A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites
Source abstract
Abstract
Abstract In this work, we demonstrate that damage mechanism identification from acoustic emission (AE) signals generated in minicomposites with elastically similar constituents is possible. AE waveforms were generated by SiC/SiC ceramic matrix minicomposites (CMCs) loaded under uniaxial tension and recorded by four sensors (two models with each model placed at two ends). Signals were encoded with a modified partial power scheme and subsequently partitioned through spectral clustering. Matrix cracking and fiber failure were identified based on the frequency information contained in the AE event they produced, despite the similar constituent elastic properties of the matrix and fiber. Importantly, the resultant identification of AE events closely followed CMC damage chronology, wherein early matrix cracking is later followed by fiber breaks, even though the approach is fully domain-knowledge agnostic. Additionally, the partitions were highly precise across both the model and location of the sensors, and the partitioning was repeatable. The presented approach is promising for CMCs and other composite systems with elastically similar constituents.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Rock Mechanics and Modeling · Ultrasonics and Acoustic Wave Propagation · Structural Health Monitoring Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (60)
Show source-provided references
1. Zok, F. W. Ceramic-matrix composites enable revolutionary gains in turbine engine efficiency. Am. Ceram. Soc. Bull 95, 22–28 (2016).
2. Lee, W. E., Gilbert, M., Murphy, S. T. & Grimes, R. W. Opportunities for advanced ceramics and composites in the nuclear sector. J. Am. Ceram. Soc. 96, 2005–2030 (2013).10.1111/jace.12406 ↗
3. Halbig, M. C., Jaskowiak, M. H., Kiser, J. D. & Zhu, D. Evaluation of ceramic matrix composite technology for aircraft turbine engine applications. In 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition 2013 (AIAA, 2013).10.2514/6.2013-539 ↗
4. Steibel, J. Ceramic matrix composites taking flight at GE Aviation. Am. Ceram. Soc. Bull. 98, 30–33 (2019).
5. Morscher, G. N. & Godin, N. In Ceramic Matrix Composites: Materials, Modeling and Technology 1st edn (eds Bansal, N. P. & Lamon, J.) 571–590 (Wiley, 2015), 1 edn.
6. Whitlow, T., Jones, E. & Przybyla, C. In-situ damage monitoring of a SiC/SiC ceramic matrix composite using acoustic emission and digital image correlation. Composite Struct. 158, 245–251 (2016).10.1016/j.compstruct.2016.09.040 ↗
7. Swaminathan, B. et al. Microscale characterization of damage accumulation in CMCs. J. Eur. Ceram. Soc. 41, 3082–3093 (2021).10.1016/j.jeurceramsoc.2020.05.077 ↗
8. Maillet, E. et al. Combining in-situ synchrotron x-ray microtomography and acoustic emission to characterize damage evolution in ceramic matrix composites. J. Eur. Ceram. Soc. 39, 3546–3556 (2019).10.1016/j.jeurceramsoc.2019.05.027 ↗
9. Sukhanov, D., Zavyalova, K. & Kadurina, A. Method for enhancement of spatial resolution of eddy current imaging. Meas. Sci. Technol. 30, 065402 (2019).10.1088/1361-6501/ab0b10 ↗
10. Smith, C. & Gyekenyesi, A. Detecting cracks in ceramic matrix composites by electrical resistance. In Proc. SPIE The International Society for Optical Engineering 7983 79830N (SPIE, 2011).10.1117/12.882027 ↗
11. Hilmas, A. M., Sevener, K. M. & Halloran, J. W. Damage evolution in SiC/SiC unidirectional composites by x-ray tomography. J. Am. Ceram. Soc. 103, 3436–3447 (2020).10.1111/jace.17017 ↗
12. Elsley, R. K. & Graham, L. J. Pattern recognition in acoustic emission experiments. Pattern Recognit. Acoust. Imaging 0768, 285 (1987).10.1117/12.940279 ↗
13. de Groot, P. J., Wijnen, P. A. & Janssen, R. B. Real-time frequency determination of acoustic emission for different fracture mechanisms in carbon/epoxy composites. Compos. Sci. Technol. 55, 405–412 (1995).10.1016/0266-3538(95)00121-2 ↗
14. Johnson, M. & Gudmundson, P. Broad-band transient recording and characterization of acoustic emission events in composite laminates. Compos. Sci. Technol. 60, 2803–2818 (2000).10.1016/S0266-3538(00)00148-2 ↗
15. Sause, M. G., Gribov, A., Unwin, A. R. & Horn, S. Pattern recognition approach to identify natural clusters of acoustic emission signals. Pattern Recognit. Lett. 33, 17–23 (2012).10.1016/j.patrec.2011.09.018 ↗
16. Muir, C. et al. Damage mechanism identification in composites via machine learning and acoustic emission. npj Comput. Mater. 7, 1–15 (2021).10.1038/s41524-021-00565-x ↗
17. Maillet, E., Baker, C., Morscher, G. N., Pujar, V. V. & Lemanski, J. R. Feasibility and limitations of damage identification in composite materials using acoustic emission. Compos. Part A Appl. Sci. Manuf. 75, 77–83 (2015).10.1016/j.compositesa.2015.05.003 ↗
18. Jain, A. K., Murty, M. P. & Flynn, P. J. Data clustering: a review. ACM Comput. Surv. 31, 264–323 (1999).10.1145/331499.331504 ↗
19. Jain, A. K. Data clustering: 50 years beyond k-means. Pattern Recognit. Lett. 31, 651–666 (2010).10.1016/j.patrec.2009.09.011 ↗
20. Gorman, M. R. & Ziola, S. M. Plate waves produced by transverse matrix cracking. Ultrasonics 29, 245–251 (1991).10.1016/0041-624X(91)90063-E ↗
21. Kostopoulos, V., Loutas, T. & Dassios, K. Fracture behavior and damage mechanisms identification of SiC/glass ceramic composites using AE monitoring. Compos. Sci. Technol. 67, 1740–1746 (2007).10.1016/j.compscitech.2005.02.002 ↗
22. Chelliah, S. K., Parameswaran, P., Ramasamy, S., Vellayaraj, A. & Subramanian, S. Optimization of acoustic emission parameters to discriminate failure modes in glass-epoxy composite laminates using pattern recognition. Struct. Health Monit. 18, 1253–1267 (2019).10.1177/1475921718791321 ↗
23. Moevus, M. et al. Analysis of damage mechanisms and associated acoustic emission in two SiCf/[Si-B-C] composites exhibiting different tensile behaviours. Part II: Unsupervised acoustic emission data clustering. Compos. Sci. Technol. 68, 1258–1265 (2008).10.1016/j.compscitech.2007.12.002 ↗
24. de Oliveira, R. & Marques, A. T. Health monitoring of FRP using acoustic emission and artificial neural networks. Comput. Struct. 86, 367–373 (2008).10.1016/j.compstruc.2007.02.015 ↗
25. Godin, N., Huguet, S. & Gaertner, R. Integration of the Kohonen’s self-organising map and k-means algorithm for the segmentation of the AE data collected during tensile tests on cross-ply composites. NDT E Int. 38, 299–309 (2005).10.1016/j.ndteint.2004.09.006 ↗
26. Marec, A., Thomas, J. H. & El Guerjouma, R. Damage characterization of polymer-based composite materials: Multivariable analysis and wavelet transform for clustering acoustic emission data. Mech. Syst. Signal Process. 22, 1441–1464 (2008).10.1016/j.ymssp.2007.11.029 ↗
27. Gorman, M. R. & Prosser, W. H. AE source orientation by plate wave analysis. J. Acoust. Emiss. 9, 283–288 (1991).
28. Surgeon, M. & Wevers, M. Modal analysis of acoustic emission signals from CFRP laminates. NDT E Int. 32, 311–322 (1999).10.1016/S0963-8695(98)00077-2 ↗
29. Morscher, G. N. Modal acoustic emission of damage accumulation in a woven SiC/SiC composite. Compos. Sci. Technol. 59, 687–697 (1999).10.1016/S0266-3538(98)00121-3 ↗
30. Hamstad, M., O’Gallagher, a & Gary, J. A wavelet transform applied to acoustic emission signals: part 2: source location. J. Acoust. Emiss. 20, 62–82 (2002).
31. Sause, M. G. & Horn, S. Simulation of acoustic emission in planar carbon fiber reinforced plastic specimens. J. Nondestructive Eval. 29, 123–142 (2010).10.1007/s10921-010-0071-7 ↗
32. Aggelis, D. G., Shiotani, T., Papacharalampopoulos, A. & Polyzos, D. The influence of propagation path on elastic waves as measured by acoustic emission parameters. Struct. Health Monit. 11, 359–366 (2012).10.1177/1475921711419992 ↗
33. Muir, C. et al. Large scale statistical methods to evaluate damage accumulation in SiC/SiC composites. In SEM Annual 2020 Virtual XIV International Congress (SEM, 2020).
34. Maillet, E. et al. Damage monitoring and identification in SiC/SiC minicomposites using combined acousto-ultrasonics and acoustic emission. Compos. Part A Appl. Sci. Manuf. 57, 8–15 (2014).10.1016/j.compositesa.2013.10.010 ↗
35. Graff, K. F. Wave Motion in Elastic Solids (Ohio State University Press, 1975).
36. Kostopoulos, V., Loutas, T. H., Kontsos, A., Sotiriadis, G. & Pappas, Y. Z. On the identification of the failure mechanisms in oxide/oxide composites using acoustic emission. NDT E Int. 36, 571–580 (2003).10.1016/S0963-8695(03)00068-9 ↗
37. Ng, A., Jordan, M. & Weiss, Y. On spectral clustering: analysis and an algorithm. In Proc. 14th International Conference on Neural Information Processing Systems: Natural and Synthetic. 849–846 (NIPS, 2001).
38. Rodriguez, M. Z. et al. Clustering algorithms: a comparative approach. PLoS ONE 14, 1–34 (2019).
39. Pedregosa, F. et al. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
40. Muir, C. Spectral clustering for AE. https://github.com/Muir-UCSB/AE-ML_Framework (2021).
41. Prosser, W. Advanced AE techniques in composite materials research. J. Acoust. Emiss 14, S1–S11 (1996).
42. Sause, M. G. & Horn, S. Quantification of the uncertainty of pattern recognition approaches applieSd to acoustic emission signals. J. Nondestructive Eval. 32, 242–255 (2013).10.1007/s10921-013-0177-9 ↗
43. Kempf, M., Skrabala, O. & Altstädt, V. Reprint of: Acoustic emission analysis for characterisation of damage mechanisms in fibre reinforced thermosetting polyurethane and epoxy. Compos. Part B Eng. 65, 117–123 (2014).10.1016/j.compositesb.2014.05.003 ↗
44. Wisner, B. et al. Acoustic emission signal processing framework to identify fracture in aluminum alloys. Eng. Fract. Mech. 210, 367–380 (2019).10.1016/j.engfracmech.2018.04.027 ↗
45. Guel, N. et al. Data merging of AE sensors with different frequency resolution for the detection and identification of damage in oxide-based ceramic matrix composites. Materials 13, 1–22 (2020).10.3390/ma13204691 ↗
46. Afzalan, M. & Jazizadeh, F. An automated spectral clustering for multi-scale data. Neurocomputing 347, 94–108 (2019).10.1016/j.neucom.2019.03.008 ↗
47. Marshall, D. B. & Oliver, W. C. Measurement of interfacial mechanical properties in fiber-reinforced ceramic composites. J. Am. Ceram. Soc. 70, 542–548 (1987).10.1111/j.1151-2916.1987.tb05702.x ↗
48. Callaway, E. B., Christodoulou, P. G. & Zok, F. W. Deformation, rupture and sliding of fiber coatings in ceramic composites. J. Mech. Phys. Solids 132, 103673 (2019).10.1016/j.jmps.2019.07.016 ↗
49. Swaminathan, B. et al. Interpreting acoustic energy emission in SiC/SiC minicomposites through modeling of fracture surface areas. J. Eur. Ceram. Soc. 41, 6883–6893 (2021).10.1016/j.jeurceramsoc.2021.06.030 ↗
50. Hubert, L. & Arabie, P. Comparing partitions. J. Classification 2, 193–218 (1985).10.1007/BF01908075 ↗
51. Gates, A. J. & Ahn, Y. Y. The impact of random models on clustering similarity. J. Mach. Learn. Res. 18, 1–28 (2017).
52. Santos, J. M. & Embrechts, M. In Artificial Neural Networks – ICANN 2009 (eds Alippi, C., Polycarpou, M., Panayiotou, C. & Ellinas, G.) 175–184 (Springer Berlin Heidelberg, 2009).
53. van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008).
54. Hamstad, M. A. Acoustic emission signals generated by monopole (pencil-lead break) versus dipole sources: finite element modeling and experiments. J. Acoust. Emiss. 25, 92–106 (2007).
55. Curtin, W. A., Ahn, B. K. & Takeda, N. Modeling brittle and tough stress-strain behavior in unidirectional ceramic matrix composites. Acta Mater. 46, 3409–3420 (1998).10.1016/S1359-6454(98)00041-X ↗
56. Almansour, A., Maillet, E., Ramasamy, S. & Morscher, G. N. Effect of fiber content on single tow SiC minicomposite mechanical and damage properties using acoustic emission. J. Eur. Ceram. Soc. 35, 3389–3399 (2015).10.1016/j.jeurceramsoc.2015.06.001 ↗
57. Callaway, E. B. & Zok, F. W. Strengths of ceramic fiber bundles: theory and practice. J. Am. Ceram. Soc. 100, 5306–5317 (2017).10.1111/jace.15062 ↗
58. Sause, M. G. Acoustic emission source identification in large scale fibre reinforced composites. In Czech Society for Nondestructive Testing 32nd European Conference on Acoustic Emission Testing. 125–136 (Czech Society for Nondestructive Testing, 2016).
59. Ospitia, N., Aggelis, D. G. & Tsangouri, E. Dimension effects on the acoustic behavior of TRC plates. Materials 13, 955 (2020).10.3390/ma13040955 ↗
60. Ono, K. Through-transmission characteristics of AE sensor couplants. J. Acoust. Emiss. 34, 1 (2017).