Study on the tunnel fire detection based on BP Neural Network
Based on the analysis of the tunnel fire environment and the characteristics, the temperature, smoke and CO are selected as the main parameters of the tunnel fire detection. Based on neural network, the mathematical model is set up. With study algorithm of neural network, the model can identify tunnel fires. The result of MATLAB simulation of tunnel fire shows that the correct recognition rate of tunnel fire is high. The false-alarm can be decreased. The suitability of this system to environmental variation can be obviously improved. The study and application of this method has a great theoretical and practical value for early prediction of tunnel fires.
fire tunnel fire automatic detection Neural network
ZHU Hongwei
The Department of Command Chinese Peoples Armed Police Academy,Lang-fang He-bei 065000
国际会议
2009 International Symposium on Fire Science and Fire-Protection Engineering(2009火灾科学与消防工程国际学术会议)
北京
英文
420-424
2009-10-17（万方平台首次上网日期，不代表论文的发表时间）