yNet: a multi-input convolutional network for ultra-fast simulation of field evolvement

The capability of multi-input field-to-field regression, i.e. mapping the initial field and applied conditions to the evolved field, is appealing, enabling ultra-fast physics-free simulation of various field evolvements across many disciplines. We hereby propose a y-shaped multi-input deep convolutional network, yNet, which can effectively account for combined effects of multiple mixed inputs on output field. The proposed yNet is applied to the simulation of porosity evolution in selective lasering sintering (SLS). Upon testing, yNet can simulate nearly identical porosity evolution and development to the physics-based model, with a 99.13% morphological similarity for various SLS conditions. We then effortlessly boost the porosity simulation capability to the realistic, full-component level. yNet is generally applicable to simulating various structural/morphological evolutions and other conditionconcerned, continuous field evolvements even with spatially and/or temporally non-uniform evolving kinetics. Once trained, the light-weight yNet can be distributed easily and ran with limited computational resource while reducing computation time to a split second. It thus may have a transformative impact by democratizing the capability of ultra-fast and extreme-scale simulation of various field evolvements.

[1]  Bai-Xiang Xu,et al.  Non-isothermal Phase-Field Modeling of Heat–Melt–Microstructure-Coupled Processes During Powder Bed Fusion , 2020, JOM.

[2]  Charlie C. L. Wang,et al.  Current and future trends in topology optimization for additive manufacturing , 2018 .

[3]  Wei Chen,et al.  A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions , 2018, Scientific Reports.

[4]  Wei-keng Liao,et al.  Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets , 2018 .

[5]  Jingjing Li,et al.  Hybrid-DNNs: Hybrid Deep Neural Networks for Mixed Inputs , 2020, ArXiv.

[6]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[7]  Long-Qing Chen.  Phase-Field Models for Microstructure Evolution , 2002 .

[8]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[9]  Shiguo Lian,et al.  Vision-based Robotic Grasping from Object Localization, Pose Estimation, Grasp Detection to Motion Planning: A Review , 2019, ArXiv.

[10]  Wenbo Wang,et al.  Predicting Manufactured Shapes of a Projection Micro-Stereolithography Process via Convolutional Encoder-Decoder Networks , 2018 .

[11]  Sanjay Kumar.  Selective laser sintering: A qualitative and objective approach , 2003 .

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Sotirios A. Tsaftaris,et al.  Medical Image Computing and Computer Assisted Intervention , 2017 .

[14]  Allen R. Roach,et al.  Sintering processes in direct ink write additive manufacturing: A mesoscopic modeling approach , 2019, Acta Materialia.

[15]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Seshadev Sahoo,et al.  Investigation of consolidation kinetics and microstructure evolution of Al alloys in direct metal laser sintering using phase field simulation , 2018 .

[17]  Yu Liu,et al.  A review of semantic segmentation using deep neural networks , 2017, International Journal of Multimedia Information Retrieval.

[18]  Josef F. Christ,et al.  “Sintering” Models and In-Situ Experiments: Data Assimilation for Microstructure Prediction in SLS Additive Manufacturing of Nylon Components , 2020, MRS Advances.

[19]  Yong-Wei Zhang,et al.  Phase field simulation of powder bed-based additive manufacturing , 2018 .

[20]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Jon C. Helton,et al.  Latin Hypercube Sampling and the Propagation of Uncertainty in Analyses of Complex Systems , 2002 .

[22]  Mark F. Horstemeyer,et al.  Insight into the mechanisms of columnar to equiaxed grain transition during metallic additive manufacturing , 2019, Additive Manufacturing.

[23]  Levent Burak Kara,et al.  Deep Learning for Stress Field Prediction Using Convolutional Neural Networks , 2018, J. Comput. Inf. Sci. Eng..

[24]  Gengdong Cheng,et al.  Multi-objective concurrent topology optimization of thermoelastic structures composed of homogeneous porous material , 2013 .

[25]  Yucheng Liu,et al.  Investigation on Microsegregation of IN718 Alloy During Additive Manufacturing via Integrated Phase-Field and Finite-Element Modeling , 2018, Journal of Materials Engineering and Performance.

[26]  Christoph Broeckmann,et al.  A comparative study of different sintering models for Al2O3 , 2016 .

[27]  John W. Elmer,et al.  Three-dimensional modeling of grain structure evolution during welding of an aluminum alloy , 2017 .

[28]  Trevor Darrell,et al.  Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  José García Rodríguez,et al.  A Review on Deep Learning Techniques Applied to Semantic Segmentation , 2017, ArXiv.

[30]  Lei Chen,et al.  Modulation of dendritic patterns during electrodeposition: A nonlinear phase-field model , 2015 .

[31]  Elizabeth A. Holm,et al.  A computer vision approach for automated analysis and classification of microstructural image data , 2015 .

[32]  Ashley D. Spear,et al.  Predicting microstructure-dependent mechanical properties in additively manufactured metals with machine- and deep-learning methods , 2020, Computational Materials Science.

[33]  Erin Antono,et al.  Building Data-driven Models with Microstructural Images: Generalization and Interpretability , 2017, ArXiv.

[34]  Houfa Shen,et al.  Advances in multi-scale modeling of solidification and casting processes , 2011 .

[35]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Yu U. Wang.  Computer modeling and simulation of solid-state sintering: A phase field approach , 2006 .

[37]  Yunzhi Wang,et al.  Simulating Microstructural Evolution and Electrical Transport in Ceramic Gas Sensors , 2004 .

[38]  Torsten Kraft,et al.  Particle-based simulation, dimensional analysis and experimental validation of laser absorption and thermo-viscous flow during sintering of polymers , 2020 .

[39]  Yaser Shanjani,et al.  Characterizations of additive manufactured porous titanium implants. , 2012, Journal of biomedical materials research. Part B, Applied biomaterials.

[40]  Zi-kui Liu,et al.  An integrated fast Fourier transform-based phase-field and crystal plasticity approach to model recrystallization of three dimensional polycrystals , 2015 .

[41]  Christopher M Wolverton,et al.  Predicting β′ precipitate morphology and evolution in Mg–RE alloys using a combination of first-principles calculations and phase-field modeling , 2014 .

[42]  Nicholas Zabaras,et al.  Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification , 2018, J. Comput. Phys..

[43]  Lin Cheng,et al.  Efficient design optimization of variable-density cellular structures for additive manufacturing: theory and experimental validation , 2017 .

[44]  Z. Wang,et al.  Investigation on evolution mechanisms of site-specific grain structures during metal additive manufacturing , 2018, Journal of Materials Processing Technology.

[45]  Ryutaro Tanaka,et al.  Permeability and strength of a porous metal structure fabricated by additive manufacturing , 2015 .