Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing
Source abstract
Abstract
Finding actionable trends in laser-based metal additive manufacturing process monitoring data is challenging owing to the diversity and complexity of the underlying physical interactions. A single monitoring solution that captures a particular process phenomenon, such as a photodiode that tracks melt pool intensity, is not alone capable of evaluating process stability or detecting flaw formation with sufficient precision for routine application in industry. In this work, to improve flaw detection performance, we adopted a data fusion approach that captures multiple process phenomena. To demonstrate this, we acquired data from laser powder bed fusion (LPBF) builds of cylindrical specimens produced with different laser spot sizes, emulating defocusing due to process faults such as thermal lensing. The resulting specimens had porosity of varying types and severity, quantified by post-build non-destructive X-ray computed tomography, Archimedes density measurements, and destructive metallographic characterization. During the build, the melt pool state was monitored with two coaxial high-speed video cameras and a temperature field imaging system. Physically intuitive low-level melt pool signatures, such as melt pool temperature, shape and size, and spatter intensity were extracted from this high-dimensional, image-based sensor data. These process signatures were subsequently used as input features in relatively simple machine learning models, such as a support vector machine, which were trained to detect laser defocusing, and in addition, predict porosity type and severity. The results show that the data fusion approach significantly enhanced system performance by reducing the overall false positive rate from ~ 0.1 to ~ 0.001 without sacrificing the true positive rate (~0.90). These results were at par with a black-box, deep machine learning approach (convolutional neural network).
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing Materials and Processes · Welding Techniques and Residual Stresses · Advanced X-ray and CT Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (84)
Show source-provided references
1. The metallurgy and processing science of metal additive manufacturing10.1080/09506608.2015.1116649 ↗
2. Additive manufacturing: technology, applications and research needs10.1007/s11465-013-0248-8 ↗
3. Process defects and in situmonitoring methods in metal powder bed fusion: a review10.1088/1361-6501/aa5c4f ↗
4. A review on measurement science needs for real-time control of additive manufacturing metal powder bed fusion processes10.1080/00207543.2016.1223378 ↗
5. A Review on Process Monitoring and Control in Metal-Based Additive Manufacturing10.1115/1.4028540 ↗
6. In-process sensing in selective laser melting (SLM) additive manufacturing10.1186/s40192-016-0045-4 ↗
7. Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing10.1016/j.matdes.2016.01.099 ↗
8. In-situ measurement and monitoring methods for metal powder bed fusion: an updated review10.1088/1361-6501/ac0b6b ↗
9. Laser powder bed fusion additive manufacturing of metals; physics, computational, and materials challenges10.1063/1.4937809 ↗
10. Closing the science gap in 3D metal printing10.1126/science.abb4938 ↗
11. Invited review article: review of the formation and impact of flaws in powder bed fusion additive manufacturing
12. Improvement of selective laser melting by beam shaping and minimized thermally induced effects in optical systems
13. Effects of shield gas flow on meltpool variability and signature in scanned laser melting
14. Goossens, L. R., Kinds, Y., Kruth, J.-P., and Van Hooreweder, B., 2018, “On the influence of thermal lensing during selective laser melting,” Solid freeform fabrication symposium proceedings (SFF Symp 2018), pp. 2267-2274.
15. Digitally twinned additive manufacturing: detecting flaws in laser powder bed fusion by combining thermal simulations with in-situ meltpool sensor data10.1016/j.matdes.2021.110167 ↗
16. In situ thermography for laser powder bed fusion: effects of layer temperature on porosity, microstructure and mechanical properties
17. Direct observation of pore formation mechanisms during LPBF additive manufacturing process and high energy density laser welding10.1016/j.ijmachtools.2020.103555 ↗
18. Part-scale thermal simulation of laser powder bed fusion using graph theory: effect of thermal history on porosity, microstructure evolution, and recoater crash10.1016/j.matdes.2021.109685 ↗
19. Laser powder-bed fusion additive manufacturing: physics of complex melt flow and formation mechanisms of pores, spatter, and denudation zones10.1016/j.actamat.2016.02.014 ↗
20. Progress towards metal additive manufacturing standardization to support qualification and certification10.1007/s11837-017-2265-2 ↗
21. Overview of materials qualification needs for metal additive manufacturing10.1007/s11837-015-1810-0 ↗
22. Research and application of machine learning for additive manufacturing
23. Monitoring and prediction of porosity in laser powder bed fusion using physics-informed meltpool signatures and machine learning10.1016/j.jmatprotec.2022.117550 ↗
24. Montazeri, M., Yavari, R., Rao, P., and Boulware, P., 2018, “In-Process Monitoring of Material Cross-Contamination Defects in Laser Powder Bed Fusion,” Journal of Manufacturing Science and Engineering, 140(11).doi:10.1115/1.4040543.10.1115/1.4040543 ↗
25. Huang, Y., Leu, M. C., Mazumder, J., and Donmez, A., 2015, “Additive Manufacturing: Current State, Future Potential, Gaps and Needs, and Recommendations,” Journal of Manufacturing Science and Engineering, 137(1).doi:10.1115/1.4028725.10.1115/1.4028725 ↗
26. Machine learning in additive manufacturing: State-of-the-art and perspectives
27. Machine learning in additive manufacturing: a review10.1007/s11837-020-04155-y ↗
28. A method for objectively evaluating the defect detection performance of in-situ monitoring systems
29. Melt pool temperature and cooling rates in laser powder bed fusion
30. Additive manufacturing of metallic components – Process, structure and properties10.1016/j.pmatsci.2017.10.001 ↗
31. Controlling interdependent meso-nanosecond dynamics and defect generation in metal 3D printing10.1126/science.aay7830 ↗
32. Denudation of metal powder layers in laser powder bed fusion processes10.1016/j.actamat.2016.05.017 ↗
33. Observation of keyhole-mode laser melting in laser powder-bed fusion additive manufacturing10.1016/j.jmatprotec.2014.06.005 ↗
34. On the use of spatter signature for in-situ monitoring of laser powder bed fusion
35. In-Process Monitoring of Selective Laser Melting: Spatial Detection of Defects Via Image Data Analysis10.1115/1.4034715 ↗
36. Application of characterization, modelling, and analytics towards understanding process-structure linkages in metallic 3D printing10.1088/1757-899X/219/1/012002 ↗
37. Mechanisms and characteristics of spatter generation in SLM processing and its effect on the properties10.1016/j.matdes.2016.12.060 ↗
38. A study on the laser spatter and the oxidation reactions during selective laser melting of 316L stainless steel, Al-Si10-Mg, and Ti-6Al-4V10.1007/s11661-015-2882-8 ↗
39. In-situ characterization and quantification of melt pool variation under constant input energy density in laser powder bed fusion additive manufacturing process
40. Laser-metal interaction dynamics during additive manufacturing resolved by detection of thermally-induced electron emission10.1038/s43246-020-00094-y ↗
41. Prediction of lack-of-fusion porosity for powder bed fusion
42. Porosity measurements and analysis for metal additive manufacturing process control10.6028/jres.119.019 ↗
43. Keyhole threshold and morphology in laser melting revealed by ultrahigh-speed x-ray imaging10.1126/science.aav4687 ↗
44. Toward in-situ flaw detection in laser powder bed fusion additive manufacturing through layerwise imagery and machine learning10.1016/j.jmsy.2021.01.008 ↗
45. Defects and anomalies in powder bed fusion metal additive manufacturing10.1016/j.cossms.2021.100974 ↗
46. Process mapping and In-process monitoring of porosity in laser powder bed fusion using layerwise optical imaging10.1115/1.4040615 ↗
47. Pyrometric-based melt pool monitoring study of CuCr1Zr processed using L-PBF10.3390/ma13204626 ↗
48. On the limitations of volumetric energy density as a design parameter for selective laser melting10.1016/j.matdes.2016.10.037 ↗
49. Closed-loop control of meltpool temperature in directed energy deposition10.1016/j.matdes.2022.110508 ↗
50. Image segmentation using K -means clustering algorithm and subtractive clustering algorithm10.1016/j.procs.2015.06.090 ↗
51. Formation processes for large ejecta and interactions with melt pool formation in powder bed fusion additive manufacturing10.1038/s41598-019-41415-7 ↗
52. Identification and characterization of spatter particles and their effect on surface roughness, density and mechanical response of 17–4 PH stainless steel laser powder-bed fusion parts10.1016/j.msea.2019.04.026 ↗
53. On the effect of spatter particles distribution on the quality of Hastelloy X parts made by laser powder-bed fusion additive manufacturing10.1016/j.jmapro.2018.11.012 ↗
54. On the role of melt flow into the surface structure and porosity development during selective laser melting10.1016/j.actamat.2015.06.004 ↗
55. Heterogeneous sensing and scientific machine learning for quality assurance in laser powder bed fusion – A single-track study
56. A three-phase model for simulation of heat transfer and melt pool behaviour in laser powder bed fusion process10.1016/j.powtec.2020.11.061 ↗
57. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences10.1016/S1352-2310(97)00447-0 ↗
58. A random forest guided tour10.1007/s11749-016-0481-7 ↗
59. What is a support vector machine?10.1038/nbt1206-1565 ↗
60. Mitchell, T. M., 1997, Machine Learning, McGraw-Hill.
61. Machine-learning-based monitoring of laser powder bed fusion10.1002/admt.201800136 ↗
62. Defect detection and monitoring in metal additive manufactured parts through deep learning of spatially resolved acoustic spectroscopy signals10.1520/SSMS20180035 ↗
63. Semi-supervised convolutional neural networks for in-situ video monitoring of selective laser melting
64. A convolutional approach to quality monitoring for laser manufacturing10.1007/s10845-019-01495-8 ↗
65. In situ process monitoring for laser-powder bed fusion using convolutional neural networks and infrared tomography
66. A multi-scale convolutional neural network for autonomous anomaly detection and classification in a laser powder bed fusion additive manufacturing process
67. Deep learning for distortion prediction in laser-based additive manufacturing using big data10.1016/j.mfglet.2019.02.001 ↗
68. Thermal field prediction for laser scanning paths in laser aided additive manufacturing by physics-based machine learning10.1016/j.cma.2019.112734 ↗
69. Geometry-agnostic data-driven thermal modeling of additive manufacturing processes using graph neural networks
70. P, Becker, C, Roth, A, Roennau, R, Dillmann, 2020, “Acoustic Anomaly Detection in Additive Manufacturing with Long Short-Term Memory Neural Networks,” 2020 IEEE 7th International Conference on Industrial Engineering and Applications (ICIEA), pp. 921-926doi:10.1109/ICIEA49774.2020.9102002.10.1109/ICIEA49774.2020.9102002 ↗
71. DLAM: deep learning based real-time porosity prediction for additive manufacturing using thermal images of the melt pool10.1109/ACCESS.2021.3105362 ↗
72. Generative adversarial network for early-stage design flexibility in topology optimization for additive manufacturing10.1016/j.jmsy.2021.04.007 ↗
73. C, Gobert, E, Arrieta, A, Belmontes, B, Wicker, F, Medina, B, McWilliams, 2019, “Conditional generative adversarial networks for in-situ layerwise additive manufacturing data,” Proceeding of the 29th international Solid Freeform Fabrication Symposium, doi:10.20944/preprints202101.0519.v1.10.20944/preprints202101.0519.v1 ↗
74. Deep semi-supervised learning of dynamics for anomaly detection in laser powder bed fusion10.1007/s10845-021-01842-8 ↗
75. An encoder-decoder based approach for anomaly detection with application in additive manufacturing
76. In situ monitoring of thin-wall build quality in laser powder bed fusion using deep learning
77. Heterogeneous sensor-based condition monitoring in directed energy deposition
78. K-fold cross validation for error rate estimate in support vector machines
79. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring10.1016/j.eswa.2017.02.017 ↗
80. Analysis of defect generation in Ti–6Al–4V parts made using powder bed fusion additive manufacturing processes
81. Toward the digital twin of additive manufacturing: integrating thermal simulations, sensing, and analytics to detect process faults10.1080/24725854.2019.1701753 ↗
82. Sensor-based build condition monitoring in laser powder bed fusion additive manufacturing process using a spectral graph theoretic approach10.1115/1.4040264 ↗
83. In-process monitoring of porosity in additive manufacturing using optical emission spectroscopy10.1080/24725854.2019.1659525 ↗
84. Wang, D., Zhang, M., Li, Z., Cui, Y., Liu, J., Yang, Y., and Wang, H., 2015, “Nonlinear decision boundary created by a machine learning-based classifier to mitigate nonlinear phase noise,” 2015 European Conference on Optical Communication (ECOC), pp. 1-3doi:10.1109/ECOC.2015.7341753.10.1109/ECOC.2015.7341753 ↗