Prediction of coal mine gas emission based on hybrid machine learning model

Abstract

Coal mine gas accident is one of the most significant threats to the safe mining process in coal mines, so it is very important to accurately predict coal mine gas emission. To improve the accuracy of coal mine gas emission prediction, a hybrid machine learning prediction model combining random forest (RF) algorithm, improved gray wolf optimizer (IGWO) algorithm and support vector regression (SVR) algorithm is proposed. Thirty groups of actual measured gas emission data from a coal mine are selected as samples, and the latter five groups are used as test sets. Firstly, the RF algorithm is used to screen 13 influencing factors of coal mine gas emission, and finally six influencing factors are selected as the input variables of the prediction model; Secondly, the IGWO algorithm is obtained by improving the GWO algorithm with a nonlinear convergence factor and a DLH search strategy; Finally, the IGWO algorithm is used to optimize the SVR algorithm to establish the RF-IGWO-SVR model, and the model is compared with other models to verify its superiority. The results show that the average relative error of the RF-GWO-SVR model is 1.55%, and this result is better than other comparative models, which indicates that the model can effectively improve the prediction accuracy of coal mine gas emission and provide a new model for coal mine gas emission prediction.