Abstract
The evaluation of the coal mine gas drainage effect is affected by many factors, such as flow rate, wind speed, drainage negative pressure, concentration, and temperature. This paper starts from actual coal mine production monitoring data and based on the lasso regression algorithm, features selection of multiple parameters of the preprocessed gas concentration time series to construct gas concentration feature selection based on the algorithm. The three-time smoothing index method is used to fill in the missing values. Aiming at the problem of different dimensions in the gas concentration time series, the MinMaxScaler method is used to normalize the data. The lasso regression algorithm is used to perform feature selection on the multivariable gas concentration time series, and the gas concentration time series selected by the lasso feature and the gas concentration time series without feature selection are input. The performance of the ANN algorithm for gas concentration prediction is compared and analyzed. The optimal α value and L1 norm are selected based on the grid search method to determine the strong explanatory gas concentration time series feature set of the working face, and an experimental comparison of the gas concentration prediction results before and after the lasso feature selection is performed. We verify the effectiveness of the algorithm.
Highlights
The evaluation of the coal mine gas drainage effect is affected by many factors, such as flow rate, wind speed, drainage negative pressure, concentration, and temperature
During the process of gas control, gas drainage is an effective measure of gas control; gas drainage is often affected by the gas concentration; elucidating the change law of gas concentration can effectively address the problem of drainage, reduce the incidence of gas accidents and improve the management level of safety products in the process of coal mining[2,3]
Wu et al.[6] used a method based on fuzzy information granulation, a support vector machine (SVM), and a differential evolution algorithm (DE) to establish a prediction model
Summary
The prediction accuracy of the two feature sets selected by the lasso feature was compared to verify the effectiveness of the gas concentration time series feature selection method based on lasso regression in this paper. The feature set selected by the lasso feature predicted the gas concentration in the working face better than the previous method. The experiment used the ANN algorithm as the prediction model to compare and analyze the prediction performance of the algorithm before and after lasso feature selection. The prediction model that took the gas concentration time series after lasso feature selection as input could effectively improve the accuracy of gas concentration prediction. An ANN model is used to predict the gas concentration at the working face, which can effectively improve the accuracy of the prediction
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call