling plants safer. belt operates like an airport luggage scanner and
screens the material stream. This technology
According to a study by the German association can also identify batteries installed in appliances
BDE, more than 10,000 fires occur annually in or concealed by other waste. An X-ray detector
German waste sorting plants. Around 80 percent mounted below the conveyor belt takes images
of these fires are caused by lithium-ion batteries. at the speed of the conveyor, resulting in a con-
Common in smartphones, electric toothbrushes tinuous series of radiographs.
or singing greeting cards, these batteries are of-
ten disposed of together with packaging waste. This series of images is then evaluated: »To do
They can be damaged and catch fire, particu- this, we are applying an AI system that is de-
larly during the recycling process in sorting signed for particularly rapid image processing
plants. The damage caused by this is estimated and is normally used in autonomous driving ap-
at around one billion euros a year. plications«, Leisner says. »We have adapted
and retrained it so that it can also analyze ra-
The DangerSort project aims to reduce the risk
56 PLASTICS NEWS May 2025
