Abstract
Wire-arc additive manufacturing (WAAM) technology has been widely recognized as a promising alternative for fabricating large-scale components, due to its advantages of high deposition rate and high material utilization rate. However, some anomalies may occur during the deposition process, such as humping, spattering, robot suspend, pores, cracking and so on. This study proposed to apply deep learning in the visual monitoring to diagnose different anomalies during WAAM process. The melt pool images of different anomalies were collected for training and validation by a visual monitoring system. The classification performance of several representative CNN (convolutional neural network) architectures, including ResNet, EfficientNet, VGG-16 and GoogLeNet, were investigated and compared. The classification accuracy of 97.62%, 97.45%, 97.15% and 97.25% was achieved by each model. The results proved that the CNN models are effective in classifying different types of melt pool images of WAAM. Our study is applicable beyond WAAM and should benefit other additive manufacturing or arc welding techniques.
Similar content being viewed by others
References
Zeng ZB, Cong J, Oliveira et al (2020) Wire and arc additive manufacturing of a Ni-rich NiTi shape memory alloy: microstructure and mechanical properties 32:101051
Rodrigues TA, Bairrão N, Farias FWC et al (2022) Steel-copper functionally graded material produced by twin-wire and arc additive manufacturing (T-WAAM) 213:110270
Ke W, Oliveira J, Cong B et al (2022) Multi-layer deposition mechanism in ultra high-frequency pulsed wire arc additive manufacturing (WAAM) of NiTi shape memory alloys 50:102513
Suryakumar S, Karunakaran K, Chandrasekhar U, Somashekara M (2013) A study of the mechanical properties of objects built through weld-deposition. Proc Inst Mech Eng B J Eng Manuf 227(8):1138–1147. https://doi.org/10.1177/0954405413482122
Lopes J, Machado CM, Duarte VR et al (2020) Effect of milling parameters on HSLA steel parts produced by wire and arc additive manufacturing (WAAM) 59:739–749
Rodrigues TA, Duarte V, Miranda R et al (2019) Current status and perspectives on wire and arc additive manufacturing (WAAM) 12(7):1121
Li Y, Su C, Zhu J (2021) Comprehensive review of wire arc additive manufacturing: Hardware system, physical process, monitoring, property characterization, application and future prospects
Ya W, Hamilton K (2017) On-demand spare parts for the marine industry with directed energy deposition: propeller use case. International Conference on Additive Manufacturing in Products and Applications. Springer, pp 70–81
Williams SW, Martina F, Addison AC et al (2016) Wire+ arc additive manufacturing. Mater Sci Technol 32(7):641–647
Greer C, Nycz A, Noakes M et al (2019) Introduction to the design rules for metal big area additive manufacturing. Addit Manuf 27:159–166. https://doi.org/10.1016/j.addma.2019.02.016
Xia C, Pan Z, Zhang S et al (2020) Model predictive control of layer width in wire arc additive manufacturing. J Manuf Process 58:179–186. https://doi.org/10.1016/j.jmapro.2020.07.060
Chabot A, Rauch M, Hascoët J-Y (2019) Towards a multi-sensor monitoring methodology for AM metallic processes. Welding in the World 1–11
Zhan Q, Liang Y, Ding J, Williams S (2017) A wire deflection detection method based on image processing in wire+ arc additive manufacturing. Int J Adv Manuf Technol 89(1–4):755–763
Zhao Z, Guo Y, Bai L et al (2019) Quality monitoring in wire-arc additive manufacturing based on cooperative awareness of spectrum and vision. Optik 181:351–360
Aminzadeh M, Kurfess TR (2019) Online quality inspection using Bayesian classification in powder-bed additive manufacturing from high-resolution visual camera images. J Intell Manuf 30(6):2505–2523. https://doi.org/10.1007/s10845-018-1412-0
Scime L, Beuth J (2018) A multi-scale convolutional neural network for autonomous anomaly detection and classification in a laser powder bed fusion additive manufacturing process. Addit Manuf 24:273–286. https://doi.org/10.1016/j.addma.2018.09.034
Caggiano A, Zhang J, Alfieri V et al (2019) Machine learning-based image processing for on-line defect recognition in additive manufacturing. CIRP Ann 68(1):451–454. https://doi.org/10.1016/j.cirp.2019.03.021
Kwon O, Kim HG, Ham MJ et al (2020) A deep neural network for classification of melt-pool images in metal additive manufacturing. J Intell Manuf 31(2):375–386. https://doi.org/10.1007/s10845-018-1451-6
Liu T, Bao J, Wang J, Zhang Y (2018) A hybrid CNN–LSTM algorithm for online defect recognition of CO2 welding. Sensors 18(12):4369. https://doi.org/10.3390/s18124369
Xia C, Pan Z, Fei Z et al (2020) Vision based defects detection for Keyhole TIG welding using deep learning with visual explanation. J Manuf Process 56:845–855
Feng Y, Chen Z, Wang D et al (2019) DeepWelding: a deep learning enhanced approach to GTAW using multisource sensing images. IEEE Trans Industr Inf 16(1):465–474
Bradstreet B (1968) Effect of surface tension and metal flow on weld bead formation. Weld J 47(7):314s–322s
Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621
Deng J, Dong W, Socher R et al (2009) Imagenet: a large-scale hierarchicalimage database in 2009 IEEE conference on computer vision and pattern recognition 248–255
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks in Adv neural inf proces syst 91–99
Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117. https://doi.org/10.1016/j.neunet.2014.09.003
Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. in Proceedings of the IEEE conference on computer vision and pattern recognition 1–9
Liu Z, Fang Y, Cui S et al (2016) Stable keyhole welding process with K-TIG. J Mater Process Technol 238:65–72
Yuan L, Pan Z, Ding D et al (2020) Investigation of humping phenomenon for the multi-directional robotic wire and arc additive manufacturing. Robotics and Computer-Integrated Manufacturing 63:101916
Carneiro T, Da Nóbrega RVM, Nepomuceno T et al (2018) Performance analysis of google colaboratory as a tool for accelerating deep learning applications. IEEE Access 6:61677–61685
Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37(1):35–46. https://doi.org/10.1046/j.1365-2249.2000.01137.x
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition 770–778
Tan M, Le QV (2019) Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946
Funding
China Scholarship Council (NO. 201704910782) and National Natural Science Foundation of China (No. 51775313) provided financial support.
Author information
Authors and Affiliations
Contributions
All the authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Chunyang Xia, Zengxi Pan and Yuxing Li. The first draft of the manuscript was written by Chunyang Xia, and all the authors commented on previous versions of the manuscript. Ji Chen helped improve the language and figures when revising the manuscript. All the authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xia, C., Pan, Z., Li, Y. et al. Vision-based melt pool monitoring for wire-arc additive manufacturing using deep learning method. Int J Adv Manuf Technol 120, 551–562 (2022). https://doi.org/10.1007/s00170-022-08811-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-08811-2