Study On Early Warning And Source Location Of Coal And Gas Outburst Based On Acoustic Emission

Coal and gas outbursts are devastating,its occurrence often has the characteristics of sudden and difficult to detect,so we can only be passive to prevent.Coal and gas outbursts are often accompanied by the generation of acoustic emission(AE),which can be used as an important basis for predicting coal and gas outbursts(possibilities and location of coal and gas outburst).In practical engineering and application,acoustic emission relative strength index(CR)is used for coal and gas outburst warning.In order to improve the accuracy of acoustic emission technology in the early warning process of coal and gas outburst disaster,a targeted acoustic emission composite filtering method is proposed for the underground noise source and its nature.Firstly,the wavelet decomposition is used to filter the regular noise.Then,the impulse noise is filtered by the median filter method.Finally,the singular value decomposition method is used to filter the random noise.In order to fully grasp the process of evolution of the coal and gas outburst disaster,and provide the possible coal and gas outburst position is for the underground workers,a method of positioning the acoustic emission source of coal and rock mass is put forward.The intelligent algorithm of the improved multi-output support vector machine is applied to the coal mine sound source localization with special waveforms.This method(KPCA-MA-MSVM)improves the coupling problem of the input parameter signal and the internal parameter selection problem of the multi-output support vector machine.Specifically,kernel principal component analysis is applied to the sample input,and the new independent influencing factors are extracted.Then the cultural gene algorithm is applied to the multi-output support vector machine model to search the optimized penalty factor C,and finally,ues the lead test to test the positioning performance.The results show that the algorithm improves the accuracy of the acoustic emission location of the test platform and has less localization time than other positioning algorithms,and has high practical application value.