Quantification and compensation of thermal distortion in additive manufacturing: A computational statistics approach

Abstract In this work, we have developed a computational probabilistic method to quantify the permanent (non-zero strain) continuum/material deformation. Different from physical-based modeling, the method developed here is based on a data-driven statistics approach, which solves the problem without needing the information of physical deformation process. The proposed method relies only on the scanned material data from the thermal distorted configuration as well as the shape of the initial design configuration. We coined this artificial intelligence based algorithm as the material deformation finding (MDF) algorithm. In this work, the MDF algorithm was first validated by a 2D synthetic example. We then demonstrated that the proposed MDF method can accurately find the permanent thermal distortion of a complex 3D printed structural component, and hence to identify the thermal compensation design configuration. The results obtained in this work indicate that one can use this data-driven statistics approach to significantly mitigate thermal distortion of 3D printed products in additive manufacturing.

[1]  Wing Kam Liu,et al.  Data-driven multi-scale multi-physics models to derive process–structure–property relationships for additive manufacturing , 2018 .

[2]  Matthew A. Davies,et al.  Recent advances in modelling of metal machining processes , 2013 .

[3]  Wing Kam Liu,et al.  Meshfree and particle methods and their applications , 2002 .

[4]  C. M. Cheah,et al.  Influence of process parameters on stereolithography part shrinkage , 1996 .

[5]  Qiang Huang,et al.  An Analytical Foundation for Optimal Compensation of Three-Dimensional Shape Deformation in Additive Manufacturing , 2016 .

[6]  Andriy Myronenko,et al.  Point Set Registration: Coherent Point Drift , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  J. Beaman,et al.  Special Issue: Additive Manufacturing (AM) and 3D Printing , 2014 .

[8]  Miguel A. Bessa,et al.  Self-consistent clustering analysis: An efficient multi-scale scheme for inelastic heterogeneous materials , 2016 .

[9]  Huijun Gao,et al.  Recent developments and trends in point set registration methods , 2017, J. Vis. Commun. Image Represent..

[10]  Per-Olof Persson,et al.  A Simple Mesh Generator in MATLAB , 2004, SIAM Rev..

[11]  Linkan Bian,et al.  Deep Learning for Distortion Prediction in Laser-Based Additive Manufacturing using Big Data , 2019, Manufacturing Letters.

[12]  Miguel Á. Carreira-Perpiñán,et al.  Non-rigid point set registration: Coherent Point Drift , 2006, NIPS.

[13]  Pan Michaleris,et al.  Experimental validation of finite element modeling for laser powder bed fusion deformation , 2016 .

[14]  M. Degroot,et al.  Probability and Statistics , 2021, Examining an Operational Approach to Teaching Probability.

[15]  P. Michaleris,et al.  In situ monitoring and characterization of distortion during laser cladding of Inconel® 625 , 2015 .

[16]  Qiang Huang,et al.  Automated Geometric Shape Deviation Modeling for Additive Manufacturing Systems via Bayesian Neural Networks , 2020, IEEE Transactions on Automation Science and Engineering.

[17]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[18]  Tarasankar DebRoy,et al.  An improved prediction of residual stresses and distortion in additive manufacturing , 2017 .

[19]  G. Casella,et al.  Statistical Inference , 2003, Encyclopedia of Social Network Analysis and Mining.

[20]  Sahibsingh A. Dudani.  The Distance-Weighted k-Nearest-Neighbor Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[21]  Kaufui Wong,et al.  A Review of Additive Manufacturing , 2012 .

[22]  F. Melchels,et al.  A review on stereolithography and its applications in biomedical engineering. , 2010, Biomaterials.

[23]  Bernhard Mueller,et al.  Additive Manufacturing Technologies – Rapid Prototyping to Direct Digital Manufacturing , 2012 .

[24]  Guirong Liu,et al.  Smoothed Particle Hydrodynamics: A Meshfree Particle Method , 2003 .

[25]  Bernhard Schölkopf,et al.  A Generalized Representer Theorem , 2001, COLT/EuroCOLT.

[26]  K. Salonitis,et al.  Simulation of metallic powder bed additive manufacturing processes with the finite element method: A critical review , 2017 .

[27]  Douglas A. Reynolds.  Gaussian Mixture Models , 2009, Encyclopedia of Biometrics.

[28]  I. J. Myung,et al.  Tutorial on maximum likelihood estimation , 2003 .

[29]  Qiang Huang,et al.  Machine learning in tolerancing for additive manufacturing , 2018 .

[30]  Tirthankar Dasgupta,et al.  Optimal offline compensation of shape shrinkage for three-dimensional printing processes , 2015 .

[31]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[32]  Wei Chen,et al.  A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality , 2017 .

[33]  Michael Rethmeier,et al.  In-situ distortions in LMD additive manufacturing walls can be measured with digital image correlation and predicted using numerical simulations , 2018 .

[34]  C. Emmelmann,et al.  Additive Manufacturing of Metals , 2016 .

[35]  Hang Z. Yu,et al.  Integration of physically-based and data-driven approaches for thermal field prediction in additive manufacturing , 2018 .

[36]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .