Research on Fire Detection in Coal Mine Based on GA-Improved Wavelet Neural Networks

Abstract:

In coal mine the forecast on fire is mainly based on the smoke, gas and temperature parameters to recognize, and sometimes it has leak check and wrong check, therefore a novel method for mine fire based on image processing is presented. First the data are obtained by infrared CCD, then the blaze characters are extracted and they are entered into the GA-improved wavelet neural networks model after being quantization, finally the fire can be detected. The experiment results show that this method can recognize fire signals and it reduced leak forecast, and also it is more reliable and has stronger antigambling ability. It will inevitably play an important role in coal mine safety production..

• Periodical: Advanced Materials Research (Volumes 490-495)
• Pages: 1636-1639
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.490-495.1636
• Online since: March 2012
• Authors: Hong Zhao
• Keywords: Fire Detection, GA-Improved, Image Processing, Neural Network (NN), Wavelet

References

[1] Ren Hui, Sun Jiping, Liu Xiaoyang, Image recognition method of mine cable fires, Journal of Liaoning Technology University, 2007, Vol 26, No 1, p.85~88.

[2] Li Ming, Wu Aiguo, Method of Early fire detection in large area based on double band images, Fire science and technology. 2009, No 2, p.37~40.

[3] Ji Ping, Lu Jiecheng. A Bus-mode fire image detecting system, Computer engineer and application, 2004, 26, p.214~215.

[4] Wu Longbiao, Song Weiguo, Lu Jiecheng, A novel fire criterion in image fire monitor,. 1997, 6(2), p.60~66.

[5] Luo Yunlin, Zhu Ruiping, Wang Jinghua, Study of fire detection system based on numeric image processing, Journal of Liaoning Technology University , 2002, Vol 21, No 6, p.754~756.

[6] Chen Chun, Computer image process technology and algorithm,. Beijing: Qinghua press, 2002, p.124~130.

[7] Zhang Naiyao, Yan Pingfan, Neural network and fuzzy control, Beijing: Qinghuapress, 1998, p.88~100.