首页|基于Stacking集成模型的煤层瓦斯含量预测研究

基于Stacking集成模型的煤层瓦斯含量预测研究

扫码查看
煤层瓦斯含量精准预测是预防井下瓦斯灾害事故的重要环节,为提高井下瓦斯含量预测的科学性及准确性,获取不同矿区的 41 组数据,包括瓦斯含量、埋深、煤厚、水分、灰分以及挥发分.对最小二乘支持向量机(LSSVM)、深度信念网络(DBN)、长短期记忆(LSTM)、Elman神经网络及自适应增强(Adaboost)五种算法进行初选,得到最优基模型为最小支持二乘向量机、自适应增强以及深度信念网络.通过基模型集成得到 7 种瓦斯含量预测模型,得到Stacking-LSSVM-Adaboost、Adaboost、Stacking-Adaboost-DBN和Stacking-LSSVM-Adaboost-DBN四种模型为优选模型.采用判定系数、平均绝对误差、均方根误差以及平均绝对百分比误差四种预测评价指标对优选出的四种模型进行综合评估,选择MAE<0.2、RMSE<0.3 且MAPE<10 的模型作为最终瓦斯含量预测模型.结果表明,Stacking-LSSVM-Adaboost-DBN集成模型判定系数为 0.951,MAE、RMSE和MAPE分别为0.170、0.204 及7.412,所建立模型拥有较高预测精度,可为矿井瓦斯灾害防治提供一定依据.
Coal seam gas content prediction based on Stacking integrated model
Accurate prediction of coal seam gas content is an important link to prevent underground gas disasters.In order to improve the scientificity and accuracy of underground gas content prediction,41 sets of data from different mining areas were obtained,including gas content,buried depth,coal thickness,moisture,ash and volatile content.Five algorithms of least square support vector machine(LSSVM),deep belief network(DBN),Long short-term memory(LSTM),Elman neural network and adaptive enhancement(Adaboost)were selected,and the optimal base model were the least square support vector machine(LSSVM),adaptive enhancement and deep belief network.Seven gas content prediction models were integrated through the base model,and four models of Stacking-LSSSVM-Adaboost,Adaboost,Stacking-Adaboost-DBN and Stacking-LSSSVm-Adaboost-DBN were optimal models.Four prediction and evaluation indexes,namely,decision coefficient,mean absolute error,root mean square error and mean absolute percentage error,were used to comprehensively evaluate the four selected models,and the models with MAE<0.2,RMSE<0.3 and MAPE<10 were selected as the final prediction models for gas content.The results show that the decision coefficient of the integrated Stacking-LSSVM-Adaboost-DBN model was 0.951,and MAE,RMSE and MAPE were 0.170,0.204 and 7.412,respectively.The established model has high prediction accuracy and can provide a basis for mine gas disaster prevention.

gas content predictionstacking integrationfive-fold cross validationmodel optimizationmodel evaluation

王琳、周捷、林海飞、李文静、张宇少

展开 >

西安科技大学 安全科学与工程学院,陕西 西安 710054

西部煤矿瓦斯灾害防控陕西省高等学校重点实验室,陕西 西安 710054

瓦斯含量预测 Stacking集成 五折交叉验证 模型优选 模型评价

国家自然科学基金面上项目陕西省杰出青年科学基金陕西省自然科学基金

521742072020JC-482019JLP-02

2024

煤炭工程
煤炭工业规划设计研究院

煤炭工程

CSTPCD北大核心
影响因子:0.806
ISSN:1671-0959
年,卷(期):2024.56(4)
  • 29