Design of comprehensive mechanical properties by machine learning and high-throughput optimization algorithm in RAFM steels

Abstract In order to make reasonable design for the improvement of comprehensive mechanical properties of RAFM steels, the design system with both machine learning and high-throughput optimization algorithm was established. As the basis of the design system, a dataset of RAFM steels was compiled from previous literatures. Then, feature engineering guided random forests regressors were trained by the dataset and NSGA II algorithm were used for the selection of the optimal solutions from the large-scale solution set with nine composition features and two treatment processing features. The selected optimal solutions by this design system showed prospective mechanical properties, which was also consistent with the physical metallurgy theory. This efficiency design mode could give the enlightenment for the design of other metal structural materials with the requirement of multi-properties.

[1]  Zhigang Yang,et al.  Multiscale Simulation of Yield Strength in Reduced-Activation Ferritic/Martensitic Steel , 2017 .

[2]  H. Fu,et al.  Effect of N on the precipitation behaviours of the reduced activation ferritic/martensitic steel CLF-1 after thermal ageing , 2013 .

[3]  George Z. Tan,et al.  Towards energy and material efficient laser cladding process: Modeling and optimization using a hybrid TS-GEP algorithm and the NSGA-II , 2019, Journal of Cleaner Production.

[4]  Ziv Bar-Joseph,et al.  MethRaFo: MeDIP‐seq methylation estimate using a Random Forest Regressor , 2017, Bioinform..

[5]  Lorenzo Malerba,et al.  Effect of W and N on mechanical properties of reduced activation ferritic/martensitic EUROFER-based steel grades , 2018 .

[6]  Nirupam Chakraborti,et al.  Genetic Algorithms in Optimization of Strength and Ductility of Low-Carbon Steels , 2007 .

[7]  Wei Wang,et al.  Effect of Thermal Aging on Microstructure and Mechanical Properties of China Low-Activation Martensitic Steel at 550 °C , 2016 .

[8]  Tae-Ho Lee,et al.  Microstructure and tensile and Charpy impact properties of reduced activation ferritic–martensitic steel with Ti , 2017 .

[9]  Luigi Ferrigno,et al.  Multifrequency Excitation and Support Vector Machine Regressor for ECT Defect Characterization , 2014, IEEE Transactions on Instrumentation and Measurement.

[10]  Lijian Rong,et al.  Effect of silicon on the microstructure and mechanical properties of reduced activation ferritic/martensitic steel , 2015 .

[11]  Sifan Long,et al.  Yield Stress Prediction Model of RAFM Steel Based on the Improved GDM-SA-SVR Algorithm , 2019, Computers, Materials & Continua.

[12]  Ruchira Naskar,et al.  Deep learning approach for segmentation of plain carbon steel microstructure images , 2019, IET Image Process..

[13]  Takuya Yamamoto,et al.  Neural-network analysis of irradiation hardening in low-activation steels , 2006 .

[14]  Huaizhi Han,et al.  Multi-objective optimization of corrugated tube inserted with multi-channel twisted tape using RSM and NSGA-II , 2019, Applied Thermal Engineering.

[15]  Zhigang Yang,et al.  Microstructure evolution and yield strength of CLAM steel in low irradiation condition , 2017 .

[16]  T. Jayakumar,et al.  Effect of tungsten on tensile properties and flow behaviour of RAFM steel , 2013 .

[17]  Michael P. Short,et al.  Predicting the onset of void swelling in irradiated metals with machine learning , 2019, Journal of Nuclear Materials.

[18]  Nirupam Chakraborti,et al.  Identification of Factors Governing Mechanical Properties of TRIP-Aided Steel Using Genetic Algorithms and Neural Networks , 2008 .

[19]  Pilar Fernández,et al.  Metallurgical characterization of the reduced activation ferritic/martensitic steel Eurofer'97 on as-received condition , 2001 .

[20]  Mikhail A. Sokolov,et al.  Effect of Chromium, Tungsten, Tantalum, and Boron on Mechanical Properties of 5-9Cr-WVTaB Steels , 2002 .

[21]  Jie Su,et al.  Microstructure analysis and yield strength simulation in high Co–Ni secondary hardening steel , 2016 .

[22]  Ronald L. Klueh,et al.  Microstructure-mechanical properties correlation of irradiated conventional and reduced-activation martensitic steels , 1995 .

[23]  Shuang Wang,et al.  Parameter optimization and real-time calibration of a measurement-device-independent quantum key distribution network based on a back propagation artificial neural network , 2018, Journal of the Optical Society of America B.

[24]  Ming Hu,et al.  Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation , 2020, Computational Materials Science.

[25]  Wei Xu,et al.  High-throughput design of low-activation, high-strength creep-resistant steels for nuclear-reactor applications , 2016 .

[26]  Zhigang Yang,et al.  Hydrogen's influence on reduced activation ferritic/martensitic steels' elastic properties: density functional theory combined with experiment , 2017 .

[27]  Yang Yang,et al.  Effect of alloying on the properties of 9Cr low activation martensitic steels , 2010 .

[28]  Gregory B Olson,et al.  Genomic materials design: The ferrous frontier , 2013 .

[29]  Revna Acar Vural,et al.  NSGA-II+FEM Based Loss Optimization of Three-Phase Transformer , 2019, IEEE Transactions on Industrial Electronics.

[30]  Dongwon Shin,et al.  Modern Data Analytics Approach to Predict Creep of High-Temperature Alloys , 2018, Acta Materialia.

[31]  Y. Katoh,et al.  Development of new generation reduced activation ferritic-martensitic steels for advanced fusion reactors , 2016 .

[32]  Jie Su,et al.  Multi-scale simulation of hydrogen influenced critical stress intensity in high Co–Ni secondary hardening steel , 2015 .

[33]  David N. Seidman,et al.  Prediction of the yield strength of a secondary-hardening steel , 2013 .

[34]  Ying Liu,et al.  Real time prediction for converter gas tank levels based on multi-output least square support vector regressor , 2012 .

[35]  Subhas Ganguly,et al.  Designing High Strength Multi-phase Steel for Improved Strength-Ductility Balance Using Neural Networks and Multi-objective Genetic Algorithms , 2007 .

[36]  Jie Su,et al.  Analysis of fracture toughness in high Co–Ni secondary hardening steel using FEM , 2015 .

[37]  Mozammel Mia,et al.  Selection of an ideal MQL-assisted milling condition: an NSGA-II-coupled TOPSIS approach for improving machinability of Inconel 690 , 2019, The International Journal of Advanced Manufacturing Technology.

[38]  Subhas Ganguly,et al.  Genetic algorithm-based search on the role of variables in the work hardening process of multiphase steels , 2009 .

[39]  Tae-Ho Lee,et al.  Effect of microstructural evolution by isothermal aging on the mechanical properties of 9Cr-1WVTa reduced activation ferritic/martensitic steels , 2017 .