The safety issues of lithium-ion batteries have attracted increasing attention, especially in the context of the widespread application of electric vehicles and energy storage equipment. The safety hazard of battery fire cannot be ignored. In order to improve battery safety warning capabilities, scientists are exploring various new methods. The editor of Downcodes will introduce to you a new study that uses sound recognition technology to provide early warning of lithium battery fires. This technology is expected to significantly improve battery safety and reduce the occurrence of fire accidents.
Picture source note: The picture is generated by AI, and the picture is authorized by the service provider Midjourney
Battery casings are usually rigid and cannot accommodate this expansion, so the safety valve inside the battery ruptures when the pressure is too high, creating a distinctive sound. The sound is somewhat similar to the clicking and hissing of a soda bottle when you open it.
To this end, a research team at the National Institute of Standards and Technology (NIST) developed a machine learning algorithm specifically designed to identify this specific crackling sound. During the algorithm training process, the researchers collaborated with a laboratory at Xi'an University of Science and Technology to collect audio data from 38 exploding batteries. By adjusting the speed and pitch of this audio data, the research team generated more than 1,000 unique audio samples to further train the algorithm.
Test results show that this algorithm can identify the cracking sound of an overheated battery with 94% accuracy. It is worth noting that the researchers also introduced various background noises during the test, including footsteps, door closing sounds, bottle opening sounds, etc., and found that only a small amount of noise would interfere with the algorithm's judgment. This finding shows the robustness of the algorithm.
The research team said that this technology has the potential to be used to develop a new type of fire alarm that can be installed in homes, offices, warehouses, and electric vehicle parking lots. By issuing warnings in advance, this technology can provide people with sufficient time to evacuate and ensure personal safety.
This lithium battery fire warning technology based on sound recognition provides a new way to improve battery safety with its high accuracy and robustness. In the future, this technology is expected to be widely used in various scenarios to protect people's lives and property. I believe that with the continuous development of technology, we will have safer and more reliable battery products.