Research on Automated Defect Classification Based on Visual Sensing and Convolutional Neural Network-Support Vector Machine for GTA-Assisted Droplet Deposition Manufacturing Process

This paper proposes a novel metal additive manufacturing process, which is a composition of gas tungsten arc (GTA) and droplet deposition manufacturing (DDM). Due to complex physical metallurgical processes involved, such as droplet impact, spreading, surface pre-melting, etc., defects, including lack of fusion, overflow and discontinuity of deposited layers always occur. To assure the quality of GTA-assisted DDM-ed parts, online monitoring based on visual sensing has been implemented. The current study also focuses on automated defect classification to avoid low efficiency and bias of manual recognition by the way of convolutional neural network-support vector machine (CNN-SVM). The best accuracy of 98.9%, with an execution time of about 12 milliseconds to handle an image, proved our model can be enough to use in real-time feedback control of the process.

[1]  Lianfa Bai,et al.  Quality monitoring in wire-arc additive manufacturing based on cooperative awareness of spectrum and vision , 2019, Optik.

[2]  Ohyung Kwon,et al.  A deep neural network for classification of melt-pool images in metal additive manufacturing , 2018, J. Intell. Manuf..

[3]  Lianfa Bai,et al.  Weld Reinforcement Analysis Based on Long-Term Prediction of Molten Pool Image in Additive Manufacturing , 2020, IEEE Access.

[4]  M. Papaelias,et al.  Automated defect classification of Aluminium 5083 TIG welding using HDR camera and neural networks , 2019, Journal of Manufacturing Processes.

[5]  Z. Pan,et al.  Model predictive control of layer width in wire arc additive manufacturing , 2020 .

[6]  Hichem Snoussi,et al.  A fast and robust convolutional neural network-based defect detection model in product quality control , 2017, The International Journal of Advanced Manufacturing Technology.

[7]  Matthieu Rauch,et al.  Towards defect monitoring for metallic additive manufacturing components using phased array ultrasonic testing , 2020, J. Intell. Manuf..

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Prahalada K. Rao,et al.  Heterogeneous sensor-based condition monitoring in directed energy deposition , 2019 .

[10]  Jing Han,et al.  Prediction of Weld Reinforcement Based on Vision Sensing in GMA Additive Manufacturing Process , 2020 .

[11]  Dong Du,et al.  Online Measurement of Deposit Surface in Electron Beam Freeform Fabrication , 2019, Sensors.

[12]  Valdemar R. Duarte,et al.  Current Status and Perspectives on Wire and Arc Additive Manufacturing (WAAM) , 2019, Materials.

[13]  A. Addison,et al.  Wire + Arc Additive Manufacturing , 2016 .

[14]  Yao Xiao,et al.  Crack Detection during Laser Metal Deposition by Infrared Monochrome Pyrometer , 2020, Materials.

[15]  Wenjin Tao,et al.  American Sign Language alphabet recognition using Convolutional Neural Networks with multiview augmentation and inference fusion , 2018, Eng. Appl. Artif. Intell..

[16]  D. Pimenov,et al.  Investigations on quality characteristics in gas tungsten arc welding process using artificial neural network integrated with genetic algorithm , 2021, The International Journal of Advanced Manufacturing Technology.

[17]  Guangrui Wen,et al.  Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding , 2019, Journal of Manufacturing Processes.

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

[19]  Jesus Mirapeix,et al.  Feasibility study of Hierarchical Temporal Memories applied to welding diagnostics , 2013 .

[20]  Zhu,et al.  Deep Learning-Based Classification of Weld Surface Defects , 2019, Applied Sciences.

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

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

[23]  Prahalada K. Rao,et al.  In Situ Monitoring of Thin-Wall Build Quality in Laser Powder Bed Fusion Using Deep Learning , 2019, Smart and Sustainable Manufacturing Systems.

[24]  Yupeng Zhang,et al.  Prediction of weld formation in 5083 aluminum alloy by twin-wire CMT welding based on deep learning , 2019, Welding in the World.

[25]  L. Quintino,et al.  Non-destructive testing for wire + arc additive manufacturing of aluminium parts , 2019, Additive Manufacturing.

[26]  Frank W. Liou,et al.  Metal Additive Manufacturing Parts Inspection Using Convolutional Neural Network , 2020, Applied Sciences.

[27]  Prakhar Jaiswal,et al.  Convolutional neural network-based inspection of metal additive manufacturing parts , 2019, Rapid prototyping journal.

[28]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[29]  Modeling for detecting weld defects based on magneto-optical imaging. , 2018, Applied optics.

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

[31]  Thomas R. Kurfess,et al.  Online quality inspection using Bayesian classification in powder-bed additive manufacturing from high-resolution visual camera images , 2018, Journal of Intelligent Manufacturing.

[32]  C. Prakash,et al.  Analysis of Sensitization in Austenitic Stainless Steel-Welded Joint , 2020 .