A team of researchers from South Korea has developed an innovative fire detection technology designed to drastically reduce false alarms—those triggered by non-fire-related particles like dust or steam—which have been a persistent issue in fire safety systems. This groundbreaking technology is on the verge of commercialization and is expected to significantly cut the social costs caused by these “unwanted alarms.”
The Electronics and Telecommunications Research Institute (ETRI) recently unveiled an AI-powered sensor capable of distinguishing between smoke from an actual fire and non-fire aerosol particles. The system works by analyzing the scattering patterns of light across particles of varying wavelengths, enabling it to differentiate between harmless particles and those associated with a real fire.
Traditional photoelectric smoke detectors operate by emitting infrared light and using a light-sensing photodiode to detect scattered light. When smoke particles enter the detector, they scatter the light, triggering the alarm once the scattering reaches a certain threshold. However, everyday activities like cooking or cigarette smoking can also generate aerosol particles that set off false alarms, leading to unnecessary fire engine dispatches.
According to the National Fire Agency, between 2021 and mid-2022, fire engines were dispatched over 258,000 times, with 96.6% of those calls attributed to alarm malfunctions rather than actual fires.
The newly developed AI sensor, however, takes a more advanced approach. By measuring the scattering characteristics of aerosol particles at different wavelengths, the sensor can accurately determine whether the particles are fire-related or not. To achieve this, the researchers at ETRI created a comprehensive database that measures how various particles scatter light based on their composition. This database, combined with AI algorithms, allows the system to analyze the nature of the particles and decide whether to trigger the alarm or not.
The AI technology will first be applied to aspirating smoke detectors, which are already known for their rapid smoke detection. These detectors work by drawing in air with a fan and analyzing the particles, offering faster response times compared to traditional photoelectric detectors. However, aspirating detectors are often prone to malfunctions caused by dust, moisture, or other non-fire particles. Currently, they are mostly used in specialized environments like semiconductor clean rooms and server rooms.
Most aspirating smoke detectors available on the market today are imported and lack the capability to distinguish between fire-related particles and other aerosols. However, once ETRI’s AI-powered technology is integrated into these detectors, it will provide a highly competitive, cost-effective solution for both domestic and international markets.
ETRI’s Director Kang Bok Lee, who leads the Defense & Safety Intelligence Research Section, explained, “Once commercialized, this technology will significantly reduce false alarms caused by non-fire incidents, lowering the cost of fire engine dispatches and preventing the wasteful use of firefighting resources, which is estimated to cost around 20 billion KRW annually.”
In addition to fire safety, the technology’s ability to measure scattering spectra also opens up potential applications in other industries, including cosmetics, medical devices, and environmental monitoring. ETRI is currently in talks with relevant companies to bring this innovative technology to market.
By Impact Lab
