SGS has launched the first AI-powered, fully automated thermal runaway testing system for energy storage batteries, developed in partnership with Chongqing Energy College (CEC).
The system addresses fire safety concerns linked to the rapid global growth of battery energy storage systems (BESS) across commercial, industrial and residential sectors.
Thermal runaway – an uncontrollable rise in temperature and pressure within a battery cell – can lead to fires or explosions. SGS’s solution complies with the ANSI/CAN/UL 9540A:2025 standard, providing essential data on fire propagation risks during such events.
Now operating at the Chongqing Renewable & Advanced Energy Laboratory, the system uses deep learning to process temperature, voltage, gas emissions, and combustion data. Proprietary algorithms automatically adjust testing parameters, collect data in real time, and apply computer vision models like Yolo, TensorFlow, ResNet and VGG to detect smoke and fire with minimal manual input.
“Thermal runaway incidents have become critical challenges in the industry and we are delighted to launch our fully automated testing solution which addresses the need for internationally accredited safety testing, faster certification turnaround, and improved test transparency”, said Walter Zheng, Connectivity & Products, SGS.
Key features include:
- Full automation of equipment and data collection
- Smart smoke and fire detection via computer vision
- Enhanced lab safety through reduced human exposure
