Kim Soocheol, Yang Hoesung, Cho Kwangsoo, Han Kyuwon, Ahn Yusun, Ryu Jin Hwa, Lee Kangbok
Defense and Safety Convergence Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, 34129, Republic of Korea.
Sci Rep. 2025 Jul 16;15(1):25752. doi: 10.1038/s41598-025-11185-6.
Although smoke detectors are actively being studied to reduce false fire alarms, they still face challenging issues such as complex and elaborate alignment, high cost, large size, and poor performance. In particular, most smoke detection systems based on Mie scattering, which rely on single-scattering measurements, may not perform effectively in real-world environments where multiple scattering occurs. We present an advanced smoke detection instrument for aspirating smoke detection and classification based on multiple scattering. Multi-angle light scattering with an LED array instead of angle-positioned PDs was measured, and the unique optical property ratios of fire and non-fire aerosols were calculated. The feasibility of smoke detection and classification was verified by evaluating the classification performance of 10 types of fire and non-fire aerosols using general supervised learning algorithms. The advanced smoke detection instrument features a simple design, making it cost-effective and compact. In addition to reducing false fire alarms, it is expected to contribute to choosing appropriate fire extinguishers based on fire class and advancing research of complex fire detection.
尽管人们正在积极研究烟雾探测器以减少误报，但它们仍面临一些具有挑战性的问题，如复杂精细的校准、高成本、大尺寸和性能不佳等。特别是，大多数基于米氏散射的烟雾探测系统依赖单次散射测量，在发生多次散射的实际环境中可能无法有效运行。我们提出了一种基于多次散射的先进吸气式烟雾探测与分类仪器。测量了使用LED阵列而非角度定位光电探测器的多角度光散射，并计算了火灾和非火灾气溶胶独特的光学特性比。通过使用通用监督学习算法评估10种火灾和非火灾气溶胶的分类性能，验证了烟雾探测与分类的可行性。这种先进的烟雾探测仪器设计简单，具有成本效益且体积紧凑。除了减少误报外，预计它还将有助于根据火灾类别选择合适的灭火器，并推动复杂火灾探测的研究。
