Qualify-as-you-go: sensor fusion of optical and acoustic signatures with contrastive deep learning for multi-material composition monitoring in laser powder bed fusion process

References

• Ahmed N, Barsoum I, Haidemenopoulos G, et al. Process parameter selection and optimization of laser powder bed fusion for 316L stainless steel: A review (in English). J Manuf Process. 2022;75:415–434. doi:10.1016/j.jmapro.2021.12.064
   Web of Science ®Google Scholar
• Sanchez-Mata O, Wang X, Muniz-Lerma JA, et al. Dependence of mechanical properties on crystallographic orientation in nickel-based superalloy Hastelloy X fabricated by laser powder bed fusion. J Alloys Compd. 2021;865:158868. doi:10.1016/j.jallcom.2021.158868
   Web of Science ®Google Scholar
• Wang L, Song Z, Zhang X, et al. Developing ductile and isotropic Ti alloy with tailored composition for laser powder bed fusion. Addit Manuf. 2022;52:102656. doi:10.1016/j.addma.2022.102656
   Web of Science ®Google Scholar
• Rometsch PA, Zhu Y, Wu X, et al. Review of high-strength aluminium alloys for additive manufacturing by laser powder bed fusion. Mater Des. 2022;219:110779. doi:10.1016/j.matdes.2022.110779
   Web of Science ®Google Scholar
• Zhou W, Kousaka T, Moriya S-i, et al. Fabrication of a strong and ductile CuCrZr alloy using laser powder bed fusion. Addit Manuf Lett. 2023;5:100121. doi:10.1016/j.addlet.2023.100121
   Google Scholar
• Zhang X, Pan T, Chen Y, et al. Additive manufacturing of copper-stainless steel hybrid components using laser-aided directed energy deposition. J Mater Sci Technol. 2021;80:100–116. doi:10.1016/j.jmst.2020.11.048
   Web of Science ®Google Scholar
• Chen J, Yang Y, Song C, et al. Interfacial microstructure and mechanical properties of 316L/CuSn10 multi-material bimetallic structure fabricated by selective laser melting. Mater Sci Eng A. 2019;752:75–85. doi:10.1016/j.msea.2019.02.097
   Web of Science ®Google Scholar
• Rodrigues TA, Bairrão N, Farias FWC, et al. Steel-copper functionally graded material produced by twin-wire and arc additive manufacturing (T-WAAM). Mater Des. 2022;213:110270. doi:10.1016/j.matdes.2021.110270
   Web of Science ®Google Scholar
• Leedy KD, Stubbins JF. Copper alloy–stainless steel bonded laminates for fusion reactor applications: crack growth and fatigue. Mat Sci Eng a-Struct. 2001;297(1-2):19–25. doi:10.1016/S0921-5093(00)01274-0
   Google Scholar
• Wang S, Ning J, Zhu L, et al. Role of porosity defects in metal 3D printing: formation mechanisms, impacts on properties and mitigation strategies. Mater Today. 2022;59:133–160. doi:10.1016/j.mattod.2022.08.014
   Web of Science ®Google Scholar
• Du Plessis A, Yadroitsava I, Yadroitsev I. Effects of defects on mechanical properties in metal additive manufacturing: A review focusing on X-ray tomography insights. Mater Des. 2020;187:108385. doi:10.1016/j.matdes.2019.108385
   Web of Science ®Google Scholar
• Cerniglia D, Scafidi M, Pantano A, et al. Inspection of additive-manufactured layered components. Ultrasonics. 2015;62:292–298. doi:10.1016/j.ultras.2015.06.001
   PubMed Web of Science ®Google Scholar
• Acevedo R, Sedlak P, Kolman R, et al. Residual stress analysis of additive manufacturing of metallic parts using ultrasonic waves: state of the art review. J Mater Res Technol. 2020;9(4):9457–9477. doi:10.1016/j.jmrt.2020.05.092
   Google Scholar
• Shah P, Racasan R, Bills P. Comparison of different additive manufacturing methods using computed tomography. Case Stud Nondestr Test Eval. 2016;6:69–78. doi:10.1016/j.csndt.2016.05.008
   Google Scholar
• Tammas-Williams S, Withers PJ, Todd I, et al. The influence of porosity on fatigue crack initiation in additively manufactured titanium components. Sci Rep. 2017;7(1):7308. doi:10.1038/s41598-017-06504-5
   PubMedGoogle Scholar
• Mazumder J. Design for metallic additive manufacturing machine with capability for “Certify as You Build”. Procedia CIRP. 2015;36:187–192. doi:10.1016/j.procir.2015.01.009
   Google Scholar
• Zhu L, Xue P, Lan Q, et al. Recent research and development status of laser cladding: A review. Opt Laser Technol. 2021;138:106915. doi:10.1016/j.optlastec.2021.106915
   Web of Science ®Google Scholar
• Wang C, Tan X, Tor SB, et al. Machine learning in additive manufacturing: State-of-the-art and perspectives. Addit Manuf. 2020;36:101538. doi:10.1016/j.addma.2020.101538
   Web of Science ®Google Scholar
• Seifi M, Gorelik M, Waller J, et al. Progress towards metal additive manufacturing standardization to support qualification and certification. JOM. 2017;69:439–455. doi:10.1007/s11837-017-2265-2
   Web of Science ®Google Scholar
• Everton SK, Hirsch M, Stravroulakis P, et al. Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing. Mater Des. 2016;95:431–445. doi:10.1016/j.matdes.2016.01.099
   Web of Science ®Google Scholar
• Hossain MS, Taheri H. In situ process monitoring for additive manufacturing through acoustic techniques. J Mater Eng Perform. 2020;29(10):6249–6262. doi:10.1007/s11665-020-05125-w
   Web of Science ®Google Scholar
• Lane B, Grantham S, Yeung H, et al. Performance characterization of process monitoring sensors on the NIST additive manufacturing metrology testbed. 2017 International solid freeform fabrication symposium. University of Texas at Austin; 2017. https://api.semanticscholar.org/CorpusID:55777435.
   Google Scholar
• Montazeri M, Rao P. Sensor-based build condition monitoring in laser powder bed fusion additive manufacturing process using a spectral graph theoretic approach. J Manuf Sci Eng. 2018;140(9):091002. doi:10.1115/1.4040264
   Web of Science ®Google Scholar
• Pandiyan V. Deep learning-based monitoring of laser powder bed fusion process on variable time-scales using heterogeneous sensing and operando X-ray radiography guidance. Addit Manuf. 2022;58:103007. doi:10.1016/j.addma.2022.103007
   Web of Science ®Google Scholar
• Özel T, Shaurya A, Altay A, et al. Process monitoring of meltpool and spatter for temporal-spatial modeling of laser powder bed fusion process. Procedia CIRP. 2018;74:102–106. doi:10.1016/j.procir.2018.08.049
   Google Scholar
• Pandiyan V, Wróbel R, Leinenbach C, et al. Optimizing in-situ monitoring for laser powder bed fusion process: deciphering acoustic emission and sensor sensitivity with explainable machine learning. J Mater Process Technol. 2023: 118144. doi:10.1016/j.jmatprotec.2023.118144
   Web of Science ®Google Scholar
• Pandiyan V, Drissi-Daoudi R, Shevchik S, et al. Analysis of time, frequency and time-frequency domain features from acoustic emissions during Laser Powder-Bed fusion process. Procedia CIRP. 2020;94:392–397. doi:10.1016/j.procir.2020.09.152
   Google Scholar
• Imani F, Gaikwad A, Montazeri M, et al. Process mapping and in-process monitoring of porosity in laser powder bed fusion using layerwise optical imaging. J Manuf Sci Eng. 2018;140(10):101009. doi:10.1115/1.4040615
   Web of Science ®Google Scholar
• McCann R, Obeidi MA, Hughes C, et al. In-situ sensing, process monitoring and machine control in Laser Powder Bed Fusion: A review. Addit Manuf. 2021;45:102058. doi:10.1016/j.addma.2021.102058
   Web of Science ®Google Scholar
• Taherkhani K, Ero O, Liravi F, et al. On the application of in-situ monitoring systems and machine learning algorithms for developing quality assurance platforms in laser powder bed fusion: A review. J Manuf Process. 2023;99:848–897. doi:10.1016/j.jmapro.2023.05.048
   Web of Science ®Google Scholar
• Cai Y, Xiong J, Chen H, et al. A review of in-situ monitoring and process control system in metal-based laser additive manufacturing. J Manuf Syst. 2023;70:309–326. doi:10.1016/j.jmsy.2023.07.018
   Web of Science ®Google Scholar
• Lane B, Zhirnov I, Mekhontsev S, et al. Transient laser energy absorption, co-axial melt pool monitoring, and relationship to melt pool morphology. Addit Manuf. 2020;36:101504. doi:10.1016/j.addma.2020.101504
   Web of Science ®Google Scholar
• Schwerz C, Nyborg L. Linking in situ melt pool monitoring to melt pool size distributions and internal flaws in laser powder bed fusion. Metals (Basel). 2021;11(11):1856. doi:10.3390/met11111856
   Web of Science ®Google Scholar
• Khanzadeh M, Tian W, Yadollahi A, et al. Dual process monitoring of metal-based additive manufacturing using tensor decomposition of thermal image streams. Addit Manuf. 2018;23:443–456. doi:10.1016/j.addma.2018.08.014
   Web of Science ®Google Scholar
• Bertoli US, Guss G, Wu S, et al. In-situ characterization of laser-powder interaction and cooling rates through high-speed imaging of powder bed fusion additive manufacturing. Mater Des. 2017;135:385–396. doi:10.1016/j.matdes.2017.09.044
   Web of Science ®Google Scholar
• Yang Z, Zhu L, Wang S, et al. Effects of ultrasound on multilayer forming mechanism of Inconel 718 in directed energy deposition. Addit Manuf. 2021;48:102462. doi:10.1016/j.addma.2021.102462
   Web of Science ®Google Scholar
• Ashby A, Guss G, Ganeriwala RK, et al. Thermal history and high-speed optical imaging of overhang structures during laser powder bed fusion: A computational and experimental analysis. Addit Manuf. 2022;53:102669. doi:10.1016/j.addma.2022.102669
   Web of Science ®Google Scholar
• Forien J-B, Calta NP, DePond PJ, et al. Detecting keyhole pore defects and monitoring process signatures during laser powder bed fusion: A correlation between in situ pyrometry and ex situ X-ray radiography. Addit Manuf. 2020;35:101336. doi:10.1016/j.addma.2020.101336
   Web of Science ®Google Scholar
• Gutknecht K, Cloots M, Wegener K. Relevance of single channel signals for two-colour pyrometer process monitoring of laser powder bed fusion. Int J Mechatron Manuf Syst. 2021;14(2):111–127. doi:10.1504/IJMMS.2021.119152
   Google Scholar
• Vallabh CKP, Zhao X. Melt pool temperature measurement and monitoring during laser powder bed fusion based additive manufacturing via single-camera two-wavelength imaging pyrometry (STWIP). J Manuf Process. 2022;79:486–500. doi:10.1016/j.jmapro.2022.04.058
   Web of Science ®Google Scholar
• Mao Z, Feng W, Ma H, et al. Continuous online flaws detection with photodiode signal and melt pool temperature based on deep learning in laser powder bed fusion. Opt Laser Technol. 2023;158:108877. doi:10.1016/j.optlastec.2022.108877
   Web of Science ®Google Scholar
• Mitchell JA, Ivanoff TA, Dagel D, et al. Linking pyrometry to porosity in additively manufactured metals. Addit Manuf. 2020;31:100946. doi:10.1016/j.addma.2019.100946
   Web of Science ®Google Scholar
• Lapointe S, Guss G, Reese Z, et al. Photodiode-based machine learning for optimization of laser powder bed fusion parameters in complex geometries. Addit Manuf. 2022;53:102687. doi:10.1016/j.addma.2022.102687
   Web of Science ®Google Scholar
• Khairallah SA, Anderson AT, Rubenchik A, et al. Laser powder-bed fusion additive manufacturing: physics of complex melt flow and formation mechanisms of pores, spatter, and denudation zones. Acta Mater. 2016;108:36–45. doi:10.1016/j.actamat.2016.02.014
   Web of Science ®Google Scholar
• Fisher BA, Lane B, Yeung H, et al. Toward determining melt pool quality metrics via coaxial monitoring in laser powder bed fusion. Manuf Lett. 2018;15:119–121. doi:10.1016/j.mfglet.2018.02.009
   PubMedGoogle Scholar
• Zhao C, et al. Real-time monitoring of laser powder bed fusion process using high-speed X-ray imaging and diffraction. Sci Rep. 2017;7(1):1–11. doi:10.1038/s41598-016-0028-x
   PubMed Web of Science ®Google Scholar
• Mazzoleni L, Demir AG, Caprio L, et al. Real-time observation of melt pool in selective laser melting: spatial, temporal, and wavelength resolution criteria. IEEE Trans Instrum Meas. 2020;69(4):1179–1190. doi:10.1109/TIM.2019.2912236
   Web of Science ®Google Scholar
• Drissi-Daoudi R, Pandiyan V, Logé R, et al. Differentiation of materials and laser powder bed fusion processing regimes from airborne acoustic emission combined with machine learning. Virtual Phys Prototyp. 2022;17(2):181–204. doi:10.1080/17452759.2022.2028380
   Web of Science ®Google Scholar
• Gaikwad A, Williams RJ, de Winton H, et al. Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing. Mater Des. 2022;221:110919. doi:10.1016/j.matdes.2022.110919
   Web of Science ®Google Scholar
• Khanzadeh M, Chowdhury S, Marufuzzaman M, et al. Porosity prediction: supervised-learning of thermal history for direct laser deposition. J Manuf Syst. 2018;47:69–82. doi:10.1016/j.jmsy.2018.04.001
   Web of Science ®Google Scholar
• Ye D, Fuh Y, Zhang Y, et al. Defects recognition in selective laser melting with acoustic signals by SVM based on feature reduction. IOP Conf Ser: Mater Sci Eng. 2018;436(1):012020. doi:10.1088/1757-899X/436/1/012020
   Google Scholar
• Ye D, Hong GS, Zhang Y, et al. Defect detection in selective laser melting technology by acoustic signals with deep belief networks. Int J Adv Manuf Technol. 2018;96:2791–2801. doi:10.1007/s00170-018-1728-0
   Web of Science ®Google Scholar
• Pandiyan V, Drissi-Daoudi R, Shevchik S, et al. Semi-supervised monitoring of laser powder bed fusion process based on acoustic emissions. Virtual Phys Prototyp. 2021;16(4):481–497. doi:10.1080/17452759.2021.1966166
   Web of Science ®Google Scholar
• Shevchik SA, Kenel C, Leinenbach C, et al. Acoustic emission for in situ quality monitoring in additive manufacturing using spectral convolutional neural networks. Addit Manuf. 2018;21:598–604. doi:10.1016/j.addma.2017.11.012
   Web of Science ®Google Scholar
• Becker P, Roth C, Rönnau A, et al. Porosity detection in powder bed fusion additive manufacturing with convolutional neural networks. doi: 10.18178/wcse.2022.04.117.
   Google Scholar
• Pandiyan V, Drissi-Daoudi R, Shevchik S, et al. Deep transfer learning of additive manufacturing mechanisms across materials in metal-based laser powder bed fusion process. J Mater Process Technol. 2022;303:117531. doi:10.1016/j.jmatprotec.2022.117531
   Web of Science ®Google Scholar
• Shevchik SA, Masinelli G, Kenel C, et al. Deep learning for in situ and real-time quality monitoring in additive manufacturing using acoustic emission. IEEE Trans Ind Inf. 2019;15(9):5194–5203. doi:10.1109/TII.2019.2910524
   Web of Science ®Google Scholar
• Xing W, Chu X, Lyu T, et al. Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process. J Manuf Process. 2022;74:486–499. doi:10.1016/j.jmapro.2021.12.030
   Web of Science ®Google Scholar
• Kwon O, Kim HG, Ham MJ, et al. A deep neural network for classification of melt-pool images in metal additive manufacturing. J Intell Manuf. 2020;31:375–386. doi:10.1007/s10845-018-1451-6
   Web of Science ®Google Scholar
• Pandiyan V, Wróbel R, Richter RA, et al. Monitoring of Laser Powder Bed Fusion process by bridging dissimilar process maps using deep learning-based domain adaptation on acoustic emissions. Addit Manuf. 2024: 103974. doi:10.1016/j.addma.2024.103974
   Web of Science ®Google Scholar
• Pandiyan V, Wróbel R, Richter RA, et al. Self-Supervised Bayesian representation learning of acoustic emissions from laser powder bed Fusion process for in-situ monitoring. Mater Des. 2023;235:112458. doi:10.1016/j.matdes.2023.112458
   Web of Science ®Google Scholar
• Khosla P, et al. Supervised contrastive learning. Adv Neural Inf Process Syst. 2020;33:18661–18673. doi:10.48550/arXiv.2004.11362
   Google Scholar
• Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations. International Conference on Machine Learning. 2020;2020: PMLR:1597–1607. doi:10.48550/arXiv.2002.05709
   Google Scholar
• Spijkervet J, Burgoyne JA. Contrastive learning of musical representations. arXiv preprint arXiv:2103.09410; 2021. doi: 10.48550/arXiv.2103.09410.
   Google Scholar
• Pandiyan V, Cui D, Le-Quang T, et al. In situ quality monitoring in direct energy deposition process using co-axial process zone imaging and deep contrastive learning. J Manuf Process. 2022;81:1064–1075. doi:10.1016/j.jmapro.2022.07.033
   Web of Science ®Google Scholar
• Ge W. Deep metric learning with hierarchical triplet loss. Proceedings of the European Conference on Computer Vision (ECCV); 2018. p. 269–285. doi:10.48550/arXiv.1810.06951
   Google Scholar
• Dong X, Shen J. Triplet loss in siamese network for object tracking. Proceedings of the European Conference on Computer Vision (ECCV); 2018. p. 472–488. doi:10.1007/978-3-030-01261-8_28
   Google Scholar
• Sun Y, et al. Circle loss: A unified perspective of pair similarity optimization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2020. p. 6398–6407. doi:10.48550/arXiv.2002.10857
   Google Scholar
• Xiao R. Adaptive margin circle loss for speaker verification. arXiv preprint arXiv:2106.08004; 2021. doi:10.48550/arXiv.2106.08004
   Google Scholar
• Li J, Cai Y, Yan F, et al. Porosity and liquation cracking of dissimilar Nd: YAG laser welding of SUS304 stainless steel to T2 copper. Opt Laser Technol. 2020;122:105881. doi:10.1016/j.optlastec.2019.105881
   Web of Science ®Google Scholar
• Xiao P, Wang L, Tang Y, et al. Effect of wire composition on microstructure and penetration crack of laser-cold metal transfer hybrid welded Cu and stainless steel joints. Mater Chem Phys. 2023;299:127480. doi:10.1016/j.matchemphys.2023.127480
   Web of Science ®Google Scholar
• Gao Z, Yang Y, Wang L, et al. Formation mechanism and control of solidification cracking in laser-welded joints of steel/copper dissimilar metals. Metals (Basel). 2022;12(7):1147. doi:10.3390/met12071147
   Web of Science ®Google Scholar
• Chen S, Yu X, Huang J, et al. Interfacial ferrite band formation to suppress intergranular liquid copper penetration of solid steel. J Alloys Compd. 2019;773:719–729. doi:10.1016/j.jallcom.2018.09.282
   Web of Science ®Google Scholar
• Paszke A, et al. Pytorch: An imperative style, high-performance deep learning library. Adv Neural Inf Process Syst. 2019: 8026–8037. doi:10.48550/arXiv.1912.01703
   Google Scholar
• Zhou Z-H, Zhou Z-H. Ensemble learning. Singapore: Springer; 2021. doi:10.1007/978-0-387-73003-5_293
   Google Scholar
• Chen T, He T, Benesty M, et al. Xgboost: Extreme Gradient Boosting. R package version 0.4-2 1, 2015; (4):1–4.
   Google Scholar
• Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-Learn: Machine Learning in Python. J Mach Learn Res. 2011; 12: 2825–2830.
   Google Scholar