A review on inverse analysis models in steel material design

Abstract

This paper reviews various inverse analysis models used in steel material design, with a focus on integrating process, microstructure, and properties through advanced machine learning techniques. The study underscores the importance of establishing comprehensive models that effectively link these elements for enhanced materials engineering. Key models discussed include the convolutional neural network–artificial neural network-coupled model, which employs convolutional neural networks for feature extraction; the Bayesian-optimized generative adversarial network–conditional generative adversarial network model, which generates diverse virtual microstructures; the multi-objective optimization model, which concentrates on process–property relationships; and the microstructure–process parallelization model, which correlates microstructural features with process conditions. Each model is assessed for its strengths and limitations, influencing its practical applicability in material design. The paper concludes by advocating for continued improvements in model accuracy and versatility, with the ultimate goal of enhancing steel properties and expanding the scope of data-driven material development.

Keywords

GAN / image regression / inverse analysis / multiple-objective optimization / steel

References

1	Wang Z.-L, Adachi Y. Property prediction and properties-tomicrostructure inverse analysis of steels by a machine-learning approach. Mater Sci Eng, A. 2019;744:661-670.
2	Lertkiatpeeti K, Janya-Anurak C, Uthaisangsuk V. Effects of spatial microstructure characteristics on mechanical properties of dual phase steel by inverse analysis and machine learning approach. Comput Mater Sci. 2024;245:113311.
3	Wang Z.-L, Ogawa T, Adachi Y. Property predictions for dual-phase steels using persistent homology and machine learning. Adv Theor Simul. 2020;3(3):1900227.
4	Kiyomura K, Wang Z.-L, Ogawa T, Adachi Y. Characterization and optimization of pearlite microstructure using persistent homology and Bayesian optimization. ISIJ Int. 2022;62(2):307-312.
5	Wang Z.-L, Ogawa T, Adachi Y. Persistent-homology-based microstructural optimization of materials using t-distributed stochastic neighbor embedding. Adv Theor Simul. 2020;3(7):2000040.
6	Shiraiwa T, Briffod F, Enoki M, Yamazaki K. Inverse analysis of the relationship between three-dimensional microstructures and tensile properties of dual-phase steels. Mater Today Commun. 2022;33:104958.
7	Sawai K, Chen T.-T, Sun F, Ogawa T, Adachi Y. Image regression analysis for linking the microstructure and property of steel. Results Mater. 2024;21:100526.
8	Adachi Y, Chen T.-T, Sun F, et al. Double convolutional neural network (CNN)-Based image regression and combined CNN–artificial neural network (ANN) models for comprehensive linkage of process, microstructure, and property in additive-manufactured 316L stainless steel. Results Mater under Rev. n.d.
9	Edelsbrunner H, Harer J. Computational Topology: An Introduction. American Mathematical Society;2010.
10	Jiao Y, Stillinger FH, Torquato S. Modeling heterogeneous materials via two-point correlation functions. II. Algorithmic details and applications. Phys Rev E. 2008;77(3):031135.
11	McInnes L, Healy J, James M. Uniform Manifold approximation and projection for dimension reduction. arXiv Prepr arXiv:1802.03426. 2018.
12	Sharifi MR, Akbarifard S, Qaderi K, Madadi MR. A new optimization algorithm to solve multi-objective problems. Sci Rep. 2021;11(1):20326.
13	Fukatsu Y, Chen T.-T, Ogawa T, et al. Maximization of strength–ductility balance of dual-phase steels using generative adversarial networks and Bayesian optimization. Mater Today Commun. 2024;41:110360.
14	Fukatsu Y, Chen T.-T, Ogawa T, et al. Analysis of the strength–ductility balance of dual-phase steel using a combination of generative adversarial networks and finite element method. Comput Mater Sci. 2024;243:113143.
15	Suzuki M, Shizawa K, Muramatsu M. Deep learning-aided inverse analysis framework to accelerate the exploration of DP steel microstructures. Mater Today Commun. 2024;41:110557.
16	Sawai K, Chen T.-T, Sun F, Ogawa T, Adachi Y. Optimization of Heat Treatment Conditions for Reverted Martensitic Steel Using Machine Learning. Proc. ISIJ Fall Meeting;2024. Osaka [CD-ROM].
17	Wang Z.-L, Ogawa T, Adachi Y. Properties-to-microstructure-toprocessing inverse analysis for steels via machine learning. ISIJ Int. 2019;59(9):1691-1694.
18	Papadimitriou I, Gialampoukidis I, Vrochidis S, Kompatsiaris I. AI methods in materials design, discovery and manufacturing: a review. Comput Mater Sci. 2024;235:112793.
19	Sharma A, Kosasih E, Zhang J, Brintrup A, Calinescu A. Digital Twins: state of the art theory and practice, challenges, and open research questions. J Ind Inf Integr. 2022;30:100383.
20	Doersch R. Tutorial on variational Autoencoders. arXiv:1606.05908v3 [stat.ML]. 2021.
21	Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. Adv Neural Inf Process Syst. 2014;27:2672.
22	Kench S, Cooper SJ. Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion. Nat Mach Intell. 2021;3(4):299-305.
23	Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models, arXiv:2006.11239v2 [cs.LG], 2020.
24	Huang X, Belongie S, Arbitrary style transfer in real-time with adaptive instance normalization, arXiv:1703.06868v2 [cs.CV], 2017.
25	Dosovitskiy A, Beyer L, Kolesnikov A, et al. AN image IS worth 16X16 words: transformers for image recognition at scale, arXiv:2010.11929v2 [cs.CV], 2021.