Predictive visualization of fiber laser cutting topography via deep learning with image inpainting
Source abstract
Abstract
Laser cutting is a fast, precise, and noncontact processing technique widely applied throughout industry. However, parameter specific defects can be formed while cutting, negatively impacting the cut quality. While light-matter interactions are highly nonlinear and are, therefore, challenging to model analytically, deep learning offers the capability of modeling these interactions directly from data. Here, we show that deep learning can be used to scale up visual predictions for parameter specific defects produced in cutting as well as for predicting defects for parameters not measured experimentally. Furthermore, visual predictions can be used to model the relationship between laser cutting defects and laser cutting parameters.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Optical Coherence Tomography Applications · Advanced Fluorescence Microscopy Techniques · Laser Material Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Optoelectronics Research Centre, University of Southampton 1 , University Road, Southampton SO17 1BJ, United Kingdom
TRUMPF Laser UK 2 , 6 Wellington Park, Toolbar Way, Hedge End, Southampton SO30 2QU, United Kingdom
Funding
Engineering and Physical Sciences Research Council
References (81)
Show source-provided references
1. Laser processing in industrial solar module manufacturing10.2961/jlmn.2010.03.0001 ↗
2. Deep learning for distortion prediction in laser-based additive manufacturing using Big data10.1016/j.mfglet.2019.02.001 ↗
3. Laser processing of materials10.1007/BF02706446 ↗
4. 2018
5. Laser-sculptured ultrathin transition metal carbide layers for energy storage and energy harvesting applications10.1038/s41467-018-07882-8 ↗
6. Pulsed 2 μm fiber lasers for direct and pumping applications in defence and security
7. Investigation of the piercing process in laser cutting of stainless steel10.2351/1.4983260 ↗
8. Aerodynamic interactions during laser cutting
9. Fiber laser—New challenges for the materials processing10.1002/latj.200790168 ↗
10. A spectroscopic method based on support vector machine and artificial neural network for fiber laser welding defects detection and classification10.1016/j.ndteint.2019.102176 ↗
11. Laser cladding of turbine blades10.1016/S0257-8972(99)00603-9 ↗
12. Comparative study of mechanical technologies over laser technology for drilling carbon fiber reinforced polymer materials
13. High power ytterbium-doped fiber lasers—Fundamentals and applications10.1142/S0217979214420090 ↗
14. A comparative study on white layer properties by laser cutting vs. electrical discharge machining of nitinol shape memory alloy10.1016/j.procir.2016.02.280 ↗
15. 1993
16. Characterization of the melt flow direction and cut front geometry in oxygen cutting with a solid state laser10.2351/1.4983262 ↗
17. Mater. Today Proc. · 2021 · 44 · 208010.1016/j.matpr.2020.12.179 ↗
18. Effect of cutting conditions on surface roughness of machined parts in CO2 laser cutting of pure titanium10.1016/j.matpr.2020.12.179 ↗
19. Generation of striations during laser cutting of mild steel10.15764/APHY.2014.02010 ↗
20. Analysis of roughness and heat affected zone of steel plates obtained by laser cutting
21. Dynamic phenomena in laser cutting and cut quality10.1007/BF00697221 ↗
22. Striation-free fibre laser cutting of mild steel sheets10.1007/s00339-007-4247-7 ↗
23. Fibre laser cutting stainless steel: Fluid dynamics and cut front morphology10.1016/j.optlastec.2016.08.002 ↗
24. 1997
25. 2016
26. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
27. K. Simonyan , and A.Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv:1409.1556v6 (2015).
28. K. He , X.Zhang, S.Ren, and J.Sun, “Deep residual learning for image recognition,” arXiv:1512.03385v1 (2015).10.1109/CVPR.2016.90 ↗
29. J. Bao , D.Chen, F.Wen, H.Li, and G.Hua, “CVAE-GAN: Fine-grained image generation through asymmetric training,” arXiv:1703.10155v1 (2017).10.1109/ICCV.2017.299 ↗
30. 1997 · 255
31. C. Szegedy , W.Liu, Y.Jia, P.Sermanet, S.Reed, D.Anguelov, D.Erhan, V.Vanhoucke, and A.Rabinovich, “Going deeper with convolutions”, arXiv:1409.4842v1 (2015).10.1109/CVPR.2015.7298594 ↗
32. 2012
33. M. Zeiler , and R.Fergus, “Visualizing and understanding convolutional networks,” arXiv:1311.2901v3 (2013).
34. I. Durugkar , L.Gemp, and S.Mahadevan, “Generative multi-adversarial networks,” arXiv:1611.01673 (2017).
35. I. Serban , R.Lowe, L.Charlin, and J.Pineau, “Generative deep neural networks for dialogue: A short review,” arXiv:1611.06216 (2016).
36. I. Goodfellow , M.Mirza, B.Xu, D.Wade-Farley, and A.Courville, “Generative adversarial nets,” arXiv:1406.2661 (2014).
37. M. Lucic , K.Kurach, M.Michalski, S.Gelly, and O.Bousquet, “Are GANs created equal? A large-scale study,” arXiv:1711.10337 (2018).
38. M. Mirza and S.Osindero, “Conditional generative adversarial nets,” arXiv:1411.1784v1 (2014).
39. G. Liu , F.Reda, K.Shih, T.Wang, A.Tao, and B.Catanzaro, “Image inpainting for irregular holes using partial convolutions,” arXiv:1804.07723.pdf (2018).10.1007/978-3-030-01252-6_6 ↗
40. Image denoising and inpainting with deep neural networks
41. 2017
42. Towards robust dynamic beam shaping for laser cutting applications10.1016/j.procir.2022.08.116 ↗
43. 2019 · 389
44. Improving the laser cutting process design by machine learning techniques10.1007/s11740-017-0718-7 ↗
45. 2020
46. Real-time continuous estimation of dross attachment in the laser cutting process based on process emission images10.2351/7.0000145 ↗
47. Real-time prediction of quality characteristics in laser beam welding using optical coherence tomography and machine learning10.2351/7.0000077 ↗
48. Laser processing quality monitoring by combining acoustic emission and machine learning: A high-speed X-ray imaging approach10.1016/j.procir.2018.08.054 ↗
49. Machine learning as a comparative tool to determine the relevance of signal features in laser welding10.1016/j.procir.2018.08.073 ↗
50. Machine learning based technique towards smart laser fabrication of CG10.1016/j.mee.2020.111314 ↗
51. A hybrid machine learning approach for additive manufacturing design feature recommendation10.1108/RPJ-03-2016-0041 ↗
52. Machine learning for 3D simulated visualization of laser machining10.1364/OE.26.021574 ↗
53. Programmable focal spot shaping of amplified femtosecond laser pulse10.1364/OL.30.001479 ↗
54. Deep learning for the monitoring and process control of femtosecond laser machining
55. Modelling laser machining of nickel with spatially shaped three pulse sequences using deep learning10.1364/OE.381421 ↗
56. Underwater laser micro-milling of fine-grained aluminium and the process modelling by machine learning10.1088/1361-6439/ab7322 ↗
57. Image-based monitoring of femtosecond laser machining via a neural network
58. Multi-sensor system for real-time monitoring of laser micro-structuring
59. Predictive capabilities for laser machining via a neural network10.1364/OE.26.017245 ↗
60. Modelling adult skeletal stem cell response to laser-machined topographies through deep learning10.1016/j.tice.2020.101442 ↗
61. Lasers that learn: The interface of laser machining and machine learning10.1049/ote2.12039 ↗
62. Modeling pulsed laser micromachining of micro geometries using machine-learning techniques10.1007/s10845-013-0835-x ↗
63. 2020
64. Int. J. Adv. Manufact. Technol. · 2019 · 104 · 188910.1007/s00170-019-03988-5 ↗
65. Lensless imaging of pollen grains at three-wavelength using deep learning
66. Phase recovery and holographic image reconstruction using deep learning in neural networks10.1038/lsa.2017.141 ↗
67. A neural lens for super-resolution biological imaging
68. Image-based roughness estimation of laser cut edges with a convolutional neural network10.1016/j.procir.2020.09.166 ↗
69. Image-based modelling and visualisation of the relationship between laser-cut edge and process parameters10.1016/j.optlastec.2021.107028 ↗
70. Modelling of fibre laser cutting via deep learning10.1364/OE.432741 ↗
71. An experimental investigation of hole geometry in friction drilling10.1080/10426914.2012.746699 ↗
72. Influence of rotational speed on mechanical features of thermally drilled holes in dual-phase steel10.1177/0954405418805601 ↗
73. Thin-sheet metal welding10.1080/09507116.2011.600022 ↗
74. Analysis of geometrical parameters and occurrence of defects in the hole-flanging process on thin sheet metal10.1016/j.jmatprotec.2016.03.027 ↗
75. Real-time monitoring of high-power fibre-laser cutting for different types of materials10.3116/16091833/20/2/72/2019 ↗
76. Experimental investigation of hydrodynamics of melt layer during laser cutting of steel10.1088/0022-3727/44/10/105502 ↗
77. P. Isola , J.Zhu, T.Zhou, and A.Efros, “Image-to-image translation with conditional adversarial networks,” arXiv:1611.07004 (2016) (Accessed 20 March 2021).10.1109/CVPR.2017.632 ↗
78. 2002 · 51
79. C. Szegedy , V.Vanhoucke, S.Ioffe, J.Shlens, and Z.Wojna, “Rethinking the inception architecture for computer vision,” arXiv:1512.00567v3.pdf (2015).10.1109/CVPR.2016.308 ↗
80. 2020
81. A. F. Courtier , M.Praeger, J. A.Grant-Jacob, C.Codemard, P.Harrison, M.Zervas, and B.Mills, “Dataset in support of the journal paper ‘Predictive Visualisation of Fibre Laser Cutting Topography via Deep Learning with Image Inpainting.’” 10.5258/SOTON/D2489