Abstract
This paper proposes a methodology for detection and classification of fatigue damage in mechanical structures in the framework of neural networks (NN). The proposed methodology has been tested and validated with polycrystalline-alloy (AL7075-T6) specimens on a laboratory-scale experimental apparatus. Signal processing tools (e.g., discrete wavelet transform and Hilbert transform) have been applied on time series of ultrasonic test signals to extract features that are derived from: (i) Signal envelope, (ii) Low-frequency and high-frequency signal spectra, and (iii) Signal energy. The performance of the neural network, combined with each one of these features, is compared with the ground truth, generated from the original ultrasonic test signals and microscope images. The results show that the NN model, combined with the signal-energy feature, yields the best performance and that it is capable of detecting and classifying the fatigue damage with (up to) 98.5% accuracy.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
Manufacturer: MTS®, Berlin, New Jersey, USA.
Manufacturer: OLYMPUS®, Shinjuku, Tokyo, Japan.
Manufacturer: QUESTAR®, New Hope, Pennsylvania, USA.
The reason for using five (apparently) identical specimens is to build both consistency and credibility of experimental results. The rationale is that, due to the uncertainties accruing from internal defects and the machining process, the fatigue life of similar test specimens may significantly duffer.
References
Suresh S (1998) Fatigue of materials. Cambridge University Press, Cambridge, UK
Campbell FC (2008) Elements of metallurgy and engineering alloys. ASM International, The Netherlands
Worden K, Farrar CR, Manson G, Park G (2007) The fundamental axioms of structural health monitoring. Proc Royal Soc A: Math Phys Eng Sci 463(2082):1639–1664
Kumar P, Prashant K (2009) Elements of fracture mechanics. Tata McGraw-Hill Education, US
See JE, Drury CG, Speed A, Williams A, Khalandi N (2017) The role of visual inspection in the 21st century, in: Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Vol. 61, SAGE Publications Sage CA: Los Angeles, CA, , pp. 262–266
Poor H (1994) An introduction to signal detection and estimation. Spriger-Verlag, New York, NY, USA
Chicco D, Jurman G (2020) The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation. BMC Genomics 21(1):1–13
Boughorbel S, Jarray F, El-Anbari M (2017) Optimal classifier for imbalanced data using matthews correlation coefficient metric. PloS one 12(6):e0177678
Kaiser G (1994) A friendly guide to wavelets. Birkhauser, Boston, MA, USA
Mallat S (2009) A wavelet tour of signal processing: the sparse way, 3rd edn. Academic Publishers, Amsterdam, The Netherlands
Alqahtani H, Ray A (2021) Forecasting and detection of fatigue cracks in polycrystalline alloys with ultrasonic testing via discrete wavelet transform. J Nondest Eval Diagn Prognostics Eng Syst 4:1–15
D’Angelo G, Rampone S (2016) Feature extraction and soft computing methods for aerospace structure defect classification. Measurement 85:192–209
Paolanti M, Romeo L, Felicetti A, Mancini A, Frontoni E, Loncarski J (2018) Machine learning approach for predictive maintenance in industry 4.0, in: 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), IEEE, , pp. 1–6
Susto GA, Schirru A, Pampuri S, McLoone S, Beghi A (2014) Machine learning for predictive maintenance: a multiple classifier approach. IEEE Trans Ind Inform 11(3):812–820
Alqahtani H, Bharadwaj S, Ray A (2021) Classification of fatigue crack damage in polycrystalline alloy structures using convolutional neural networks. Eng Fail Anal 119:104908
Gholizadeh S (2016) A review of non-destructive testing methods of composite materials. Proc Struct Integr 1:50–57
Garnier C, Pastor M-L, Eyma F, Lorrain B (2011) The detection of aeronautical defects in situ on composite structures using non destructive testing. Compos Struct 93(5):1328–1336. https://doi.org/10.1016/j.compstruct.2010.10.017
Shull PJ (2002) Nondestructive evaluation: theory, techniques, and applications. CRC Press, Boca Raton, Florida, USA
Ghojogh B, Samad MN, Mashhadi S A, Kapoor T, Ali W, Karray F, Crowley M Feature selection and feature extraction in pattern analysis: A literature review, arXiv preprint arXiv:1905.02845
Vithlani P, Kumbharana C (2015) Structural and statistical feature extraction methods for character and digit recognition. Int J Comput Appl 120(24):0975–8887
Alonso GA, Gutiérrez JM, Marty J-L, Muñoz R, Implementation of the discrete wavelet transform used in the calibration of the enzymatic biosensors, Discrete Wavelet Transforms-Biomedical Applications
Rioul O, Vetterli M (1991) Wavelets and signal processing. IEEE Signal Proc Mag 8(4):14–38
Oliveira MO, Bretas AS (2009) Application of discrete wavelet transform for differential protection of power transformers, in. IEEE Buchat PowerTech IEEE 2009:1–8
Mane AR, Biradar P, Shastri P (2015) Review paper on feature extraction methods for eeg signal analysis. Department of electronics and telecommunication engineering. VPCOE/Savitribi Phule University, IJEEBS, pp 2349–6967
Cohen L (1995) Time-frequency analysis. Prentice-Hall PTR, Upper Saddle River, NJ, USA
Klingspor M(2015) Hilbert transform: Mathematical theory and applications to signal processing
Kschischang FR (2006) The Hilbert transform. University of Toronto, Toronto, Canada 83:277
Alqahtani H, Ray A (2020) Neural network-based automated assessment of fatigue damage in mechanical structures. Machines 8(4):85
Coolen AC (1998) A beginner’s guide to the mathematics of neural networks. Concepts for neural networks. Springer, NY, pp 13–70
Zakaria M, Al-Shebany M, Sarhan S (2014) Artificial neural network: a brief overview. Int J Eng Res Appl 4:7–12
Islam M, Chen G, Jin S (2019) An overview of neural network. Am J Neural Netw Appl 5(1):7–11
A. Zayegh, N. Al Bassam (2018) Neural network principles and applications, in: Digital Systems, IntechOpen
Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin
Møller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6(4):525–533
Dkhichi F, Oukarfi B (2014) Neural network training by gradient descent algorithms: application on the solar cell. Int J Innov Res Sci Eng Technol 3:15696–15702
Ghorpade S, Ghorpade J, Mantri S (2010) Pattern recognition using neural networks. Int J Comput Sci Inform Technol (IJCSIT) 2(6):92
Ghotkar VN, Indurkar P, Chilke B (2015) The pattern recognition using spiking neural network and neural network. Int J 5:ISO 690
Acknowledgements
The first author gratefully acknowledges the financial support of the Saudi Arabian Cultural Mission (SACM). The work reported in this paper has been supported in part by U.S. Air Force Office of Scientific Research (AFOSR) under Grant No. FA9550-15-1-0400.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
We have no conflicts of interest to disclose.
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
Alqahtani, H., Ray, A. Feature extraction and neural network-based fatigue damage detection and classification. Neural Comput & Applic 34, 21253–21273 (2022). https://doi.org/10.1007/s00521-022-07609-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07609-3