基于PCA-BO-XGBoost的矿井回采工作面瓦斯涌出量预测  

Gas emission prediction of the stope in coal mine based on PCA-BO-XGBoost

作　　者：王媛彬[1] 李媛媛 韩骞 李瑜杰 周冲 WANG Yuanbin;LI Yuanyuan;HAN Qian;LI Yujie;ZHOU Chong(College of Electrical and Control Engineering,Xi’an University of Science and Technology,Xi’an 710054,China)

机构地区：[1]西安科技大学电气与控制工程学院,陕西西安710054

出　　处：《西安科技大学学报》2022年第2期371-379,共9页Journal of Xi’an University of Science and Technology

基　　金：国家自然科学基金项目(52174198);陕西省科技厅项目(2019JQ-892)。

摘　　要：针对矿井回采工作面瓦斯涌出量预测精度欠佳的问题,建立基于极端梯度提升(XGBoost)瓦斯涌出量预测模型。首先,为解决瓦斯涌出量影响因素维数高和信息冗余等问题,在预测模型中引入主成分分析法(PCA)对11种影响因素降维。其次,通过贝叶斯优化算法(BOA)对XGBoost中超参数进行优化以提高预测模型的精度。最后,将训练集数据作为预测模型的输入进行训练,利用训练好的模型对测试集数据进行验证,并与传统的BP神经网络和支持向量机进行对比。结果表明:PCA-BO-XGBoost模型的平均绝对误差为0.0703,均方根误差为0.0957,能够满足对瓦斯涌出量预测的精度要求。与其他机器学习算法相比,建立的模型预测精度更高、耗时更短、效率均更高,对煤矿井回采工作面瓦斯涌出量的预测精度和效率提升具有借鉴作用。In order to solve the problem of poor prediction accuracy of gas emission in the stope,a prediction model based on extreme Gradient Boosting was established.For the influencing factors from gas emission such as high dimension and information redundancy,principal component analysis was introduced into the prediction model firstly to reduce the dimension.Secondly,the hyper parameters in XGBoost were optimized by Bayesian optimization algorithm to improve the prediction accuracy.Finally,the data of the training set was utilized as the input of the prediction model for training,and the trained model was employed to verify the data of the test set,and it was compared with the traditional BP neural network and support vector machine.The results show that the mean absolute error of PCA-Bo-XGBoost model is 0.0703,and the root mean square error is 0.0957,which can meet the accuracy requirements of gas emission prediction.Compared with other machine learning algorithms,the model established in this paper is higher in prediction accuracy,less in time-consuming and stronger in efficiency,which has great significance for the improvement of the prediction accuracy and efficiency of gas emission in the stope.

关 键 词：瓦斯涌出量预测 XGBoost算法 主成分分析法 贝叶斯优化 超参数 

分 类 号：TD76[矿业工程—矿井通风与安全]