摘要
为了更精准地预测矿井突水灾害,对突水预测和救援提供帮助,减少水灾造成的损失,提出基于GAPSO-RFR的矿井突水预测模型。利用遗传-粒子群算法对随机森林回归模型(RFR)进行优化,选取34例样本对GAPSO-RFR模型进行迭代和训练。测试结果表明,GAPSO-RFR模型提高了预测精度,减少了泛化误差。同时利用模型对王家岭矿区部分盘区的10号煤层与2号煤层的突水风险进行预测分析,得出了突水风险较高的区域分布情况。
In order to predict mine water inrush disaster more accurately,provide help for water inrush prediction and rescue,and reduce the loss caused by flood,a mine water inrush prediction model based on GAPSO-RFR is proposed.Genetic particle swarm optimization algorithm(GAPSO)is used to optimize the random forest regression(RFR)model.34 samples are selected to iterate and train the GAPSO-RFR model,and the optimal parameters are obtained.The test results show the GAPSO-RFR model improved the prediction accuracy and reduced the generalization error.The model is used to predict the risk of water inrush in some mining areas of Wangjialing coalfield.The regional distribution of high risk of water inrush is gained.
作者
师煜
朱希安
王占刚
刘德民
SHI Yu;ZHU Xi'an;WANG Zhangang;LIU Demin(School of Information&Communication Engineering,Beijing Information Science&Technology University,Beijing 100101,China;College of Safety Engineering,North China Institute of Science&Technology,Beijing 101601,China)
出处
《中国矿业》
北大核心
2020年第8期152-157,共6页
China Mining Magazine
关键词
矿井水灾
突水预测
粒子群优化
遗传算法
随机森林
mine water disaster
water inrush prediction
particle swarm optimization
genetic algorithm
random forest
