1.东北大学冶金学院,沈阳110819
2.东北大学轧制及自动化国家重点实验室,沈阳110819
3.东北大学多金属共生矿生态化冶金教育部重点实验室,沈阳110819
刘玉潇(1998—),男,博士; E-mail:liu2428332@163.com
董艳伍(1978—),男,博士生导师,教授; E-mail:dongyw@smm.neu.edu.cn
收稿:2024-04-17,
纸质出版:2025-01-30
移动端阅览
刘玉潇,董艳伍,姜周华等.基于MI和XGBoost算法电渣重熔终点磷含量预报模型[J].特殊钢,2025,46(01):117-125.
Liu Yuxiao,Dong Yanwu,Jiang Zhouhua,et al.Prediction Model of Phosphorus Content at the End Point of Electroslag Remelting Based on MI and XGBoost Algorithms[J].Special Steel,2025,46(01):117-125.
刘玉潇,董艳伍,姜周华等.基于MI和XGBoost算法电渣重熔终点磷含量预报模型[J].特殊钢,2025,46(01):117-125. DOI: 10.20057/j.1003-8620.2024-00096.
Liu Yuxiao,Dong Yanwu,Jiang Zhouhua,et al.Prediction Model of Phosphorus Content at the End Point of Electroslag Remelting Based on MI and XGBoost Algorithms[J].Special Steel,2025,46(01):117-125. DOI: 10.20057/j.1003-8620.2024-00096.
研究针对电渣重熔流程提出了一种基于互信息法(MI)和XGBoost的电渣重熔终点磷含量预报模型,利用互信息法对影响终点磷含量的因素进行特征选择与特征评估,特征选择后的数据集作为模型的输入变量。建立MI-XGBoost模型对生产数据进行训练及验证,利用网格搜索交叉验证对模型结构调整和超参数优化,并与MI-RR、MI-RF、MI-GBDT和MI-KNN模型进行横向对比,结果表明,MI-XGBoost模型具有最高的预测精度,MI和GridSearchCV的加入提高了模型预测性能和拟合能力。通过对于测试集的验证,MI-XGBoost模型的
<math id="M1"><msup><mrow><mi mathvariant="bold-italic">R</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msup></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=72356319&type=
2.53999996
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=72356415&type=
3.13266683
、平均绝对误差、解释方差分数和最大误差的数值分别为0.889 4、0.000 4、0.897 2和0.004 1,均优于MI-RR、MI-RF、MI-GBDT和MI-KNN模型。MI-XGBoost模型实现了终点磷含量的有效预测,为电渣重熔流程终点控制和判断提供了很好的参考,为实现电渣重熔过程智能化提供了一个新思路。
This study proposes a phosphorus content prediction model for the endpoint of electroslag remelting (ESR) refining process based on Mutual Information (MI) method and XGBoost. The MI method is utilized for feature selection and assessment of factors affecting the endpoint phosphorus content. The dataset after feature selection serves as the input variables for the model.The MI-XGBoost model is trained and validated using production data. Grid search cross-validation is employed for model structure adjustment and hyperparameter optimization. It is compared horizontally with MI-RR, MI-RF, MI-GBDT, and MI-KNN models. The results demonstrate that the MI-XGBoost model exhibits the highest prediction accuracy. The incorporation of MI and GridSearchCV enhances the model's predictive performance and fitting ability.Validation of the test set shows that the MI-XGBoost model achieves
<math id="M2"><msup><mrow><mi mathvariant="bold-italic">R</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msup></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=72356417&type=
2.53999996
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=72356418&type=
3.13266683
, Mean Absolute Error, Explained Variance Score, and Maximum Error values of 0.889 4, 0.000 4, 0.897 2, and 0.004 1, respectively, all superior to MI-RR, MI-RF, MI-GBDT, and MI-KNN models. The MI-XGBoost model effectively predicts the endpoint phosphorus content, providing valuable reference for endpoint control and determination in the ESR refining process. It presents a new perspective for realizing the intelligence of the ESR refining process.
Shi C B , Wang S J , Li J , et al . Non-metallic inclusions in electroslag remelting: A review [J]. Journal of Iron and Steel Research International , 2021 , 28 ( 12 ): 1483 - 1503 .
Ahmadi S , Arabi H , Shokuhfar A , et al . Evaluation of the electroslag remelting process in medical grade of 316LC stainless steel [J]. Journal of Materials Science & Technology , 2009 , 25 ( 5 ): 592 - 596 .
刘晓航 , 王肸杰 , 刘 畅 , 等 . 基于BP神经网络的钢包渣眼演化行为的预测 [J]. 钢铁研究学报 , 2024 , 36 ( 4 ): 469 - 480 .
Liu Y X , Dong Y W , Jiang Z H , et al . XGBoost-based model for predicting hydrogen content in electroslag remelting [J]. Journal of Iron and Steel Research International , 2023 , 30 ( 5 ): 887 - 896 .
孙 辉 , 杨 帆 , 高正男 , 等 . 考虑特征重要性值波动的MI-BILSTM短期负荷预测 [J]. 电力系统自动化 , 2022 , 46 ( 8 ): 95 - 103 .
谢万鹏 , 刘 欢 , 吴银花 , 等 . 基于改进SIFT和互信息法的单色和彩色视频高精度配准 [J]. 液晶与显示 , 2023 , 38 ( 12 ): 1689 - 1697 .
李占山 , 杨云凯 , 张家晨 . 基于熵权法的过滤式特征选择算法 [J]. 东北大学学报(自然科学版) , 2022 , 43 ( 7 ): 921 - 929 .
Bentéjac C , Csörgő A , Martínez-Muñoz G . A comparative analysis of gradient boosting algorithms [J]. Artificial Intelligence Review , 2021 , 54 ( 3 ): 1937 - 1967 .
江 丽 , 张智谟 , 王琦玮 , 等 . 基于不同机器学习模型的石油测井数据岩性分类对比研究 [J]. 物探与化探 , 2024 , 48 ( 2 ): 489 - 497 .
宋家威 , 郇宝乾 , 秦 涛 , 等 . 基于IGWO-CatBoost模型的岩石爆破块度预测 [J]. 爆破器材 , 2024 , 53 ( 2 ): 56 - 64 .
Sheridan R P , Wang W M , Liaw A , et al . Extreme gradient boosting as a method for quantitative structure-activity relationships [J]. Journal of Chemical Information and Modeling , 2016 , 56 ( 12 ): 2353 - 2360 .
Montero-Manso P , Athanasopoulos G , Hyndman R J , et al . FFORMA: Feature-based forecast model averaging [J]. International Journal of Forecasting , 2020 , 36 ( 1 ): 86 - 92 .
Friedman J , Hastie T , Tibshirani R . Regularization paths for generalized linear models via coordinate descent [J]. Journal of Statistical Software , 2010 , 33 ( 1 ): 1 - 22 .
梁佳佳 , 何晓霞 , 肖浩逸 . 基于CS-DBN的锂电池剩余寿命预测 [J]. 太阳能学报 , 2024 , 45 ( 3 ): 251 - 259 .
和 征 , 李忠鹏 , 杨小红 . 基于数字孪生与k-近邻算法的车间设备运行状态预测研究 [J]. 制造技术与机床 , 2024 ( 3 ): 193 - 199 .
Friedman J H . Stochastic gradient boosting [J]. Computational Statistics & Data Analysis , 2002 , 38 ( 4 ): 367 - 378 .
彭雷朕 , 姜周华 , 沈国劬 , 等 . 电渣重熔9CrMoCoB钢过程电极表面氧化行为及脱氧制度 [J]. 特殊钢 , 2023 , 44 ( 6 ): 70 - 77 .
Li S J , Cheng G G , Huang Y , et al . Kinetics of phosphorus transfer during industrial electroslag remelting of G20CrNi2Mo bearing steel [J]. Metals , 2019 , 9 ( 4 ): 467 .
Gao G , Zhu C L , Shi X F , et al . Effect of magnetic field on elements segregation in electroslag ingot [J]. Journal of Iron and Steel Research International , 2022 , 29 ( 3 ): 434 - 444 .
Zhong Y B , Qiang L , Fang Y P , et al . Effect of transverse static magnetic field on microstructure and properties of GCr15 bearing steel in electroslag continuous casting process [J]. Materials Science and Engineering: A , 2016 , 660 : 118 - 126 .
李练兵 , 肖亚泽 , 张 萍 , 等 . 基于CWT-RES34的风电机组叶片裂纹状态评估 [J]. 噪声与振动控制 , 2024 , 44 ( 2 ): 143 - 148+293 .
谭建荣 , 高铭宇 , 徐敬华 , 等 . 数智化正向设计方法及其在制造装备与过程中的应用 [J]. 机械工程学报 , 2023 , 59 ( 19 ): 111 - 125 .
0
浏览量
1
下载量
0
CSCD
0
CNKI被引量
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621