In-Process monitoring of porosity during laser additive manufacturing process

Abstract This paper describes a deep-learning-based method for porosity monitoring in laser additive manufacturing process. A high-speed digital camera was mounted coaxially to the process laser beam for in-process sensing of melt-pool data, and convolutional neural network models were designed to learn melt-pool features to predict the porosity attributes in deposited specimens during laser additive manufacturing. With the image processing tools developed in this paper, the extraction of porosity information from raw quality inspection data, such as cross-section images and tomography data sets, can be automated. The CNN models with a compact architecture, part of whose hyperparameters were selected through cross-validation analysis, achieved a classification accuracy of 91.2% for porosity occurrence detection in the direct laser deposition of sponge Titanium powders and presented predictive capacity for micro pores below 100 μm. For local volume porosity prediction, the model also achieved a root mean square error of 1.32% and exhibited high fidelity for both high porosity and low porosity specimens.

[1]  N. Shamsaei,et al.  An overview of Direct Laser Deposition for additive manufacturing; Part II: Mechanical behavior, process parameter optimization and control , 2015 .

[2]  J. Ziegert,et al.  In situ surface topography of laser powder bed fusion using fringe projection , 2016 .

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

[4]  M. Spies,et al.  Online Monitoring of Additive Manufacturing Processes Using Ultrasound , 2016 .

[5]  B. Colosimo,et al.  Characterization of in-situ measurements based on layerwise imaging in laser powder bed fusion , 2018, Additive Manufacturing.

[6]  Y. Shin,et al.  Additive manufacturing of Ti6Al4V alloy: A review , 2019, Materials & Design.

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

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

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

[10]  J. Mazumder,et al.  Visualization of a laser melt pool. , 1990, Applied optics.

[11]  Mohammad Marufuzzaman,et al.  In-situ monitoring of melt pool images for porosity prediction in directed energy deposition processes , 2019, IISE Trans..

[12]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[13]  A. Nassar,et al.  Physics-Based Multivariable Modeling and Feedback Linearization Control of Melt-Pool Geometry and Temperature in Directed Energy Deposition , 2017 .

[14]  Y. Shin,et al.  Vision-based weld pool boundary extraction and width measurement during keyhole fiber laser welding , 2015 .

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Linkan Bian,et al.  Dual process monitoring of metal-based additive manufacturing using tensor decomposition of thermal image streams , 2018, Additive Manufacturing.

[17]  Lijun Song,et al.  Control of melt pool temperature and deposition height during direct metal deposition process , 2012 .

[18]  E. Garboczi,et al.  Porosity Measurements and Analysis for Metal Additive Manufacturing Process Control , 2014, Journal of research of the National Institute of Standards and Technology.

[19]  Manyalibo J. Matthews,et al.  In situ measurements of layer roughness during laser powder bed fusion additive manufacturing using low coherence scanning interferometry , 2018, Materials & Design.

[20]  Prahalada Rao,et al.  Sensor-Based Build Condition Monitoring in Laser Powder Bed Fusion Additive Manufacturing Process Using a Spectral Graph Theoretic Approach , 2018, Journal of Manufacturing Science and Engineering.

[21]  Perry P. Gao,et al.  Synchronized Monitoring of Droplet Transition and Keyhole Bottom in High Power Laser-MAG Hybrid Welding Process , 2019, IEEE Sensors Journal.

[22]  G. Tapia,et al.  A Review on Process Monitoring and Control in Metal-Based Additive Manufacturing , 2014 .

[23]  Jun Xiong,et al.  Online measurement of bead geometry in GMAW-based additive manufacturing using passive vision , 2013 .

[24]  Ryan B. Wicker,et al.  Closed-loop automatic feedback control in electron beam melting , 2015 .

[25]  Wei Xu,et al.  Topological design and additive manufacturing of porous metals for bone scaffolds and orthopaedic implants: A review. , 2016, Biomaterials.

[26]  M. F. Zaeh,et al.  Thermography for Monitoring the Selective Laser Melting Process , 2012 .

[27]  Tom Craeghs,et al.  Detection of Process Failures in Layerwise Laser Melting with Optical Process Monitoring , 2012 .

[28]  Frank W. Liou,et al.  Vision-based defect detection in laser metal deposition process , 2014 .

[29]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[30]  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.

[31]  Radovan Kovacevic,et al.  Sensing, modeling and control for laser-based additive manufacturing , 2003 .

[32]  3D ANALYSIS IN LASER BEAM MELTING BASED ON REAL-TIME PROCESS MONITORING , 2016 .

[33]  Thomas Hess,et al.  Process monitoring of additive manufacturing by using optical tomography , 2015 .

[34]  Jean-Pierre Kruth,et al.  In situ quality control of the selective laser melting process using a high-speed, real-time melt pool monitoring system , 2014 .

[35]  B. Colosimo,et al.  Process defects and in situ monitoring methods in metal powder bed fusion: a review , 2017 .