Abstract:
Based on analysis of principle and characteristics of mine fire monitoring methods such as temperature monitoring method, gas monitoring method, smoke monitoring method, visible light image monitoring method and infrared image monitoring method, a mine fire monitoring and trend prediction method based on multi-parameter fusion was proposed. Conclusions were got as following:① Thermocouple temperature measurement method and semiconductor temperature measurement method have advantages of high accuracy, strong real-time performance and early detection of early fire, but there are disadvantages such as large sensor consumption and large maintenance workload; Infrared temperature measurement method has advantages of wide monitoring range and easy sensor arrangement, but shielding and coal dust between sensor and measured object will affect monitoring result; Fiber distributed temperature measurement method has advantages of multi-point temperature monitoring and small amount of cable consumption, but there are disadvantages such as easy damage, complicated installation and difficult maintenance of optical fiber. ② Gas monitoring method and smoke monitoring method have advantages of wide monitoring range, convenient use and maintenance, but there are disadvantages such as cannot monitor early fire with low concentration of index gas and less smoke. ③ Visible light image monitoring method has advantages of wide monitoring range, convenient use and maintenance, low cost, but interference sources such as roadway light, miner's lamp, vehicle lamp and red clothes and smoke will affect monitoring effect, and the method cannot monitor early fire with no flame and less smoke.④ Infrared image monitoring method has advantages of wide monitoring range, convenient use and maintenance, but cost is high, and shielding and coal dust between infrared camera and measured object will affect monitoring effect. ⑤ Mine fire monitoring and trend prediction method based on multi-parameter fusion of temperature, smoke, gas concentration, odor, wind direction, wind speed, air volume, visible light image and infrared image can not only detect fire in time, but also locate fire source and predict fire development trend.