基于线性判别分析的火灾烟雾探测研究

Research on Fire Smoke Detection Based on Linear Discriminant Analysis

针对传统火灾烟雾探测器误报的问题,提出基于线性判别分析的火灾烟雾算法,并设计了多传感器线性判别分析,使用火灾测试中记录的历史传感器数据产生与各种类型的火灾和干扰条件相关的模式,并在相同火灾测试情况下建模分析及实验测试。应用线性判别分析算法于光电传感器,可以比传统探测器更快地检测到阴燃火灾,添加温度传感器或一氧化碳传感器可以更好区分真实火灾和干扰源。

Aiming at the problem of false alarm of traditionalfire smoke detector,this paper proposes afire smoke algorithm based on linear discriminant analysis,and designs a multi-sensor linear discriminant analysis.The historical sensor data recorded in thefire test is used to generate patterns related to various types offire and interference conditions,and the linear discriminant analysis algorithm is applied to the photoelectric sensor under the samefire test,smolderingfire can be detected faster than traditional detectors.Adding temperature sensor or carbon monoxide sensor can better distinguish between realfire and interference source.