Research on fire detection in coal mine based on GA-improved Wavelet Neural Networks

摘要

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.