Prediction Of Coal And Gas Outburst Risk Based On Acoustic Emission Multi-parameters

The frequent occurrence of accidents such as coal and gas outbursts and the great harm it brings are major threats to the safe production of coal mines.Therefore,the monitoring and prevention of coal-rock dynamic disasters has become an important issue to be faced and studied in the coal mine safety production process.Coal and gas outburst is a complex and nonlinear system with many uncertainties.The methods for forecasting are also emerging and constantly updating.Because of its dynamic and non-destructive characteristics,acoustic emission detection technology can invert the evolution process of coal rock fracture through its characteristic parameter information,and it is also flourishing in predicting the dynamic disaster of coal and rock.Based on this,this paper combines acoustic emission detection technology with neural network,and proposes a PCA-SW-ESN coal and gas outburst prediction method based on multi-parameters of acoustic emission.As coal and gas outburst are nonlinear dynamic systems,their acoustic emission signals must also be high-dimensional and disorderly.Therefore,in this paper,the principal component analysis method is used to reduce the dimensionality of the acoustic emission characteristic parameters,and the comprehensive index parameters that are closely related to coal and gas outburst are extracted.The echo state network with strong nonlinear approximation ability and self-adaptive ability is selected as the basic network.In order to adapt to the complexity of the coal-rock fracture process,and to solve the ill-posed problem of the echo state network,the small-world network is used to change its topology and optimize the echo state network;thus,coal and gas outburst prediction can be realized.Through the establishment of prediction systems for coal and gas outbursts,monitoring and analysis of various acoustic emission index data at the site of the mine site are performed,and the PCA-SW-ESN prediction method proposed in this paper is used for simulation and comparison analysis.The results show that the prediction model presented in this paper has a fast iteration speed and high prediction accuracy,and can provide a reliable theoretical basis for predicting coal and gas outbursts such as coal-fired power disasters.