| Coal and gas outburst is one of the main dynamic disasters in the process of coal production.The study shows that in coal and gas outburst mines,the coal seams all develop a certain degree of tectonic coal,and the greater the thickness of the tectonic coal,the more dangerous the gas outburst is.Therefore,if the thickness of the coal in the coal seam can be accurately predicted,it will play a vital role in the safety management of the coal mine and the development and utilization of the coal bed gas.In view of the low accuracy of the current prediction methods for tectonic coal distribution,a deep learning method based on deep belief networks is proposed to predict the distribution of tectonic coal.Firstly,the principal component analysis technology is used to reduce the dimension of three-dimensional seismic attributes and eliminate the correlation between variables while reducing the dimension of seismic attributes.Then,aiming at the problem that limited Boltzmann machine can only accept binary input and result in data loss,a deep belief networks prediction model containing a continuous restricted Boltzmann machine is constructed.The whole model is finetuned with BP neural network supervised.At the same time,in order to improve the accuracy of the prediction model,multi-layer perceptron combined with softmax regression is used to output the prediction results,which effectively improves the performance of the prediction model.Finally,the prediction model is applied to 8 coal seams in 6 mining area of Luling Coal Mine.The predicted distribution of tectonic coal in mining area is in good agreement with the actual geological data.The optimization model is compared with SVM model and ELM model,and better prediction results are obtained.It can be seen that the prediction model proposed in this paper has high prediction accuracy and small prediction error,and can be applied to the prediction of tectonic coal distribution in actual mining areas. |
PDF Full Text Request