基于WOA-XGBoost模型的胶结充填体强度预测  

Strength Prediction of Cemented Paste Backfill Body Based on WOA-XGBoost Model

作　　者：袁丛祥 刘志祥[1] 杨小聪 郭金峰 万串串 熊帅 刘伟军[1] YUAN Congxiang;LIU Zhixiang;YANG Xiaocong;GUO Jinfeng;WAN Chuanchuan;XIONG Shuai;LIU Weijun(School of Resources and Safety Engineering,Central South University,Changsha 410083,Hunan,China;BGRIMM Technology Group,Beijing 102628,China;National Center for International Joint Research on Green Mental Mining,Beijing 102628,China;Sinosteel Maanshan General Institute of Mining Research Co.Ltd.,Maanshan 243000,Anhui,China)

机构地区：[1]中南大学资源与安全工程学院,湖南长沙410083 [2]矿冶科技集团有限公司,北京102628 [3]国家金属矿绿色开采国际联合研究中心,北京102628 [4]中钢集团马鞍山矿山研究总院股份有限公司,安徽马鞍山243000

出　　处：《高压物理学报》2023年第5期113-123,共11页Chinese Journal of High Pressure Physics

基　　金：国家重点研发计划项目(2022YFC2904101);国家自然科学基金(52374107,51974359)。

摘　　要：单轴抗压强度作为胶结充填体重要的力学性能指标,通常使用传统的力学试验来确定。使用鲸鱼优化算法(whale optimization algorithm,WOA)对极限梯度提升模型(XGBoost)进行优化,建立了WOA-XGBoost混合模型。以某铅锌矿充填料浆配比试验得到的80组数据作为数据库,选取固体质量分数、水泥占比、尾砂占比及养护天数作为输入参数,充填体试块抗压强度作为输出参数。为了与WOA-XGBoost模型进行比较,还构建了XGBoost、RF和WOA-RF模型。结果表明:WOA-XGBoost模型的决定系数为0.9650,均方根误差为0.2074,平均绝对误差为0.1703;XGBoost模型的决定系数、均方根误差、平均绝对误差分别为0.8971、0.4084和0.2467。可见,鲸鱼优化算法能够显著提高XGBoost模型的预测能力。相比XGBoost、RF和WOA-RF模型,WOA-XGBoost混合模型具有更高的预测精度。研究结果对于胶结充填材料的设计和配比优化具有重要意义。The uniaxial compressive strength of cemented paste backfill(CPB),as an important indicator of their mechanical properties,is usually determined by traditional mechanical tests.In the proposed model,the whale optimization algorithm(WOA)with global optimization capacity was used to tune the hyperparameters of the extreme gradient boosting(XGBoost)model.Taking the 80 sets of data obtained from the filling slurry ratio test of a lead-zinc mine as the database,the solid mass fraction,cement content,tailings content as well as curing age,were selected as input variables and the uniaxial compressive strength of the filling body as an output variable.XGBoost,random forest(RF)and WOA-RF models were constructed to compare with the WOA-XGBoost model.The results indicates that the hybrid WOAXGBoost model(Its determination coefficient is 0.9650,the root mean square error is 0.2074,and the mean absolute error is 0.1703)performs rather better than the individual XGBoost model(Its determination coefficient is 0.8971,the root mean square error is 0.4084,and the mean absolute error is 0.2467).Compared with other models,the WOA-XGBoost model exhibits the highest prediction accuracy,contributing to the design and ratio optimization of cemented paste backfill materials.

关 键 词：胶结充填材料 单轴抗压强度 预测 极限梯度提升模型 鲸鱼优化算法 

分 类 号：O346[理学—固体力学] TD853[理学—力学]