Baode Coal Mine, CHN Energy Shendong Coal Group Co., Ltd.
CCTEG ShengyangResearch Insititute
State Key Laboratory of Coal Mine Safety Technology
School of Human Settlements and Civil Engineering, Xi'an Jiaotong University

回采工作面是矿井瓦斯涌出的主要场所,精准预测回采工作面的瓦斯涌出量,进而有针对性地提出防治措施,对保证矿井安全生产具有重要意义。提出了基于随机森林回归算法的回采工作面瓦斯涌出量预测方法。以工作面实测瓦斯涌出量数据为原始样本,利用Bootstrap抽样方法进行随机抽样,以袋外数据(OOB)评估分数oob_score作为随机森林回归模型调参、特征变量重要性的评判指标,计算得出模型的最佳参数、特征变量重要性占比。对各特征变量的重要性占比进行排序,并按排序进行随机森林回归模型性能分析,结果表明:随着特征变量数的增加,模型性能不会呈现规律性的变化;当特征变量数较少时,可能存在过拟合的情况。测试结果表明,所创建的随机森林回归模型预测值与实测值的平均绝对误差、平均相对误差随着特征变量数的增加呈下降趋势,特征变量数的增加可在一定程度上提高模型的预测效果。针对同一组数据,与主成分回归分析法相比,随机森林回归模型平均相对误差降低了14.29%,预测效果更好,且原理更简单、调参更容易、计算速度更快,能够为矿井回采工作面瓦斯涌出量预测提供有力的理论支撑。

The mining face is the main place for gas emission in mines. Accurately predicting the amount ofgas emission from the mining face and proposing targeted prevention and control measures are of greatsignificance for ensuring mine safety production. A prediction method for gas emission in mining face based onrandom forest regression algorithm has been proposed. Using the measured gas emission data from the workingface as the original sample, the Bootstrap sampling method is used for random sampling. The out-of-bag (OOB)data assessment score oob_score is used as an evaluation indicator for the random forest regression model tuningparameter and importance of feature variables. The optimal parameters of the model and the percentage ofimportance of feature variables are calculated. The method ranks the importance proportion of each featurevariable and conducts performance analysis of the random forest regression model according to the ranking. The results show that as the number of feature variables increases, the model performance does not show a regularchange. When the number of feature variables is small, there may be overfitting. The test results show that theaverage absolute error and relative error between the predicted and measured values of the created random forestregression model decrease with the increase of the number of feature variables. The increase of the number offeature variables can improve the predictive performance of the model to a certain extent. Compared with theprincipal component regression analysis method, the random forest regression model reduces the average relativeerror by 14.29% for the same set of data, resulting in better prediction performance. The principle is simpler,parameter adjustment is easier, and the calculation speed is faster. The results can provide strong theoreticalsupport for predicting gas emission in mining face.

国家科技重大专项资助项目(2016ZX05045-004-001)

张增辉,马文伟. 基于随机森林回归算法的回采工作面瓦斯涌出量预测[J]. 工矿自动化,2023,49(12):33-39.

ZHANG Zenghui, MA Wenwei. Prediction of gas emission in mining face based on random forest regression algorithm[J]. Journalof Mine Automation,2023,49(12):33-39.