典型文献
A novel stacking-based ensemble learning model for drilling efficiency prediction in earth-rock excavation
文献摘要：
Accurate prediction of drilling efficiency is critical for developing the earth-rock excavation schedule. The single machine learning (ML) prediction models usually suffer from problems including parameter sensitivity and overfitting. In addition, the influence of environmental and operational factors is often ignored. In response, a novel stacking-based ensemble learning method taking into account the combined effects of those factors is proposed. Through multiple comparison tests, four models, eXtreme gradient boosting (XGBoost), random forest (RF), back propagation neural network (BPNN) as the base learners, and support vector regression (SVR) as the meta-learner, are selected for stacking. Furthermore, an improved cuckoo search optimization (ICSO) algorithm is developed for hyper-parameter optimization of the ensemble model. The application to a real-world project demonstrates that the proposed method outperforms the popular single ML method XGBoost and the ensemble model optimized by particle swarm optimization (PSO), with 16.43％ and 4.88％ improvements of mean absolute percentage error (MAPE), respectively.
文献关键词：
中图分类号：
作者姓名：
Fei LV;Jia YU;Jun ZHANG;Peng YU;Da-wei TONG;Bin-ping WU
作者机构：
State Key Laboratory of Hydraulic Engineering Simulation and Safety,Tianjin University,Tianjin 300350,China
文献出处：
引用格式：
[1]Fei LV;Jia YU;Jun ZHANG;Peng YU;Da-wei TONG;Bin-ping WU-.A novel stacking-based ensemble learning model for drilling efficiency prediction in earth-rock excavation)[J].浙江大学学报（英文版）（A辑：应用物理和工程）,2022(12):1027-1046
A类：
B类：
novel,stacking,ensemble,learning,drilling,efficiency,prediction,earth,rock,excavation,Accurate,critical,developing,schedule,single,machine,ML,models,usually,suffer,from,problems,including,parameter,sensitivity,overfitting,In,addition,influence,environmental,operational,factors,often,ignored,response,method,taking,into,account,combined,effects,those,proposed,Through,multiple,comparison,tests,four,eXtreme,gradient,boosting,XGBoost,random,forest,RF,back,propagation,neural,network,BPNN,learners,support,vector,regression,SVR,meta,are,selected,Furthermore,improved,cuckoo,search,optimization,ICSO,algorithm,developed,hyper,application,real,world,project,demonstrates,that,outperforms,popular,optimized,by,particle,swarm,PSO,improvements,mean,absolute,percentage,error,MAPE,respectively
AB值：
0.65342
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
