基于网格搜索和ELM的冲击地压危险等级预测  

Prediction of rock burst risk rating based on grid search and ELM

作　　者：王彦彬[1] 孙韶光[1] WANG Yanbin SUN Shaoguang(College of Business Administration, Liaoning Technical University, Huludao Liaoning 125105, China)

机构地区：[1]辽宁工程技术大学工商管理学院

出　　处：《中国安全科学学报》2017年第8期97-101,共5页China Safety Science Journal

基　　金：国家自然科学基金资助(71371091;61401185)

摘　　要：为提高冲击地压危险等级预测模型的泛化性能及预测精度,采用网格搜索法结合十折交叉验证法对极限学习机(ELM)中的隐含层神经元个数及激活函数的类型进行组合优化,进而建立冲击地压危险等级预测模型;选取重庆砚石台煤矿36组实测数据进行试验,对影响因素数据进行标准化处理,选择其中26组样本对模型进行训练,采用该模型对后10组样本中冲击地压危险等级进行预测,并与其他方法作对比。结果显示:经过十折交叉验证,用该模型得到的正确识别率为84.615%,高于朴素贝叶斯及Adaboost M1的76.92%、61.54%,采用该模型对测试样本集中冲击地压危险等级进行预测,预测准确率为90%,高于朴素贝叶斯及Adaboost M1预测准确率80%。In order to improve the generalization performance and prediction accuracy in the prediction of rock burst risk rating,the number of neurons in the hidden layer and the excitation function of the ELM were optimized by using grid search method with 10-fold cross-validation.Then a prediction model was build with the optimized parameters.26 groups of 36 groups of actual measured data form Yanshitai coal mine were used to train the model and the rest 10 groups of data to test it.The result shows that the correct recognition rate by the trained model reaches 84.615%using 10-fold cross-validation,which is better than Naive Bayes＇ s 76.92% and Adaboost M1＇s 61.54%,and the prediction accuracy by the trained model for the rest 10 groups of data is 90%,which is better than Naive Bayes and Adaboost M1＇s 80%.

关 键 词：冲击地压 危险等级预测 极限学习机(ELM) 网格搜索法 十折交叉验证 

分 类 号：X936[环境科学与工程—安全科学] TD324[矿业工程—矿井建设]