Ensemble prediction modeling of flotation recovery based on machine learning  

作　　者：Guichun He Mengfei Liu Hongyu Zhao Kaiqi Huang 

机构地区：[1]Jiangxi Provincial Key Laboratory of Low-Carbon Processing and Utilization of Strategic Metal Mineral Resources,Ganzhou 341000,China [2]School of Resources and Environmental Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China [3]Hefei GoldStart Intelligent Control Technical Co.,Ltd.,Hefei 230088,China [4]School of Mechanical and Electrical Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China

出　　处：《International Journal of Mining Science and Technology》2024年第12期1727-1740,共14页矿业科学技术学报（英文版）

基　　金：supported by the National Key R&D Program of China(No.2023YFC2908200);National Natural Science Foundation of China(No.52174249);Key Research and Development Program of Jiangxi Province(No.20203BBGL73231).

摘　　要：With the rise of artificial intelligence(AI)in mineral processing,predicting the flotation indexes has attracted significant research attention.Nevertheless,current prediction models suffer from low accuracy and high prediction errors.Therefore,this paper utilizes a two-step procedure.First,the outliers are pro-cessed using the box chart method and filtering algorithm.Then,the decision tree(DT),support vector regression(SVR),random forest(RF),and the bagging,boosting,and stacking integration algorithms are employed to construct a flotation recovery prediction model.Extensive experiments compared the prediction accuracy of six modeling methods on flotation recovery and delved into the impact of diverse base model combinations on the stacking model’s prediction accuracy.In addition,field data have veri-fied the model’s effectiveness.This study demonstrates that the stacking ensemble approaches,which uses ten variables to predict flotation recovery,yields a more favorable prediction effect than the bagging ensemble approach and single models,achieving MAE,RMSE,R2,and MRE scores of 0.929,1.370,0.843,and 1.229%,respectively.The hit rates,within an error range of±2%and±4%,are 82.4%and 94.6%.Consequently,the prediction effect is relatively precise and offers significant value in the context of actual production.

关 键 词：Machine learning STACKING BAGGING Flotation recovery rate Filtering algorithm 

分 类 号：TD923[矿业工程—选矿] TP181[自动化与计算机技术—控制理论与控制工程]