中文摘要：

根据火灾的特征与燃烧产物,设计了一种基于多传感器信息融合的火灾探测系统。该系统以DSP TMS320LF2407A为处理器,包括一氧化碳传感器模块、温度传感器模块和紫外火焰传感器模块。紫外火焰传感器可以很好地区分闪燃火和阴燃火,一氧化碳传感器和温度传感器能够对闪燃火和阴燃火产生不同的反应,因此系统采用两种不同的算法来探测闪燃火和阴燃火。该火灾探测系统在燃烧室中通过了实验验证。实验表明,该火灾探测系统比通用的感烟型探测器具有更快的探测速度和准确度,且不会在常见干扰源的干扰下产生误报警。

英文摘要：

According to fire characteristics and products of combustion, a fire detection system based on multi-sensor data fusion is designed. The system selects DSP TMS320LF2407A as its CPU, and is integrated with a CO sensor unit, a tempearture sensor unit and an ultraviolet flame sensor unit. The ultraviolet flame sensor can distinguish flaming fire and smoldering fire. The CO sensor and temperature sensor have different response to flaming fire and smoldering fire. Two different algorithms are used to detect flaming fire and smoldering fire in the system. The fire detection system was validated by experiments in a burnable room. The experimental results show that the fire detection system detects fire more rapidly and exactly than commercial smoke detectors, and does not respond to common nuisances.