Acoustic emission with machine learning in fracture of composites: preliminary study

• Autorzy: Smolnicki Michał , Duda Szymon , Stabla Paweł , Zielonka Paweł , Lesiuk Grzegorz

Identyfikatory

DOI

10.1007/s43452-023-00795-4

• Języki publikacji: EN

Abstrakty

EN

In this paper, preliminary studies on the failure analysis of hybrid composite materials utilizing acoustic emission and machine learning are presented. The main purpose of this study was to analyze the possibilities of using machine learning techniques as a way to better cluster the data obtained from acoustic emission. In this paper, we focus on data preparation, feature extraction (Laplacian score), determination of cluster number (Caliński-Harabasz, Silhouette, and Davies-Bouldin), and testing three clustering techniques, namely K-means, fuzzy C-means, and spectral clustering. The dataset was obtained by testing fber metal laminates-composites consisting of metal and composite layers. Two experimental tests were realized on pre-cracked rectangular specimens-one with loading in mode I and one with loading in mode II (DCB-double cantilever beam and ENF-end-notch fexural test). Elastic waves were recorded during these tests via an acoustic emission system. Preliminary studies show that the proposed method can be used successfully to cluster data obtained in this way. The obtained dataset was split into 3 clusters (for the ENF test) and 5 clusters (DCB test). In the next stages of the research campaign, based on the presented results, we intend to change the approach to semi-supervised by running additional single cause damage tests to enhance the achieved results and enable easier damage recognition.

Słowa kluczowe

EN

FML; composites; acoustic emission; clustering; machine learning; DCB

• Wydawca: Springer ; Wrocław University of Science and Technology
• Czasopismo: Archives of Civil and Mechanical Engineering
• Rocznik: 2023
• Tom: Vol. 23, no. 4
• Strony: art. e254, 1--18
• Opis fizyczny: Bibliogr. 44 poz., il., tab., wykr.

Twórcy

autor

Smolnicki Michał

• Wroclaw University of Science and Technology, Mechanical Engineering Department, Wrocław, Poland

• https://orcid.org/0000-0003-1489-1062

autor

Duda Szymon

• Wroclaw University of Science and Technology, Mechanical Engineering Department, Wrocław, Poland

• https://orcid.org/0000-0002-5046-5485

autor

Stabla Paweł

• Wroclaw University of Science and Technology, Mechanical Engineering Department, Wrocław, Poland

• https://orcid.org/0000-0001-6891-582X

autor

Zielonka Paweł

• Wroclaw University of Science and Technology, Mechanical Engineering Department, Wrocław, Poland

• https://orcid.org/0000-0002-1178-3368

autor

Lesiuk Grzegorz

• Wroclaw University of Science and Technology, Mechanical Engineering Department, Wrocław, Poland

• https://orcid.org/0000-0003-3553-6107

Bibliografia

• 1. Prabhu T. NONDESTRUCTIVE TESTING (NDT): a comprehensive guide to NDT, Kindle Edition. 2021. https://www.amazon.com/ NONDE STRUC TIVE-TESTI NG-NDT-Comprehensive-Guide-ebook/dp/B0957XCZ4W. Accessed 17 Aug 2023.
• 2. Ohtsu M. History and fundamentals. In: Grosse C, Ohtsu M, editors. Acoustic emission testing: basics for research-applications in civil engineering. Berlin: Springer, Berlin Heidelberg; 2008. p. 11-18. https://doi.org/10.1007/978-3-540-69972-9_2.
• 3. Ohtsu M. Sensor and instrument. In: Grosse C, Ohtsu M, editors. Acoustic emission testing: basics for research-applications in civil engineering. Berlin: Springer, Berlin Heidelberg; 2008. p. 19-40. https://doi.org/10.1007/978-3-540-69972-9_3.
• 4. Schulze K, Hausmann J, Wielage B. The Stability of different titanium-PEEK interfaces against water. Proced Mater Sci. 2013;2:92-102. https://doi.org/10.1016/j.mspro.2013.02.012.
• 5. Pärnänen T, Alderliesten R, Rans C, Brander T, Saarela O. Applicability of AZ31B-H24 magnesium in fibre metal laminates - an experimental impact research. Compos Part A Appl Sci Manuf. 2012;43(9):1578-86. https:// doi. org/10.1016/j.compositesa.2012.04.008.
• 6. Khokhar S, Husain, SW and. Fakhar MA, “Numerical and experimental analysis of fracture toughness improvement using multi-walled carbon nanotube modified epoxy in fiber metal laminate joints. https://www.ist.edu.pk/.
• 7. Santulli C, Kuan HT, Sarasini F, De Rosa IM, Cantwell WJ. “Damage characterisation on PP-hemp/aluminium fibre-metal-laminates using acoustic emission. J Compos Mater. 2012. https://doi.org/10.1177/0021998312457098.
• 8. Ishak NM, Malingam SD, Mansor R, Razali N, Mustafa Z, Ab Ghani AF. Investigation of natural fibre metal laminate as car front hood. Mater Res Express. 2021;8(2):25303. https:// doi.org/10.1088/2053-1591/abe49d.
• 9. Chandrasekar M, Ishak MR, Sapuan SM, Leman Z, Jawaid M, Shahroze RM. Fabrication of fibre metal laminate with flax and sugar palm fibre based epoxy composite and evaluation of their fatigue properties. J Polym Mater. 2018;35(4):463–73. https://doi.org/10.32381/JPM.2018.35.04.5.
• 10. Du D, Hu Y, Li H, Liu C, Tao J. Open-hole tensile progressive damage and failure prediction of carbon fiber-reinforced PEEK-titanium laminates. Compos B Eng. 2016;91:65-74. https://doi.org/10.1016/j.compositesb.2015.12.049.
• 11. Smolnicki M, Duda S, Stabla P, Osiecki T. Mechanical investigation on interlaminar behaviour of inverse FML using acoustic emission and finite element method. Compos Struct. 2022. https://doi.org/10.1016/j.compstruct.2022.115810.
• 12. Gonzalez-Canche NG, Flores-Johnson EA, Carrillo JG. Mechanical characterization of fiber metal laminate based on aramid fiber reinforced polypropylene. Compos Struct. 2017;172:259-66. https://doi.org/10.1016/j.compstruct.2017.02.100.
• 13. Smolnicki M, Duda Sz, Stabla P, Osiecki T. Mechanical investigation of inverse FML under mode II loading using acoustic emission and finite element method. Compos Struct. 2023;313:116943. https://doi.org/10.1016/J.COMPSTRUCT.2023.116943.
• 14. Al-Azzawi ASM, Kawashita LF, Featherston CA. A modified cohesive zone model for fatigue delamination in adhesive joints: numerical and experimental investigations. Compos Struct. 2019;225:111114. https://doi. org/ 10. 1016/j. comps truct. 2019. 111114.
• 15. McCrory J. Advanced acoustic emission (AE) monitoring techniques for aerospace structures cardiff school of engineering, Cardiff. 2015. https://orca. cardiff.ac.uk/id/ print/ 89212.Accessed 10 Apr 2021.
• 16. Dia A, Dieng L, Gaillet L, Gning PB. Damage detection of a hybrid composite laminate aluminum/glass under quasi-static and fatigue loadings by acoustic emission technique. Heliyon. 2019;5(3):e01414. https:// doi. org/10.1016/j.heliyon.2019.e01414.
• 17. Chow MF. “Acoustic emission study of fiber orientations on fiber-metal laminates under monotonic tensile loading,” CUNY City College. 2013. https://academicworks.cuny.edu/cc_etds_theses/179. Accessed 10 Apr 2021.
• 18. McCrory JP, Pullin R, Pearson MR, Eaton MJ, Featherston CA, Holford KM. Effect of delta-T grid resolution on acoustic emission source location in GLARE. https://www.ndt.net/article/ewgae2012/content/papers/46_McCrory_Rev2.pdf. Accessed 10 Apr 2021.
• 19. Kuznetsova R, Ergun H, Liaw B. Acoustic emission of failure in fiber-metal laminates. RILEM Bookseries. 2012;6:619–25. https://doi.org/10.1007/978-94-007-0723-8_88.
• 20 Jenis J, Ondriga J, Hrcek S, Brumercik F, Cuchor M, Sadovsky E. Engineering applications of artificial intelligence in mechanical design and optimization. Machines. 2023;11(6):577.
• 21. Nasiri S, Khosravani MR. Applications of data-driven approaches in prediction of fatigue and fracture. Mater Today Commun. 2022;33:104437. https://doi.org/10.1016/J. MTCOMM. 2022.104437.
• 22. Nasiri S, Khosravani MR. Machine learning in predicting mechanical behavior of additively manufactured parts. J Market Res.2021;14:1137–53. https://doi.org/10.1016/J.JMRT.2021.07.004.
• 23. Smolnicki M. Machine learning approach based on the finite element method to predict reaction forces. Struct Integr.2022;25:337-46. https://doi. org/10.1007/978-3-030- 91847-7_32/COVER.
• 24. Asongo AI, Barma. Machine learning techniques, methods and algorithms: conceptual and practical insights. Int J Eng Res Appl. 2021;11:55-64. https://doi.org/10.9790/9622-1108025564.
• 25. Barile C, Casavola C, Pappalettera G, Paramsamy Kannan V. “Laplacian score and K-means data clustering for damage characterization of adhesively bonded CFRP composites by means of acoustic emission technique. Appl Acoust. 2022.
• 26. Pashmforoush F, Khamedi R, Fotouhi M, Hajikhani M, Ahmadi M. Damage classification of sandwich composites using acoustic emission technique and k-means genetic algorithm. J Nondestr Eval. 2014;33(4):481-92.
• 27. Qiao S, Zhou W, Liang Y, Liu J, Liu S. Cluster analysis on damage pattern recognition in carbon/epoxy composites using acoustic emission wavelet packet. J Reinf Plast Compos. 2022;2022:073168442211443.
• 28. Li L, Lomov SV, Yan X, Carvelli V. Cluster analysis of acoustic emission signals for 2D and 3D woven glass/epoxy composites. Compos Struct. 2014;116(1):286-299. https://doi.org/10.1016/j.compstruct.2014.05.023.
• 29. Godin N, Huguet S, Gaertner R, Salmon L. Clustering of acoustic emission signals collected during tensile tests on unidirectional glass/polyester composite using supervised and unsupervised classifiers. NDT E Int. 2004;37(4):253-64. https://doi.org/10.1016/j.ndteint.2003.09.010.
• 30. Pashmforoush F, Fotouhi M, Ahmadi M. Acoustic emission-based damage classification of glass/polyester composites using harmony search k-means algorithm. J Reinf Plast Compos. 2012;31(10):671-680. https://doi.org/10.1177/0731684412442257.
• 31. RefahiOskouei A, Heidary H, Ahmadi M, Farajpur M. Unsupervised acoustic emission data clustering for the analysis of damage mechanisms in glass/polyester composites. Mater Des. 2021;37:416-22. https://doi.org/10.1016/J.MATDES.2012.01.018.
• 32. Ichenihi A, Li W, Gao Y, Rao Y. Feature selection and clustering of damage for pseudo-ductile unidirectional carbon/glass hybrid composite using acoustic emission. Appl Acoust. 2021. https://doi.org/10.1016/j.apacoust.2021.108184.
• 33. He X, Cai D, Niyogi P. “Laplacian Score for Feature Selection. In: Proceedings of the 18th international conference on neural information processing systems, Vancouver, British Columbia, Canada: MIT Press, 2005, pp. 507-514.
• 34. ASTM D5528-01. Standard test method for mode I interlaminar fracture toughness of unidirectional fiber-reinforced polymer matrix composites. American Standard of Testing Methods, 2014.
• 35. ASTM D7905. Standard test method for determination of the mode II interlaminar fracture toughness of unidirectional fiber-reinforced polymer matrix composites. West Conshohocken: ASTM; 2014. p. 1-18. https:// doi. org/ 10. 1520/ D7905_D7905M-14.
• 36. Giallanza A, Parrinello F, Ruggiero V, Marannano G. Fatigue crack growth of new FML composites for light ship buildings under predominant mode II loading condition. Int J Interact Des Manuf. 2020;14(1):77-87. https://doi. org/10.1007/s12008-019-00617-z.
• 37. Davies DL, Bouldin DW. A cluster separation measure. IEEE Trans Pattern Anal Mach Intell. 1979; PAMI1(2):224-7. https://doi.org/10.1109/TPAMI.1979.4766909.
• 38. Rousseeuw PJ. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math. 1987;20(C):53-65. https:// doi.org/10.1016 0377-0427(87)90125-7.
• 39. Caliñski T, Harabasz J. A dendrite method foe cluster analysis. Commun Stat. 1974;3(1):1-27. https:// doi. org/10.1080/03610.927408827101.
• 40. MacQueen J. Some methods for classification and analysis of multivariate observations. Comput Chem. 1967;4:257-272.
• 41. Dunn JC. “A fuzzy relative of the ISODATA process and Its use in detecting compact well-separated clusters. J Cyberne. 2008;3(3):32-57. https://doi.org/10.1080/01969727308546046.
• 42 Bezdek JC. Pattern recognition with fuzzy objective function algorithms. 1st ed. New York, NY: Springer; 1981. https://doi.org/10. 1007/978-1-4757-0450-1.
• 43. Madson Luiz Dantas Dias, “fuzzy-c-means: An implementation of Fuzzy C-means clustering algorithm.” Zenodo, 2019. Accessed: Jun. 06, 2023. 10.5281/zenodo.3066222.
• 44. Saeedifar M, Zarouchas D. Damage characterization of laminated composites using acoustic emission: a review. Compos B Eng. 2020;195:108039. https:// doi.org/10.1016/J. COMPO SITESB. 2020.108039.