| 143 | 0 | 7 |
| 下载次数 | 被引频次 | 阅读次数 |
针对金浸出率预测准确率不高及噪声数据较大的问题，提出了一种高效的智能预测方法。将改进的XGBoost和LightGBM模型相结合，并采用动态学习率、正则化优化和贝叶斯优化算法，设计了一个集成学习模型对金浸出率进行预测。结果表明：相较于传统单一模型，集成学习模型预测精度明显提升，其均方误差较XGBoost和LightGBM分别降低28.8%和22.9%左右，在真实生产环境中稳定性较高。该集成学习模型能够有效提高金浸出率的预测精度，具有较强的实际应用价值。
Abstract：To address the problem of low prediction accuracy and large noise data in gold leaching rate prediction, a high-efficiency intelligent prediction method was proposed. Combining the improved XGBoost and LightGBM models, a dynamic learning rate, regularization optimization, and Bayesian optimization algorithm were used to design an ensemble learning model for gold leaching rate prediction. The results show that the ensemble learning model has a significantly improved prediction accuracy compared to traditional single models, and its MSE is about 28.8% and 22.9% lower than XGBoost and LightGBM,respectively.The model has high stability in real production environments. The ensemble learning model can effectively improve the prediction accuracy of gold leaching rate and has strong practical application value.
[1] 胡广浩，毛志忠，何大阔.浸出过程浸出率预测与在线优化[J].系统工程学报，2011,26(4):524-530.HU Guanghao,MAO Zhizhong,HE Dakuo.Prediction of leaching rate and on-line optimization operation of leaching process [J].Journal of Systems Engineering,2011,26(4):524-530.
[2] 白璐.湿法冶金浸出过程非线性预测控制方法的研究[D].沈阳：东北大学，2019.
[3] 李淑芹，王宇斌，毛欣钰，等.基于不同算法的磁化水水洗去除飞灰中可溶性氯盐浸出率预测模型[J].化工矿物与加工，2022,51(1):44-48.LI Shuqin,WANG Yubin,MAO Xinyu,et al.A prediction model for the leaching rate of soluble chlorides from washing fly ash with magnetic water based on different algorithms[J].Industrial Minerals & Processing,2022,51(1):44-48.
[4] 郭计敏.金氰化浸出过程非线性预测控制方法及仿真算法分析研究[J].湿法冶金，2023,42(6):659-665.GUO Jiming.Nonlinear predictive control method and simulation algorithm analysis of gold cyanide leaching process[J].Hydrometallurgy of China,2023,42(6):659-665.
[5] 莫文水.金氰化浸出过程混合建模及仿真算法分析研究[J].湿法冶金，2023,42(4):429-435.MO Wenshui.Hybrid modeling and simulation algorithm of gold cyanide leaching process[J].Hydrometallurgy of China,2023,42(4):429-435.
[6] 刘尊方，雷浩川，盛海彦.基于XGBoost模型的湟水流域耕地土壤养分遥感反演[J].干旱区地理，2023,46(10):1643-1653.LIU Zunfang,LEI Haochuan,SHENG Haiyan.Remote sensing inversion of soil nutrient on farmland in Huangshui River Basin based on XGBoost model [J].Arid Land Geography,2023,46(10):1643-1653.
[7] 郝若飞，赵松.基于XGBoost模型的缺血性脑卒中患者中医药治疗复发预测研究[J].中国药物应用与监测，2023,20(6):441-447.HAO Ruofei,ZHAO Song.Prediction of recurrence in ischemic stroke patients treated with traditional Chinese medicine based on XGBoost model [J].China Drug Application and Monitoring,2023,20(6):441-447.
[8] BHUTTA A A,NISA M U,MIAN A N.Lightweight real-time WiFi-based intrusiondetection system using LightGBM[J].Wireless networks,2024,30(2):749-761.
[9] 何哲，石玉玲，李富春，等.基于LightGBM模型的甘肃省临夏县滑坡易发性评价[J].水资源与水工程学报，2024,35(1):197-205.HE Zhe,SHI Yuling,LI Fuchun,et al.Landslide susceptibility assessment based on LightGBM model in Linxia County,Gansu Province[J].Journal of Water Resources and Hydraulic Engineering,2024,35(1):197-205.
[10] 曲羽姗.基于SMOTE和LR-RF-AdaBoost-XGBoost模型的银行代发工资客户流失预测研究[D].大连：东北财经大学，2023.
[11] 李赟波，王士同.多源域分布下优化权重的迁移学习Boosting方法[J].计算机科学与探索，2023,17(6):1441-1452.LI Yunbo,WANG Shitong.Transfer learning Boosting for weight optimization under multi-source domain distribution[J].Journal of Frontiers of Computer Science & Technology,2023,17(6):1441-1452.
[12] 牛庆威，张如玉，白雨昊，等.基于梯度提升决策树(GBDT)的低阻油层识别[J].计算机与数字工程，2023,51(6):1428-1432.NIU Qingwei,ZHANG Ruyu,BAI Yuhao,et al.Low resistivity reservoir identification based on gradient boosting decision tree(GBDT) [J].Computer & Digital Engineering,2023,51(6):1428-1432.
[13] 李亚茹，张宇来，王佳晨.面向超参数估计的贝叶斯优化方法综述[J].计算机科学，2022,49(增刊1):86-92.LI Yarou,ZHANG Yulai,WANG Jiachen.Survey on Bayesian optimization methods for hyper-parameter tuning [J].Computer Science,2022,49(Sup.1):86-92.
[14] 卫升，王艳，纪志成.多工况生产过程下的即时学习能耗预测建模方法[J].系统仿真学报，2024,36(6):1378-1391.WEI Sheng,WANG Yan,JI Zhicheng.Just-in-time learning energy consumption predictive modeling method in multi-condition production process[J].Journal of System Simulation,2024,36(6):1378-1391.
[15] AHN J M,KIM J,KIM K.Ensemble machine learning of gradient boosting (XGBoost,LightGBM,CatBoost) and attention-based CNN-LSTM for harmful algal blooms forecasting[J].Toxins,2023,15(10).DOI:10.3390/toxins15100608.
基本信息:
DOI：10.13355/j.cnki.sfyj.2025.05.016
中图分类号:TF831;TP181
引用信息:
[1]周一帆.基于集成学习算法的金浸出率智能预测模型设计研究[J].湿法冶金,2025,44(05):698-705.DOI:10.13355/j.cnki.sfyj.2025.05.016.
基金信息: