Author(s)

Bo Li, Tingting Li, Dechang Huang

Corresponding Author

Bo Li

Abstract

With the deepening of research on wireless sensor networks, wireless sensor networks have been applied to the actual environmental monitoring and fire monitoring is one of the important applications. This paper mainly designs an intelligent fire real-time sensing and monitoring system based on wireless sensor network. In order to solve the problem of delay or even missed alarm caused by low-power sensor nodes' inadequate perception ability, this paper proposes a sensor data acquisition algorithm based on time series prediction (TSDC) and a fire identification algorithm based on neural network. Among them, TSDC algorithm reduces the delay of data acquisition caused by the delay of temperature and humidity sensing of sensor nodes. The fire identification algorithm based on neural network provides an intelligent fire identification method. By fusing the temperature, humidity and light intensity collected by sensor nodes, the fire probability under current conditions can be obtained.

Keywords

Wireless sensor networks, Fire perception, Fire monitoring system, Neural network