Abstract
Additive manufacturing (AM) technologies enable complex, high-value components to be printed, with potential applications in the automotive, aerospace, and biomedical sectors. Porosity in AM processes for metals is a recurrent problem which can lead to adverse effects such as crack initiation and ultimately to parts’ early-life failure. There are several pore classifications described in the literature, which are focused on traditional manufacturing processes. The current lack of information makes it difficult to accurately identify and classify pores in AM-made parts. The present work describes a proposal based on image processing and machine learning, specifically random forests, to classify porosity automatically in metallographic images. The proposed method is divided into 3 stages. (1) Preprocessing stage: image denoising, smoothing, and unblurring to highlight the areas with pores. (2) Feature extraction stage: segmentation of pores and the morphological/geometrical features that describe the porosity. (3) Intelligent classifier stage: definition, training, testing, and validation of the random forest classifier. Our proposal has an accurate balance between the calculation of the feature importance as well as the number to use, the adequate number of trees to grow per forest, and the correct selection of the size of the database. The proposed method achieves an accuracy of 94.41% and out-of-bag error less than 5%. These results guarantee high precision in the porosity classification task. Our approach has the potential to be used in the porosity analysis of any metallic additively manufactured component.
Similar content being viewed by others
References
A. C. F. on Additive Manufacturing Technologies, A. C. F. on Additive Manufacturing Technologies (2012) Subcommittee F42. 91 on Terminology Standard terminology for additive manufacturing technologies Astm International
Jiang J, Xu X, Stringer J (2018) Support structures for additive manufacturing: a review. J Manufact Mater Process 2(4):64
Mahamood RM (2018) Laser metal deposition process of metals, alloys, and composite materials, Springer, New York
Dass A, Moridi A (2019) State of the art in directed energy deposition: from additive manufacturing to materials design. Coatings 9(7):418
Yasa E, Kruth J-P, Deckers J (2011) Manufacturing by combining selective laser melting and selective laser erosion/laser re-melting. CIRP annals 60(1):263–266
Liu Y, Wang W, Xie J, Sun S, Wang L, Qian Y, Meng Y, Wei Y (2012) Microstructure and mechanical properties of aluminum 5083 weldments by gas tungsten arc and gas metal arc welding. Mater Sci Eng A 549:7–13
Tabernero I, Lamikiz A, Martínez S, Ukar E, Figueras J (2011) Evaluation of the mechanical properties of inconel 718 components built by laser cladding. Int J Mach Tools Manuf 51(6):465–470
Lowell S, Shields JE, Thomas MA, Thommes M (2012) Characterization of porous solids and powders: surface area, pore size and density, vol 16. Springer Science & Business Media, Berlin
Zdravkov BD, Čermák JJ, Šefara M, Jankŭ J (2007) Pore classification in the characterization of porous materials: A perspective. Central European J Chem 5(2):385–395. https://doi.org/10.2478/s11532-007-0039-3
B. C. o. M. o. I. American Welding Society (AWS) (2015) Guide for the visual examination of welds, Tech. rep. American National Standards Institute
A. R. 577 (2013) Welding inspection and metallurgy, Tech. rep. American Petroleum Institute (API)
Welding and allied processes - classification of geometric imperfections in metallic materials - part 1: Fusion welding (2020) Tech. rep., International Organization for Standardization
Mays T (2007) A new classification of pore sizes, studies in surface science and catalysis 160 (Characterization of) 57–62
Khanzadeh M, Chowdhury S, Marufuzzaman M, Tschopp MA, Bian L (2018) Porosity prediction: supervised-learning of thermal history for direct laser deposition. J Manuf Syst 47:69–82
Zhang B, Liu S, Shin YC (2019) In-process monitoring of porosity during laser additive manufacturing process. Addit Manuf 28:497–505
Ye D, Wang W, Zhou H, Huang J, Wu W, Gong H, Li Z (2019) In-situ evaluation of porosity in thermal barrier coatings based on the broadening of terahertz time-domain pulses: simulation and experimental investigations. Opt Express 27(20):28150–28165
Dilip J, Zhang S, Teng C, Zeng K, Robinson C, Pal D, Stucker B (2017) Influence of processing parameters on the evolution of melt pool, porosity, and microstructures in ti-6al-4v alloy parts fabricated by selective laser melting. Prog Addit Manuf 2(3):157–167
Zhan X, Qi C, Gao Z, Tian D, Wang Z (2019) The influence of heat input on microstructure and porosity during laser cladding of invar alloy. Opt Laser Technol 113:453–461
Schlüter S, Sheppard A, Brown K, Wildenschild D (2014) Image processing of multiphase images obtained via x-ray microtomography: a review. Water Resour Res 50(4):3615–3639
Schwerdtfeger J, Singer RF, Körner C (2012) In situ flaw detection by ir-imaging during electron beam melting. Rapid Prototyp J 18(4):259–263
Cai X, Malcolm AA, Wong BS, Fan Z (2015) Measurement and characterization of porosity in aluminium selective laser melting parts using x-ray ct. Virt Phys Prototyp 10(4):195–206
Cunningham R, Narra SP, Montgomery C, Beuth J, Rollett A (2017) Synchrotron-based x-ray microtomography characterization of the effect of processing variables on porosity formation in laser power-bed additive manufacturing of ti-6al-4v. Jom 69(3):479–484
Farzadi A, Solati-Hashjin M, Asadi-Eydivand M, Osman NAA (2014) Effect of layer thickness and printing orientation on mechanical properties and dimensional accuracy of 3d printed porous samples for bone tissue engineering. PloS one 9(9):e108252
Deshpande S, Kulkarni A, Sampath S, Herman H (2004) Application of image analysis for characterization of porosity in thermal spray coatings and correlation with small angle neutron scattering. Surface and coatings technology 187(1):6–16
Brooks AJ, Ge J, Kirka MM, Dehoff RR, Bilheux HZ, Kardjilov N, Manke I, Butler LG (2017) Porosity detection in electron beam-melted ti-6al-4v using high-resolution neutron imaging and grating-based interferometry. Progress Addit Manufact 2(3):125–132
Serdeczny MP, Comminal R, Pedersen DB, Spangenberg J (2018) Numerical prediction of the porosity of parts fabricated with fused deposition modeling. In: 29th annual international solid freeform fabrication symposium (SFF Symp 2018), laboratory for freeform fabrication, pp 1849–1854
García-Moreno A-I (2019) Automatic quantification of porosity using an intelligent classifier. Int J Adv Manuf Technol 105(5-6):1883–1899
Zhang B, Allebach JP (2008) Adaptive bilateral filter for sharpness enhancement and noise removal. IEEE Trans Image Process 17(5):664–678
Vankawala F, Ganatra A, Patel A (2015) A survey on different image deblurring techniques, International Journal of Computer Applications 116 (13)
Yang H-L, Huang P-H, Lai S-H (2014) A novel gradient attenuation richardson–lucy algorithm for image motion deblurring. Signal Process 103:399–414
Breiman L (2001) Random forests. Mach Learn 45:5–32
Degenhardt F, Seifert S, Szymczak S (2019) Evaluation of variable selection methods for random forests and omics data sets. Brief Bioinform 20(2):492–503
Breiman L (2001) . Machine Learning 45(1):5–32. https://doi.org/10.1023/a:1010933404324
Deng H, Runger G (2013) Gene selection with guided regularized random forest. Patt Recog 46(12):3483–3489. https://doi.org/10.1016/j.patcog.2013.05.018
Hapfelmeier A, Ulm K (2013) A new variable selection approach using random forests. Comput Stat Data Anal 60:50–69. https://doi.org/10.1016/j.csda.2012.09.020
Ishwaran H, Kogalur U (2014) Randomforestsrc: Random forests for survival, regression and classification (rf-src), R package version 1 (0)
Genuer R, Poggi J-M, Tuleau-Malot C (2015) Vsurf: an r package for variable selection using random forests
Janitza S, Celik E, Boulesteix A-L (2018) A computationally fast variable importance test for random forests for high-dimensional data. ADAC 12(4):885–915
Kuhn M, et al. (2008) Building predictive models in r using the caret package. J Stat Softw 28 (5):1–26
Acknowledgments
Acknowledgments are due to program Cátedras-CONACYT (National Council for Science and Technology of Mexico) for the support provided by generating research opportunities through the project num. 730. Additionally, thanks are due to the CONACYT Consortium in Additive Manufacturing (CONMAD) for the use of experimental facilities for this work.
Funding
The authors received the financial support provided by CONACYT through the Programs Fordecyt (projects 297265 and 296384).
Author information
Authors and Affiliations
Corresponding author
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
García-Moreno, AI., Alvarado-Orozco, JM., Ibarra-Medina, J. et al. Image-based porosity classification in Al-alloys by laser metal deposition using random forests. Int J Adv Manuf Technol 110, 2827–2845 (2020). https://doi.org/10.1007/s00170-020-05887-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-020-05887-6