Applying Neural-Network-Based Machine Learning to Additive Manufacturing: Current Applications, Challenges, and Future Perspectives

Abstract Additive manufacturing (AM), also known as three-dimensional printing, is gaining increasing attention from academia and industry due to the unique advantages it has in comparison with traditional subtractive manufacturing. However, AM processing parameters are difficult to tune, since they can exert a huge impact on the printed microstructure and on the performance of the subsequent products. It is a difficult task to build a process–structure–property–performance (PSPP) relationship for AM using traditional numerical and analytical models. Today, the machine learning (ML) method has been demonstrated to be a valid way to perform complex pattern recognition and regression analysis without an explicit need to construct and solve the underlying physical models. Among ML algorithms, the neural network (NN) is the most widely used model due to the large dataset that is currently available, strong computational power, and sophisticated algorithm architecture. This paper overviews the progress of applying the NN algorithm to several aspects of the AM whole chain, including model design, in situ monitoring, and quality evaluation. Current challenges in applying NNs to AM and potential solutions for these problems are then outlined. Finally, future trends are proposed in order to provide an overall discussion of this interdisciplinary area.

[1]  L. Froyen,et al.  Binding Mechanisms in Selective Laser Sintering and Selective Laser Melting , 2004 .

[2]  Han Chen,et al.  Learning Algorithm Based Modeling and Process Parameters Recommendation System for Binder Jetting Additive Manufacturing Process , 2015 .

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  Ranadip Acharya,et al.  Prediction of microstructure in laser powder bed fusion process , 2017 .

[5]  Tsz-Ho Kwok,et al.  In-situ droplet inspection and closed-loop control system using machine learning for liquid metal jet printing , 2018 .

[6]  Aurélien Géron,et al.  Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems , 2017 .

[7]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[8]  Tao Zhang,et al.  A Survey of Model Compression and Acceleration for Deep Neural Networks , 2017, ArXiv.

[9]  Imre Horváth,et al.  Enhanced beads overlapping model for wire and arc additive manufacturing of multi-layer multi-bead metallic parts , 2018 .

[10]  L. Murr,et al.  Metal Fabrication by Additive Manufacturing Using Laser and Electron Beam Melting Technologies , 2012 .

[11]  Anoop Kumar Sood,et al.  Experimental investigation and empirical modelling of FDM process for compressive strength improvement , 2012 .

[12]  Mario Fritz,et al.  Advanced Steel Microstructural Classification by Deep Learning Methods , 2017, Scientific Reports.

[13]  Christopher McComb,et al.  Predicting Part Mass, Required Support Material, and Build Time via Autoencoded Voxel Patterns , 2018 .

[14]  Brian Derby,et al.  Additive Manufacture of Ceramics Components by Inkjet Printing , 2015 .

[15]  Christopher B. Williams,et al.  An exploration of binder jetting of copper , 2015 .

[16]  Siba Sankar Mahapatra,et al.  Prediction of dimensional accuracy in fused deposition modelling: a fuzzy logic approach , 2011 .

[17]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[18]  S. A. Shevchik,et al.  In Situ Quality Monitoring in AM Using Acoustic Emission: A Reinforcement Learning Approach , 2018, Journal of Materials Engineering and Performance.

[19]  Paul Witherell,et al.  A Collaborative Data Management System for Additive Manufacturing , 2017 .

[20]  R. Banerjee,et al.  Additive manufacturing of metals: a brief review of the characteristic microstructures and properties of steels, Ti-6Al-4V and high-entropy alloys , 2017, Science and technology of advanced materials.

[21]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[22]  Richard Leach,et al.  Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing , 2016 .

[23]  Steven Y. Liang,et al.  Analytical modelling of residual stress in additive manufacturing , 2017 .

[24]  Shuxiang Xu,et al.  A novel approach for determining the optimal number of hidden layer neurons for FNN’s and its application in data mining , 2008 .

[25]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[26]  Alessandra Caggiano,et al.  Laser Direct Metal Deposition of 2024 Al Alloy: Trace Geometry Prediction via Machine Learning , 2018, Materials.

[27]  Ming-Chuan Leu,et al.  A neural network approach to the modelling and analysis of stereolithography processes , 2001 .

[28]  Kang Tai,et al.  State-of-the-art in empirical modelling of rapid prototyping processes , 2014 .

[29]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[30]  E. García-Plaza,et al.  Additive manufacturing of PLA structures using fused deposition modelling: Effect of process parameters on mechanical properties and their optimal selection , 2017 .

[31]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[32]  Xinhua Li,et al.  ANN model for the prediction of density in Selective Laser Sintering , 2009, Int. J. Manuf. Res..

[33]  Geok Soon Hong,et al.  Extraction and evaluation of melt pool, plume and spatter information for powder-bed fusion AM process monitoring , 2018, Materials & Design.

[34]  R. K. Ohdar,et al.  An investigation on sliding wear of FDM built parts , 2012 .

[35]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[36]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[37]  L. Froyen,et al.  Lasers and materials in selective laser sintering , 2002 .

[38]  Xiaoyong Tian,et al.  Development Trends in Additive Manufacturing and 3D Printing , 2015 .

[39]  Xinyi Gong,et al.  Process-Structure Linkages Using a Data Science Approach: Application to Simulated Additive Manufacturing Data , 2017, Integrating Materials and Manufacturing Innovation.

[40]  Charles-André Gandin,et al.  Three-dimensional finite element thermomechanical modeling of additive manufacturing by selective laser melting for ceramic materials , 2017 .

[41]  姜宁,et al.  Prediction of Sintering Strength for Selective Laser Sintering of Polystyrene Using Artificial Neural Network , 2015 .

[42]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[43]  A. K. Sood,et al.  Parametric appraisal of mechanical property of fused deposition modelling processed parts , 2010 .

[44]  Shahir Mohd Yusuf,et al.  Influence of energy density on metallurgy and properties in metal additive manufacturing , 2017 .

[45]  Nagiza F. Samatova,et al.  Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data , 2016, IEEE Transactions on Knowledge and Data Engineering.

[46]  Sam Anand,et al.  Artificial Neural Network Based Geometric Compensation for Thermal Deformation in Additive Manufacturing Processes , 2016 .

[47]  Apostol Natsev,et al.  YouTube-8M: A Large-Scale Video Classification Benchmark , 2016, ArXiv.

[48]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[49]  Mujian Xia,et al.  A Multiscale Understanding of the Thermodynamic and Kinetic Mechanisms of Laser Additive Manufacturing , 2017 .

[50]  R. K. Ohdar,et al.  Parametric appraisal of fused deposition modelling process using the grey Taguchi method , 2010 .

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

[52]  Yong-zhi Zhang,et al.  Modeling and Applying of RBF Neural Network Based on Fuzzy Clustering and Pseudo-Inverse Method , 2009, 2009 International Conference on Information Engineering and Computer Science.

[53]  Qingqing Ding,et al.  Dislocation network in additive manufactured steel breaks strength–ductility trade-off , 2017 .

[54]  Ian Gibson,et al.  Additive manufacturing technologies : 3D printing, rapid prototyping, and direct digital manufacturing , 2015 .

[55]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[56]  D.R. Reddy,et al.  Speech recognition by machine: A review , 1976, Proceedings of the IEEE.

[57]  Kilian Wasmer,et al.  In Situ Quality Monitoring in AM Using Acoustic Emission: A Machine Learning Approach , 2017 .

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

[59]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[60]  Ingmar Posner,et al.  Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks , 2016, AAAI.

[61]  S. Shevchik,et al.  Acoustic emission for in situ quality monitoring in additive manufacturing using spectral convolutional neural networks , 2017 .

[62]  Yang Wang,et al.  Density Prediction of Selective Laser Sintering Parts Based on Artificial Neural Network , 2004, ISNN.

[63]  C. Kamath,et al.  Laser powder bed fusion additive manufacturing of metals; physics, computational, and materials challenges , 2015 .

[64]  Wentai Zhang,et al.  MACHINE LEARNING ENABLED POWDER SPREADING PROCESS MAP FOR METAL ADDITIVE MANUFACTURING ( AM ) , 2017 .

[65]  Aditya Singh Rathore,et al.  Image Dataset for Visual Objects Classification in 3D Printing , 2018, ArXiv.

[66]  George-Christopher Vosniakos,et al.  A method for optimizing process parameters in layer-based rapid prototyping , 2007 .

[67]  Meng Zhang,et al.  Neural Network Methods for Natural Language Processing , 2017, Computational Linguistics.

[68]  Joaquim Ciurana,et al.  Neural-network-based model for build-time estimation in selective laser sintering , 2009 .

[69]  Wang Lingling,et al.  Optimizing process parameters for selective laser sintering based on neural network and genetic algorithm , 2009 .

[70]  A. Bachelor.  GLOSSARY OF TERMS GLOSSARY OF TERMS , 2010 .

[71]  Surya R. Kalidindi,et al.  Materials informatics , 2018, Journal of Intelligent Manufacturing.

[72]  Bernd Markert,et al.  Efficient numerical modeling of 3D-printed lattice-cell structures using neural networks , 2018 .