PATO: Producibility-Aware Topology Optimization using Deep Learning for Metal Additive Manufacturing

In this paper, we propose PATO—a producibility-aware topology optimization (TO) framework to help efficiently explore the design space of components fabricated using metal additive manufacturing (AM), while ensuring manufacturability with respect to cracking. Specifically, parts fabricated through Laser Powder Bed Fusion (LPBF) are prone to defects such as warpage or cracking due to high residual stress values generated from the steep thermal gradients produced during the build process. Maturing the design for such parts and planning their fabrication can span months to years, often involving multiple handoffs between design and manufacturing engineers. PATO is based on the a priori discovery of crack-free designs, so that the optimized part can be built defect-free at the outset. To ensure that the design is crack free during optimization, producibility is explicitly encoded within the standard formulation of TO, using a crack index. Multiple crack indices are explored and using experimental validation, maximum shear strain index (MSSI) is shown to be an accurate crack index. Simulating the build process, in order to estimate MSSI, is a coupled, multi-physics, time-complex computation and incorporating it in the TO loop can be computationally prohibitive. We leverage the current advances in deep convolutional neural networks (DCNN) and present a high-fidelity surrogate model based on an Attention-based U-Net architecture to predict the MSSI values as a spatially varying field over the part’s domain. Further, we employ automatic differentiation to directly compute the gradient of maximum MSSI with respect to the input design variables and augment it with the performance-based sensitivity field to optimize the design while considering the trade-off between weight, manufacturability, and functionality. We demonstrate the effectiveness of the proposed method through benchmark studies in 3D as well as experimental validation.

[1]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[2]  Nikos D. Lagaros,et al.  Accelerated topology optimization by means of deep learning , 2020, Structural and Multidisciplinary Optimization.

[3]  Yiming Zhang,et al.  Attention-Based 3D Neural Architectures for Predicting Cracks in Designs , 2021, ICANN.

[4]  Matthijs Langelaar,et al.  Topology optimization of 3D self-supporting structures for additive manufacturing , 2016 .

[5]  A. Gurson.  Plastic flow and fracture behavior of ductile materials incorporating void nucleation, growth and interaction , 1988 .

[6]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Yipeng Hu,et al.  Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration , 2019, Medical Image Anal..

[8]  V. Tvergaard.  Influence of voids on shear band instabilities under plane strain conditions , 1981 .

[9]  Saigopal Nelaturi,et al.  Exploring Feasible Design Spaces for Heterogeneous Constraints , 2019, Comput. Aided Des..

[10]  Rahul Rai,et al.  Deep learning–based stress prediction for bottom-up SLA 3D printing process , 2019, The International Journal of Advanced Manufacturing Technology.

[11]  Mu Zhu,et al.  Casting and Milling Restrictions in Topology Optimization via Projection-Based Algorithms , 2012, DAC 2012.

[12]  Krishnan Suresh,et al.  Multi-Material Topology Optimization Using Neural Networks , 2021, Comput. Aided Des..

[13]  Yong Li,et al.  Applying Neural-Network-Based Machine Learning to Additive Manufacturing: Current Applications, Challenges, and Future Perspectives , 2019, Engineering.

[14]  Lothar Harzheim,et al.  A review of optimization of cast parts using topology optimization , 2005 .

[15]  V. Paquit,et al.  Correlations of cracking with scan strategy and build geometry in electron beam powder bed additive manufacturing , 2020 .

[16]  Thomas de Quincey.  [C] , 2000, The Works of Thomas De Quincey, Vol. 1: Writings, 1799–1820.

[17]  Zhan Kang,et al.  Structural shape and topology optimization of cast parts using level set method , 2017 .

[18]  Krishnan Suresh,et al.  Length Scale Control in Topology Optimization using Fourier Enhanced Neural Networks , 2021, ArXiv.

[19]  K. Svanberg.  The method of moving asymptotes—a new method for structural optimization , 1987 .

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

[21]  Matthijs Langelaar,et al.  Topology optimization for multi-axis machining , 2019, Computer Methods in Applied Mechanics and Engineering.

[22]  William E. Frazier,et al.  Metal Additive Manufacturing: A Review , 2014, Journal of Materials Engineering and Performance.

[23]  Krishnan Suresh,et al.  TOuNN: Topology Optimization using Neural Networks , 2020, Structural and Multidisciplinary Optimization.

[24]  T. Wierzbicki,et al.  On fracture locus in the equivalent strain and stress triaxiality space , 2004 .

[25]  Ben Glocker,et al.  Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images , 2018, Medical Image Anal..

[26]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[27]  Song Wang,et al.  Performance evaluation of 2D and 3D deep learning approaches for automatic segmentation of multiple organs on CT images , 2018, Medical Imaging.

[28]  G. Fitzgerald,et al.  'I. , 2019, Australian journal of primary health.

[29]  Amir M. Mirzendehdel,et al.  A Pareto-Optimal Approach to Multimaterial Topology Optimization , 2015 .

[30]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[31]  Saigopal Nelaturi,et al.  Topology Optimization with Accessibility Constraint for Multi-Axis Machining , 2020, Comput. Aided Des..

[32]  O. Sigmund,et al.  Topology optimization considering material and geometric uncertainties using stochastic collocation methods , 2012 .

[33]  P. Alam.  ‘K’ , 2021, Composites Engineering.

[34]  Wei Chen,et al.  Level set based robust shape and topology optimization under random field uncertainties , 2010, DAC 2009.

[35]  H. Sebastian Seung,et al.  Superhuman Accuracy on the SNEMI3D Connectomics Challenge , 2017, ArXiv.

[36]  Krishnan Suresh,et al.  Support structure constrained topology optimization for additive manufacturing , 2016, Comput. Aided Des..

[37]  A. Gurson.  Continuum Theory of Ductile Rupture by Void Nucleation and Growth: Part I—Yield Criteria and Flow Rules for Porous Ductile Media , 1977 .

[38]  J. S. Zuback,et al.  Additive manufacturing of metallic components – Process, structure and properties , 2018 .

[39]  Saigopal Nelaturi,et al.  Fabricated shape estimation for additive manufacturing processes with uncertainty , 2020, Comput. Aided Des..

[40]  Amir M. Mirzendehdel,et al.  Strength-Based Topology Optimization for Anisotropic Parts , 2018 .

[41]  O. Sigmund,et al.  Minimum length scale in topology optimization by geometric constraints , 2015 .

[42]  Wei Sun,et al.  A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis , 2018, Journal of The Royal Society Interface.

[43]  T. Sørensen,et al.  A method of establishing group of equal amplitude in plant sociobiology based on similarity of species content and its application to analyses of the vegetation on Danish commons , 1948 .

[44]  Hao Chen,et al.  Volumetric ConvNets with Mixed Residual Connections for Automated Prostate Segmentation from 3D MR Images , 2017, AAAI.

[45]  Glaucio H. Paulino,et al.  Topology optimization with manufacturing constraints: A unified projection-based approach , 2016, Adv. Eng. Softw..

[46]  Hoon Huh,et al.  New ductile fracture criterion for prediction of fracture forming limit diagrams of sheet metals , 2012 .

[47]  Jack Beuth,et al.  A multi-scale convolutional neural network for autonomous anomaly detection and classification in a laser powder bed fusion additive manufacturing process , 2018, Additive Manufacturing.

[48]  T. Wierzbicki,et al.  A new model of metal plasticity and fracture with pressure and Lode dependence , 2008 .

[49]  A. Rubenchik,et al.  Laser powder-bed fusion additive manufacturing: Physics of complex melt flow and formation mechanisms of pores, spatter, and denudation zones , 2015, 1512.02593.

[50]  James K. Guest,et al.  Topology optimization considering overhang constraints: Eliminating sacrificial support material in additive manufacturing through design , 2016 .

[51]  Tomasz Wierzbicki,et al.  A Comparative Study on Various Ductile Crack Formation Criteria , 2004 .

[52]  V. Tvergaard.  On localization in ductile materials containing spherical voids , 1982, International Journal of Fracture.

[53]  M. Zhou,et al.  PROGRESS IN TOPOLOGY OPTIMIZATION WITH MANUFACTURING CONSTRAINTS , 2002 .

[54]  Yongsheng Ma,et al.  3D level-set topology optimization: a machining feature-based approach , 2015 .

[55]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[56]  Yunqing Zhang,et al.  Manufacturing- and machining-based topology optimization , 2006 .

[57]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

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

[59]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[60]  Matthijs Langelaar,et al.  An additive manufacturing filter for topology optimization of print-ready designs , 2016, Structural and Multidisciplinary Optimization.

[61]  D. Dye,et al.  Vacuum heat treatments of titanium porous structures , 2021 .

[62]  Shutian Liu,et al.  Topology optimization design of cast parts based on virtual temperature method , 2018, Comput. Aided Des..

[63]  P. Alam.  ‘L’ , 2021, Composites Engineering: An A–Z Guide.

[64]  Yongsheng Ma,et al.  A survey of manufacturing oriented topology optimization methods , 2016, Adv. Eng. Softw..

[65]  Le Song,et al.  Universal machine learning for topology optimization , 2021, Computer Methods in Applied Mechanics and Engineering.

[66]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[67]  Ole Sigmund,et al.  Manufacturing tolerant topology optimization , 2009 .