Weld Reinforcement Analysis Based on Long-Term Prediction of Molten Pool Image in Additive Manufacturing

Wire Arc Additive Manufacturing (WAAM) has developed rapidly in recent years and has been widely used in industry. Cold Metal Transfer (CMT), a kind of Gas Metal Arc Welding (GMAW), is widely used in the modeling of thin parts. In the monitoring of CMT process, it is necessary to monitor the weld reinforcement of the deposited layer. It can provide effective alerting for welding and help to improve welding quality. In this paper, the weld reinforcement and the position of molten pool image on the deposited layer are determined by the molten pool visual acquisition system. According to the data of the same direction additive manufacturing experiment, the future molten pool image is predicted by the improved prediction network (PredNet). Meanwhile through a regression network (SERes), the predicted results are regressed to the accurate weld reinforcement information of the deposited layer in advance. The experimental results show that the monitoring system designed in this paper can predict the change of molten pool shape 140ms in advance and the average precision of the weld reinforcement regression is better than 0.3mm. This paper provides the necessary basis for the shape online monitoring and controlling in WAAM process.

[1]  Ruisheng Huang,et al.  Infrared temperature measurement and interference analysis of magnesium alloys in hybrid laser-TIG welding process , 2007 .

[2]  Gabriel Kreiman,et al.  Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning , 2016, ICLR.

[3]  Ling-Yu Duan,et al.  Group-Sensitive Triplet Embedding for Vehicle Reidentification , 2018, IEEE Transactions on Multimedia.

[4]  Interference Analysis of Infrared Temperature Measurement in Hybrid Welding , 2011 .

[5]  Joerg Beersiek,et al.  A CMOS camera as a tool for process analysis not only for laser beam welding , 2001 .

[6]  Liang Chen,et al.  Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis , 2016 .

[7]  Gang Wang,et al.  Thermal analysis for single-pass multi-layer GMAW based additive manufacturing using infrared thermography , 2017 .

[8]  I. Tabernero,et al.  Wire and arc additive manufacturing: a comparison between CMT and TopTIG processes applied to stainless steel , 2018, Welding in the World.

[9]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[10]  Zengxi Pan,et al.  Wire-feed additive manufacturing of metal components: technologies, developments and future interests , 2015 .

[11]  Di Wu,et al.  Online Monitoring and Model-Free Adaptive Control of Weld Penetration in VPPAW Based on Extreme Learning Machine , 2019, IEEE Transactions on Industrial Informatics.

[12]  Zhou Wang,et al.  Multiscale structural similarity for image quality assessment , 2003, The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003.

[13]  Lin Wu,et al.  Bead geometry prediction for robotic GMAW-based rapid manufacturing through a neural network and a second-order regression analysis , 2012, Journal of Intelligent Manufacturing.

[14]  Philip S. Yu,et al.  PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs , 2017, NIPS.

[15]  I. Yadroitsava,et al.  Selective laser melting of Ti6Al4V alloy for biomedical applications: Temperature monitoring and microstructural evolution , 2014 .

[16]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[18]  Yi Zhang,et al.  Coaxial monitoring of the fibre laser lap welding of Zn-coated steel sheets using an auxiliary illuminant , 2013 .

[19]  Patrick M. Pilarski,et al.  Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learning , 2016 .

[20]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[22]  Xiang-Dong Gao,et al.  Prediction model of weld width during high-power disk laser welding of 304 austenitic stainless steel , 2014 .

[23]  Sandra Aigner,et al.  FUTUREGAN: ANTICIPATING THE FUTURE FRAMES OF VIDEO SEQUENCES USING SPATIO-TEMPORAL 3D CONVOLUTIONS IN PROGRESSIVELY GROWING GANS , 2018, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

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

[25]  Yanxi Zhang,et al.  Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding , 2014 .

[26]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Tomonori Yamada,et al.  In-situ X-ray observation of molten pool depth during laser micro welding , 2012 .

[28]  Jun Xiong,et al.  Vision-sensing and bead width control of a single-bead multi-layer part: material and energy savings in GMAW-based rapid manufacturing , 2013 .

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