任鑫,王浩鑫,樊献金,孙涛,王港

• 1:辽宁工程技术大学材料科学与工程学院

摘要(Abstract)：

时间-温度-转变(TTT)图是制定钢的优化热处理工艺的重要工具，但是实验测定相当耗时且昂贵，并且计算方法也较为单一。因此，有必要开发一种快速准确预测TTT图的替代方法。本文将Artificial Neural Network(ANN)、K-Nearest Neighbor(IBK)、Bootstrap Aggregating(Bagging)、Random Committee(RC)、Gaussian Processes(GP)、Self-Organizing Maps(SOM)和Random Forest(RF)算法结合起来，形成组合式机器学习(CML)算法，用于预测Cr系合金结构钢的TTT图，其参数包括了合金化元素、奥氏体化温度和时间。使用相关系数(CC)、误差分析(RMSE、MAE)和性能拟合进行验证和筛选模型。本项工作应用CML模型来预测4种Cr系合金钢的TTT图，以评估模型的预测能力。最后，还将CML模型的预测结果与JMatPro软件的预测结果进行了比较。结果表明：与JMatPro相比，CML模型误差值小，预测结果与实际值较为接近。

关键词(KeyWords)： 机器学习;合金结构钢;时间-温度-转变图;算法

Abstract:

Keywords:

基金项目(Foundation): 辽宁省教育厅科学研究经费项目(LJ2020JCL027)

作者(Author): 任鑫,王浩鑫,樊献金,孙涛,王港

DOI: 10.13289/j.issn.1009-6264.2022-0541

参考文献(References)：

• [1] Vlasov V M,Zelenko V K,Malenko P I.Combined low-temperature chemicothermal treatment of structural alloy steels[J].Metal Science and Heat Treatment,2002,44(5/6):258-262.
• [2] Huang X Y,Wang H,Xue W H,et al.Study on time-temperature-transformation diagrams of stainless steel using machine-learning approach[J].Computational Materials Science,2020,171:109282.
• [3] Zhao J C,Notis M R.Continuous cooling transformation kinetics versus isothermal transformation kinetics of steels:A phenomenological rationalization of experimental observations[J].Materials Science & Engineering R,1995,15(4/5):135-207.
• [4] Zhang Y P,Zhan D P,Qi X W,et al.Effect of tempering temperature on the microstructure and properties of ultrahigh-strength stainless steel[J].Journal of Materials Science & Technology,2019,35(7):1240-1249.
• [5] Powell D J,Pilkington R,Miller D A.The precipitation characteristics of 20% Cr/25% Ni-Nb stabilised stainless steel[J].Acta Metallurgica,1988,36(3):713-724.
• [6] Geng X X,Wang H,Xue W H,et al.Modeling of CCT diagrams for tool steels using different machine learning techniques[J].Computational Materials Science,2020,171:109235.
• [7] Castellero A,Fiore G,Steenberge N V,et al.Processing a Fe67Mo4.5Cr2.3Al2Si3C7P8.7B5.5 metallic glass:Experimental and computed TTT and CCT curves[J].Journal of Alloys and Compounds,2020,843:156061.
• [8] Trzaska J,Dobrzański L A.Modelling of CCT diagrams for engineering and constructional steels[J].Journal of Materials Processing Technology,2007,192(S1):504-510.
• [9] Huang X Y,Wang H,Xue W H,et al.A combined machine learning model for the prediction of time-temperature-transformation diagrams of high-alloy steels[J].Journal of Alloys and Compounds,2020,823:153694.
• [10] Rauch L,Kuziak R,Pietrzyk M.From high accuracy to high efficiency in simulations of processing of dual-phase steels[J].Metallurgical and Materials Transactions,2014,45(2):497-506.
• [11] Barmak K.A commentary on:“Reaction kinetics in processes of nucleation and growth”[J].Metallurgical and Materials Transactions B,2018,49(6):3616-3680.
• [12] Li M V,Niebuhr D V,Meekisho L L,et al.A computational model for the prediction of steel hardenability[J].Metallurgical and Materials Transactions B,1998,29(3):661-672.
• [13] Tougui I,Jilbab A,Mhamdi J E.Heart disease classification using data mining tools and machine learning techniques[J].Health and Technology,2020,10(5):1137-1144.
• [14] Jiang X,Yin H Q,Zhang C,et al.An materials informatics approach to Ni-based single crystal superalloys lattice misfit prediction[J].Computational Materials Science,2018,143:295-300.
• [15] Gola J,Webel J,Britz D,et al.Objective microstructure classification by support vector machine (SVM) using a combination of morphological parameters and textural features for low carbon steels[J].Computational Materials Science,2019,160:186-196.
• [16] Kundu M,Ganguly S,Datta S,et al.Simulating time temperature transformation diagram of steel using artificial neural network[J].Materials and Manufacturing Processes,2009,24(2):169-173.
• [17] Pillai N,Karthikeyan R.Prediction of TTT curves of cold working tool steels using support vector machine model[J].IOP Conference Series:Materials Science and Engineering,2018,346(1):012067.
• [18] Geng X X,Wang H,Ullah A,et al.Prediction of continuous cooling transformation diagrams for Ni-Cr-Mo welding steels via machine learning approaches[J].JOM,2020,72(11):3926-3934.
• [19] Deng Z H,Yin H Q,Jiang X,et al.Machine-learning-assisted prediction of the mechanical properties of Cu-Al alloy[J].International Journal of Minerals,Metallurgy and Materials,2020,27(3):362-373.
• [20] Schumacher O,Marvel C J,Kelly M N,et al.Complexion time-temperature-transformation (TTT) diagrams:Opportunities and challenges[J].Current Opinion in Solid State & Materials Science,2016,20(5):316-323.
• [21] Takahashi K,Tanaka Y.Material synthesis and design from first principle calculations and machine learning[J].Computational Materials Science,2016,112:364-367.
• [22] Qiao L,Zhu J C,Wang Y.Coupling physics in machine learning to predict interlamellar spacing and mechanical properties of high carbon pearlitic steel[J].Materials Letters,2021,293:129645.
• [23] Li S Z,Zhang H R,Dai D B,et al.Study on the factors affecting solid solubility in binary alloys:An exploration by Machine Learning[J].Journal of Alloys and Compounds,2019,782:110-118.
• [24] Jiang X,Yin H Q,Zhang C,et al.An materials informatics approach to Ni-based single crystal superalloys lattice misfit prediction[J].Computational Materials Science,2018,143:295-300.
• [25] Wang C S,Fu H D,Jiang L,et al.A property-oriented design strategy for high performance copper alloys via machine learning[J].npj Computational Materials,2019,5(1):261-270.
• [26] Bobbitt N S,Snurr R Q.Molecular modelling and machine learning for high-throughput screening of metal-organic frameworks for hydrogen storage[J].Molecular Simulation,2019,45(14/15):1069-1081.
• [27] Chelgani S C,Matin S S,Makaremi S.Modeling of free swelling index based on variable importance measurements of parent coal properties by random forest method[J].Measurement,2016,94:416-422.
• [28] Viji C,Rajkumar N,Duraisamy S.Prediction of software fault-prone classes using an unsupervised hybrid SOM algorithm[J].Cluster Computing,2019,22(S1):133-143.
• [29] Ni M H,Cheng H Q,Lai J F.GAN-SOM:A clustering framework with SOM-similar network based on deep learning[J].The Journal of Supercomputing,2020,77(5):4871-4886.
• [30] Heung B,Bulmer C E,Schmidt M G.Predictive soil parent material mapping at a regional-scale:A Random Forest approach[J].Geoderma,2014,214-215:141-154.
• [31] Diamantidis N A,Karlis D,Giakoumakis E A.Unsupervised stratification of cross-validation for accuracy estimation[J].Artificial Intelligence,2000,116(1/2):1-16.
• [32] Hayajneh M T,Hassan A M,Mayyas A T.Artificial neural network modeling of the drilling process of self-lubricated aluminum/alumina/graphite hybrid composites synthesized by powder metallurgy technique[J].Journal of Alloys and Compounds,2009,478(1/2):559-565.
• [33] Jiang X,Yin H Q,Zhang C,et al.An materials informatics approach to Ni-based single crystal superalloys lattice misfit prediction[J].Computational Materials Science,2018,143:295-300.
• [34] Trzaska J,Jagie??o A,Dobrzański L A.The calculation of CCT diagrams for engineering steels[J].Archives of Materials Science and Engineering,2009,39(1):13-20.
• [35] Li M V,Niebuhr D V,Meekisho L L,et al.A computational model for the prediction of steel hardenability[J].Metallurgical and Materials Transactions B,1998,29(3):661-672.
• [36] Marion M,Michael W,Michael L,et al.Hot stamping of boron steel sheets with tailored properties:A review[J].Journal of Materials Processing Technology,2015,228:11-24.

文章评论(Comment)：