Recognition of Fire Detection Based on Neural Network

Aiming to the fire detection, a fire detection system based on temperature and pyroelectric infrared sensors is designed in this paper. According to the National Fire Detection Standard, a great number of test data are acquired. A model based on Levenberg-Marquardt Back Propagation (LM-BP) neutral network is established to recognize the fire status using the acquired data. Among the data, 200 groups of samples are used to train the established LM-BP networks while 1500 groups of samples test the LM-BP model. A 90% recognition rate is obtained by the LM-BP model. Compared with the other neutral networks such as Radial Basis Function (RBF) network, the LM-BP neural network has a significantly higher recognition rate (90%) than the RBF net (70%). The initial results show that the LM-BP recognition method has a favourable performance, which provides an effective way for fire detection.