Towards an instant structure-property prediction quality control tool for additive manufactured steel using a crystal plasticity trained deep learning surrogate
Source abstract
Abstract
The ability to conduct in-situ real-time process-structure-property checks has the potential to overcome process and material uncertainties, which are key obstacles to improved uptake of metal powder bed fusion in industry. Efforts are underway for live process monitoring such as thermal and image-based data gathering for every layer printed. Current crystal plasticity finite element (CPFE) modelling is capable of predicting the associated strength based on a microstructural image and material data but is computationally expensive. This work utilizes a large database of input–output samples from CPFE modelling to develop a trained deep neural network (DNN) model which instantly estimates the output (strength prediction) associated with a given input (microstructure) of multi-phase additive manufactured stainless steels. The DNN model successfully recognizes phase regions and the associated unique crystallographic orientation variations. It also captures differences in macroscopic stress response due to the varying microstructure. However, it is less reliable in terms of fatigue life predictions. The DNN model exhibits high accuracy for the structure–property relationship as a surrogate prediction tool compared to CPFE while significantly reducing the computational cost to just a few seconds.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing Materials and Processes · Titanium Alloys Microstructure and Properties · Welding Techniques and Residual Stresses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (90)
Show source-provided references
1. Steels in additive manufacturing: A review of their microstructure and properties10.1016/j.msea.2019.138633 ↗
2. Overview of constitutive laws, kinematics, homogenization and multiscale methods in crystal plasticity finite-element modeling: Theory, experiments, applications10.1016/j.actamat.2009.10.058 ↗
3. Crystal plasticity10.1115/1.3167205 ↗
4. Chapter 6 - Metal additive manufacturing process modeling and simulation
5. Micromechanical modeling approach to single track deformation, phase transformation and residual stress evolution during selective laser melting using crystal plasticity
6. Functionally graded bimodal Ti6Al4V fabricated by powder bed fusion additive manufacturing: Crystal plasticity finite element modelling10.1016/j.msea.2019.138736 ↗
7. Crystal plasticity modeling of 3rd generation multi-phase AHSS with martensitic transformation10.1016/j.ijplas.2019.03.010 ↗
8. Crystal plasticity simulation of the effect grain size on the fatigue behavior of polycrystalline Inconel 718
9. Strain-gradient modelling of grain size effects on fatigue of CoCr stents10.1016/j.actamat.2014.06.044 ↗
10. Simulation of the Hall-Petch effect in FCC polycrystals by means of strain gradient crystal plasticity and FFT homogenization10.1016/j.jmps.2019.103755 ↗
11. Intergranular and intragranular behavior of polycrystalline aggregates. Part 1: F.E. model10.1016/S0749-6419(00)00061-9 ↗
12. A systematic study of hcp crystal orientation and morphology effects in polycrystal deformation and fatigue10.1098/rspa.2007.1833 ↗
13. A texture-based representative volume element crystal plasticity model for predicting Bauschinger effect during cyclic loading10.1016/j.msea.2014.04.067 ↗
14. Two stage deformation modeling for DP 780 steel sheet using crystal plasticity10.1016/j.msea.2014.03.002 ↗
15. The sources of the micro stress and strain inhomogeneity in dual phase steels10.1016/j.msea.2016.07.028 ↗
16. A micro mechanical study on failure initiation of dual phase steels under tension using single crystal plasticity model10.1016/j.ijplas.2010.12.001 ↗
17. A multi-scale crystal plasticity model for cyclic plasticity and low-cycle fatigue in a precipitate-strengthened steel at elevated temperature10.1016/j.jmps.2016.12.010 ↗
18. Lengthscale-dependent, elastically anisotropic, physically-based hcp crystal plasticity: Application to cold-dwell fatigue in Ti alloys10.1016/j.ijplas.2006.10.013 ↗
19. Y. Tu, S.B. Leen, N.M. Harrison, A high-fidelity crystal-plasticity finite element methodology for low-cycle fatigue using automatic electron backscatter diffraction scan conversion: Application to hot-rolled cobalt–chromium alloy, Proc. Instit. Mech. Eng., Part L: J. Mater.: Des. Appl. (2021) 14644207211010836.10.1177/14644207211010836 ↗
20. On the crack initiation and heterogeneous deformation of Ti-6Al-4V during high cycle fatigue at high R ratios10.1016/j.jmps.2019.04.017 ↗
21. Structural Representation of Additively Manufactured 316L Austenitic Stainless Steel10.1016/j.ijplas.2019.01.012 ↗
22. Micromechanical finite element modelling of thermo-mechanical fatigue for P91 steels10.1016/j.ijfatigue.2015.11.025 ↗
23. Microstructurally-sensitive fatigue crack growth in HCP, BCC and FCC polycrystals10.1016/j.jmps.2019.02.012 ↗
24. P.J. Ashton, T.-S. Jun, Z. Zhang, T.B. Britton, A.M. Harte, S.B. Leen, F.P.E. Dunne, The effect of the beta phase on the micromechanical response of dual-phase titanium alloys, 100(P1) (2017).10.1016/j.ijfatigue.2017.03.020 ↗
25. The role of elastic anisotropy, length scale and crystallographic slip in fatigue crack nucleation10.1016/j.jmps.2013.01.001 ↗
26. An upscaling approach for micromechanics based fatigue: from RVEs to specimens and component life prediction
27. Metal Additive Manufacturing: A Review10.1007/s11665-014-0958-z ↗
28. Mechanical behavior of additive manufactured, powder-bed laser-fused materials10.1016/j.msea.2015.10.068 ↗
29. Effects of particle characteristics on the microstructure and mechanical properties of 17–4 PH stainless steel fabricated by laser-powder bed fusion10.1016/j.powtec.2018.03.025 ↗
30. Microstructure and mechanical behavior of 17–4 precipitation hardenable steel processed by selective laser melting10.1007/s11665-014-1226-y ↗
31. Effect of heat treatments on microstructural evolution of additively manufactured and wrought 17–4PH stainless steel10.1016/j.matdes.2018.07.015 ↗
32. Effects of crack orientation and heat treatment on fatigue-crack-growth behavior of AM 17–4 PH stainless steel10.1016/j.engfracmech.2020.106874 ↗
33. Cyclic deformation and fatigue behavior of additively manufactured 17–4 PH stainless steel10.1016/j.ijfatigue.2019.02.006 ↗
34. Effect of scan pattern on the microstructure and mechanical properties of Powder Bed Fusion additive manufactured 17–4 stainless steel10.1016/j.matdes.2017.07.047 ↗
35. Effect of heat-treatment on the microstructure, mechanical properties and corrosion behaviour of SS 316 structures built by laser directed energy deposition based additive manufacturing10.1007/s12540-020-00838-y ↗
36. Effect of heat treatment on microstructure, mechanical and corrosion properties of austenitic stainless steel 316L using arc additive manufacturing10.1016/j.msea.2017.10.002 ↗
37. A. Azarniya, X.G. Colera, M.J. Mirzaali, S. Sovizi, F. Bartolomeu, M.k. St Weglowski, W.W. Wits, C.Y. Yap, J. Ahn, G. Miranda, F.S. Silva, H.R. Madaah Hosseini, S. Ramakrishna, A.A. Zadpoor, Additive manufacturing of Ti–6Al–4V parts through laser metal deposition (LMD): Process, microstructure, and mechanical properties, J. Alloys Compounds 804 (2019) 163–191.10.1016/j.jallcom.2019.04.255 ↗
38. Microstructure and mechanical properties of long Ti-6Al-4V rods additively manufactured by selective electron beam melting out of a deep powder bed and the effect of subsequent hot isostatic pressing10.1007/s11661-015-2976-3 ↗
39. Prediction of age hardening parameters for 17–4PH stainless steel by artificial neural network and genetic algorithm10.1016/j.msea.2016.08.049 ↗
40. Parametrically homogenized constitutive models (PHCMs) from micromechanical crystal plasticity FE simulations, part I: Sensitivity analysis and parameter identification for Titanium alloys10.1016/j.ijplas.2019.05.008 ↗
41. Using machine learning and a data-driven approach to identify the small fatigue crack driving force in polycrystalline materials10.1038/s41524-018-0094-7 ↗
42. Machine learning-based accelerated property prediction of two-phase materials using microstructural descriptors and finite element analysis10.1016/j.commatsci.2021.110328 ↗
43. A machine learning method for defect detection and visualization in selective laser sintering based on convolutional neural networks
44. In-Process monitoring of porosity during laser additive manufacturing process
45. Material structure-property linkages using three-dimensional convolutional neural networks10.1016/j.actamat.2017.11.053 ↗
46. An efficient machine learning approach to establish structure-property linkages10.1016/j.commatsci.2018.09.034 ↗
47. Predicting the mechanical response of oligocrystals with deep learning10.1016/j.commatsci.2019.109099 ↗
48. Machine learning-based reduce order crystal plasticity modeling for ICME applications10.1007/s40192-018-0123-x ↗
49. Deep neural network approach to estimate biaxial stress-strain curves of sheet metals10.1016/j.matdes.2020.108970 ↗
50. Applied machine learning to predict stress hotspots II: Hexagonal close packed materials10.1016/j.ijplas.2018.08.003 ↗
51. ASTM International. E606/E606M-21 Standard Test Method for Strain-Controlled Fatigue Testing. West Conshohocken, PA, 2021.
52. Dream. 3D: A digital representation environment for the analysis of microstructure in 3D10.1186/2193-9772-3-5 ↗
53. ABAQUS, Dassault Systèmes Simulia Corp.
54. Heterogeneous linear elastic trabecular bone modelling using micro-CT attenuation data and experimentally measured heterogeneous tissue properties10.1016/j.jbiomech.2008.05.014 ↗
55. J.H. Friedman, The elements of statistical learning: Data mining, inference, and prediction, springer open2017.
56. D. Systèmes, ABAQUS Documentation.
57. A numerical study into element type and mesh resolution for crystal plasticity finite element modeling of explicit grain structures10.1007/s00466-020-01918-x ↗
58. Statistical grain size effects in fretting crack initiation10.1016/j.triboint.2016.09.022 ↗
59. Huang · 1991
60. Micromechanical methodology for fatigue in cardiovascular stents10.1016/j.ijfatigue.2012.04.022 ↗
61. K. Shoemake, III.5. - Euler Angle Conversion, in: P.S. Heckbert (Ed.), Graphics Gems, Academic Press, 1994, pp. 222-229.10.1016/B978-0-12-336156-1.50030-6 ↗
62. K.M.K. Anthony Kelly, Appendix 5: Slip Systems in C.C.P. and B.C.C. Crystals, Crystallography and Crystal Defects, Wiley, 2012, pp. 481–486.10.1002/9781119961468.app5 ↗
63. A. Manonukul, F.P.E. Dunne, High– and low–cycle fatigue crack initiation using polycrystal plasticity, Proc. Roy. Soc. London. Series A: Math., Phys. Eng. Sci. 460(2047) (2004) 1881–1903.10.1098/rspa.2003.1258 ↗
64. Fatigue crack nucleation: Mechanistic modelling across the length scales10.1016/j.cossms.2014.02.005 ↗
65. Microstructure-sensitive computational modeling of fatigue crack formation10.1016/j.ijfatigue.2010.01.003 ↗
66. Crystal plasticity simulation of the effect of grain size on the fatigue behavior of polycrystalline Inconel 71810.1016/j.ijfatigue.2018.04.018 ↗
67. Microstructure-based fatigue life model of metallic alloys with bilinear Coffin-Manson behavior10.1016/j.ijfatigue.2017.10.014 ↗
68. Ashton · 2018
69. Experimental characterisation for micromechanical modelling of CoCr stent fatigue10.1016/j.biomaterials.2013.09.087 ↗
70. Influence of statistical size effects on the plastic deformation of coronary stents10.1016/j.jmbbm.2012.12.008 ↗
71. A. Zhang, Z.C. Lipton, M. Li, A.J. Smola, Dive into deep learning, arXiv preprint arXiv:2106.11342 (2021).
72. Artificial Neural Network
73. Siamese Neural Networks: An Overview
74. J. Wu, Introduction to convolutional neural networks, National Key Lab for Novel Software Technology. Nanjing University. China 5(23) (2017) 495.
75. S. Albawi, T.A. Mohammed, S. Al-Zawi, Understanding of a convolutional neural network, 2017 International Conference on Engineering and Technology (ICET), 2017, pp. 1-6.10.1109/ICEngTechnol.2017.8308186 ↗
76. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, Tensorflow: Large-scale machine learning on heterogeneous distributed systems, arXiv preprint arXiv:1603.04467 (2016).
77. Multimodal similarity-preserving hashing10.1109/TPAMI.2013.225 ↗
78. A. Gulli, A. Kapoor, S. Pal, Deep learning with TensorFlow 2 and Keras: regression, ConvNets, GANs, RNNs, NLP, and more with TensorFlow 2 and the Keras API, Packt Publishing Ltd, 2019.
79. Multiscale modelling of mechanical response in a martensitic steel: A micromechanical and length-scale-dependent framework for precipitate hardening10.1016/j.actamat.2014.08.012 ↗
80. Microstructure-based modelling and Digital Image Correlation measurement of strain fields in austenitic stainless steel 316L during tension loading10.1016/j.msea.2019.02.063 ↗
81. Incorporating grain-level residual stresses and validating a crystal plasticity model of a two-phase Ti-6Al-4 V alloy produced via additive manufacturing10.1016/j.jmps.2018.07.025 ↗
82. Mechanical behavior of selective laser melted 316L stainless steel10.1016/j.msea.2017.04.058 ↗
83. Mechanism of high yield strength and yield ratio of 316 L stainless steel by additive manufacturing10.1016/j.msea.2018.12.092 ↗
84. Twinning induced plasticity in austenitic stainless steel 316L made by additive manufacturing10.1016/j.msea.2017.07.082 ↗
85. Effects of processing parameters on tensile properties of selective laser melted 304 stainless steel10.1016/j.matdes.2013.03.056 ↗
86. Individual phase constitutive properties of a TRIP-assisted QP980 steel from a combined synchrotron X-ray diffraction and crystal plasticity approach10.1016/j.actamat.2017.04.028 ↗
87. PRISMS-Fatigue computational framework for fatigue analysis in polycrystalline metals and alloys10.1038/s41524-021-00506-8 ↗
88. Experimental investigation into selective laser melting of austenitic and martensitic stainless steel powder mixtures10.1243/09544054JEM1574 ↗
89. Prediction of microstructure evolution for additive manufacturing of Ti-6Al-4V10.1016/j.promfg.2020.04.170 ↗
90. Towards a process-structure model for Ti-6Al-4V during additive manufacturing10.1016/j.jmapro.2020.11.033 ↗