Abstract
Artificial neural networks (ANNs) are a powerful method for solving classification problems, particularly for clustered data. However, one of the main challenges in using ANNs for general classification problems is determining the best topology (number of layers and neurons per layer) for a given problem or dataset. This study proposes a novel approach to address this challenge by using a optimisation algorithm. The algorithm first solves an external optimisation problem to obtain the optimal topology that maximises the accuracy of supervised learning. After, an inner optimisation problem is used to train the network to detect damage, using the Frequency Response Function of vibration-based measurements as input. To test the proposed methodology, it is applied to three different mechanical systems: metallic beams, rolling bearings, and composite plates. Principal component analysis is used to reduce the number of inputs to the neural network, and the external optimisation problem is solved using Particle swarm optimisation. The results demonstrate that the proposed methodology can accurately assess damage. Through the results, a discussion is presented about the potentialities and limitations of the proposed methodology as a support tool for damage detection.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available from the corresponding author upon request.
References
S.S. Kessler, S.M. Spearing, M.J. Atalla, C.E. Cesnik, C. Soutis, Damage detection in composite materials using frequency response methods. Compos. B Eng. 33(1), 87–95 (2002). https://doi.org/10.1016/S1359-8368(01)00050-6
C.R. Farrar, K. Worden, An introduction to structural health monitoring. Philos. Trans. R. Soc. Lond. A: Mat. Phys. Eng. Sci. 365(1851), 303–315 (2007). https://doi.org/10.1098/rsta.2006.1928
S.A. Rahim, G. Manson, Kernel principal component analysis for structural health monitoring and damage detection of an engineering structure under operational loading variations. J. Fail. Anal. Prev. 21, 1981–1990 (2021). https://doi.org/10.1007/s11668-021-01260-1
A.R. Webb, K.D. Copsey, G. Cawley, Statistical Pattern Recognition, vol. 2. Wiley Online Library, The Atrium, Southern Gate, Chichester (2011). https://doi.org/10.1002/9781119952954
P. Jayaswal, A. Wadhwani, Application of artificial neural networks, fuzzy logic and wavelet transform in fault diagnosis via vibration signal analysis: A review. Aust. J. Mech. Eng. 7(2), 157–171 (2009). https://doi.org/10.1080/14484846.2009.11464588
Y. Lei, B. Yang, X. Jiang, F. Jia, N. Li, A.K. Nandi, Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech. Syst. Signal Process. 138, 106587 (2020). https://doi.org/10.1016/j.ymssp.2019.106587
O. Avci, O. Abdeljaber, S. Kiranyaz, M. Hussein, M. Gabbouj, D.J. Inman, A review of vibration-based damage detection in civil structures: from traditional methods to machine learning and deep learning applications. Mech. Syst. Signal Process. 147, 107077 (2021). https://doi.org/10.1016/j.ymssp.2020.107077
I.Y. Tumer, E.M. Huff, Principal components analysis of triaxial vibration data from helicopter transmissions, in 56th Meeting of the Society for Machinery Failure Prevention Technology (2001)
C. Kao, S.-L. Hung, Detection of structural damage via free vibration responses generated by approximating artificial neural networks. Comput. Struct. 81(28–29), 2631–2644 (2003). https://doi.org/10.1016/S0045-7949(03)00323-7
P. Jayaswal, S. Verma, Application of vibration signature analysis techniques for rolling element bearing fault identification. Aust. J. Mech. Eng. 8(1), 21–36 (2011). https://doi.org/10.1080/14484846.2011.11464592
O. Abdeljaber, O. Avci, S. Kiranyaz, M. Gabbouj, D.J. Inman, Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J. Sound Vib. 388, 154–170 (2017). https://doi.org/10.1016/j.jsv.2016.10.043
L.A. Pinedo-Sanchez, D.A. Mercado-Ravell, C.A. Carballo-Monsivais, Vibration analysis in bearings for failure prevention using CNN. J. Braz. Soc. Mech. Sci. Eng. 42(12), 1–17 (2020). https://doi.org/10.1007/s40430-020-02711-w
P.A. Reis, K.M. Iwasaki, L.R. Voltz, E.L. Cardoso, R.D. Medeiros, Damage detection of composite beams using vibration response and artificial neural networks. Proc. Inst. Mech. Eng. Part L: J. Mater.: Des. Appl. 236(7), 1419–1430 (2022)
J. Li, U. Dackermann, Y.-L. Xu, B. Samali, Damage identification in civil engineering structures utilizing PCA-compressed residual frequency response functions and neural network ensembles. Struct. Control Health Monit. 18(2), 207–226 (2011). https://doi.org/10.1002/stc.369
Y. Ni, X. Zhou, J. Ko, Experimental investigation of seismic damage identification using PCA-compressed frequency response functions and neural networks. J. Sound Vib. 290(1–2), 242–263 (2006). https://doi.org/10.1016/j.jsv.2005.03.016
B. Samali, U. Dackermann, J. Li, Location and severity identification of notch-type damage in a two-storey steel framed structure utilising frequency response functions and artificial neural network. Adv. Struct. Eng. 15(5), 743–757 (2012). https://doi.org/10.1260/1369-4332.15.5.74
R.P. Bandara, T.H. Chan, D.P. Thambiratnam, Frequency response function based damage identification using principal component analysis and pattern recognition technique. Eng. Struct. 66, 116–128 (2014). https://doi.org/10.1016/j.engstruct.2014.01.044
V.M. Nistane, Wavelet-based features for prognosis of degradation in rolling element bearing with non-linear autoregressive neural network. Aust. J. Mech. Eng. 19(4), 423–437 (2021). https://doi.org/10.1080/14484846.2019.1630949
G.F. Gomes, C.A. Diniz, S.S. Cunha, A.C. Ancelotti, Design optimization of composite prosthetic tubes using GA-ANN algorithm considering Tsai-Wu failure criteria. J. Fail. Anal. Prev. 17, 740–749 (2017). https://doi.org/10.1007/s11668-017-0304-5
C. Zang, M. Imregun, Structural damage detection using artificial neural networks and measured FRF data reduced via principal component projection. J. Sound Vib. 242(5), 813–827 (2001). https://doi.org/10.1006/jsvi.2000.3390
U. Dackermann, J. Li, B. Samali, Dynamic-based damage identification using neural network ensembles and damage index method. Adv. Struct. Eng. 13(6), 1001–1016 (2016). https://doi.org/10.1260/1369-4332.13.6.10
P. Selva, O. Cherrier, V. Budinger, F. Lachaud, J. Morlier, Smart monitoring of aeronautical composites plates based on electromechanical impedance measurements and artificial neural networks. Eng. Struct. 56, 794–804 (2013). https://doi.org/10.1016/j.engstruct.2013.05.025
P. Cawley, The impedance method of non-destructive inspection. NDT Int. 17(2), 59–65 (1984). https://doi.org/10.1016/0308-9126(84)90045-2
R.J. O’Brien, J.M. Fontana, N. Ponso, L. Molisani, A pattern recognition system based on acoustic signals for fault detection on composite materials. Eur. J. Mech.-A/Solids. 64, 1–10 (2017). https://doi.org/10.1016/j.euromechsol.2017.01.007
Z. Su, L. Ye, Quantitative damage prediction for composite laminates based on wave propagation and artificial neural networks. Struct. Health Monit. 4(1), 57–66 (2005). https://doi.org/10.1177/1475921705049747
R.P. Bandara, T.H. Chan, D.P. Thambiratnam, Structural damage detection method using frequency response functions. Struct. Health Monit. 13(4), 418–429 (2014). https://doi.org/10.1177/1475921714522847
D.B. Verstraete, E.L. Droguett, V. Meruane, M. Modarres, A. Ferrada, Deep semi-supervised generative adversarial fault diagnostics of rolling element bearings. Struct. Health Monit. 19(2), 390–411 (2020). https://doi.org/10.1177/1475921719850576
N. Zobeiry, J. Reiner, R. Vaziri, Theory-guided machine learning for damage characterization of composites. Compos. Struct. 246, 112407 (2020). https://doi.org/10.1016/j.compstruct.2020.112407
G. Puscasu, B. Codres, Nonlinear system identification and control based on modular neural networks. Int. J. Neural Syst. 21(04), 319–334 (2011). https://doi.org/10.1142/S0129065711002869
S.L.J. Ma, H. Hao, S. Jiang, Structural response recovery based on improved multi-scale principal component analysis considering sensor performance degradation. Adv. Struct. Eng. 21(2), 241–255 (2017). https://doi.org/10.1177/1369433217717114
K. Ghoulem, T. Kormi, N. Bel Hadj Ali, Damage detection in nonlinear civil structures using kernel principal component analysis. Adv. Struct. Eng. 23(11), 2414–2430 (2020). https://doi.org/10.1177/1369433220913207
V. Meruane, J. Mahu, Real-time structural damage assessment using artificial neural networks and antiresonant frequencies. Shock Vib. 2014, 1–14 (2010). https://doi.org/10.1155/2014/653279
J.C.S. Queiroz, Y.T.B. Santos, I.C. Silva, C.T.T. Farias, Damage detection in composite materials using tap test technique and neural networks. J. Nondestr. Eval. 40, 27 (2021). https://doi.org/10.1007/s10921-021-00759-9
M.J. Fogaça, E.L. Cardoso, R. Medeiros, Artificial neural networks to damage detection of composite materials, in Proceedings of the 26th International Congress of Mechanical Engineering (2021)
M.J. Fogaça, E.L. Cardoso, R. Medeiros, A systematic approach to find the hyperparameters of artificial neural networks applied to damage detection in composite materials. J. Braz. Soc. Mech. Sci. Eng. 45(9), 496 (2023). https://doi.org/10.1007/s40430-023-04371-y
I.H. Witten, E. Frank, M.A. Hall (ed.), Data Mining: Practical Machine Learning Tools and Techniques The Morgan Kaufmann Series in Data Management Systems, (Morgan Kaufmann, Boston, 2011), p.629. https://doi.org/10.1016/C2009-0-19715-5
C.M. Bishop, Neural Networks for Pattern Recognition. (Oxford University Press, Birmingham, 1995)
I.T. Jolliffe, J. Cadima, Principal component analysis: A review and recent developments. Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci. 374(2065), 20150202 (2016). https://doi.org/10.1098/rsta.2015.0202
Z. Jaade, A., step-by-step explanation of principal component analysis (pca). https://builtin.com/data-science/step-step-explanation-principal-component-analysis. Accessed 17 May 2022 (2021)
M.J. Powell, A view of algorithms for optimization without derivatives. Math. Today-Bull. Inst. Math. Appl. 43(5), 170–174 (2007)
R. Mohapatra, S. Saha, C.A.C. Coello, A. Bhattacharya, S.S. Dhavala, S. Saha, AdaSwarm: augmenting gradient-based optimizers in deep learning with swarm intelligence. IEEE Trans. Emerg. Top. Comput. Intell. (2020). https://doi.org/10.1109/TETCI.2021.3083428
A. Banks, J. Vincent, C. Anyakoha, A review of particle swarm optimization. Part I: background and development. Nat. Comput. 6, 467–484 (2007). https://doi.org/10.1007/s11047-007-9049-5
M.S. Innocente, J. Sienz, Coefficients’ settings in particle swarm optimization: insight and guidelines, in Computational Intelligence Techniques for Optimization and Data Modeling (B), vol. XXIX, pp. 9253–9269 (2010). https://doi.org/10.48550/arXiv.2101.11944
T. Varga, A. Király, J. Abonyi, Improvement of PSO algorithm by memory based gradient search—application in inventory management. IEEE Trans. Emerg. Top. Comput. Intell. (2020). https://doi.org/10.1016/B978-0-12-405163-8.00019-3
M. Malik, A. Arif, Ann prediction model for composite plates against low velocity impact loads using finite element analysis. Compos. Struct. 101, 290–300 (2013). https://doi.org/10.1016/j.compstruct.2013.02.020
C.M. Bishop, N.M. Nasrabadi, Pattern Recognition and Machine Learning, vol 4 (Springer, New York, 2006)
N. Qian, On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145–151 (1999). https://doi.org/10.1016/S0893-6080(98)00116-6
J. Revels, M. Lubin, T. Papamarkou, Forward-mode automatic differentiation in Julia. https://doi.org/10.48550/arXiv.1607.07892. arXiv:1607.07892 (2016)
O. Manzyuk, B.A. Pearlmutter, A.A. Radul, D.R. Rush, J.M. Siskind, Perturbation confusion in forward automatic differentiation of higher-order functions. J. Funct. Program. 29, 12 (2019). https://doi.org/10.1017/S095679681900008X
I.B.V. Silva, P.J. Adeodato, Pca and gaussian noise in MLP neural network training improve generalization in problems with small and unbalanced data sets, in The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 2664–2669 (IEEE, 2011). https://doi.org/10.1109/IJCNN.2011.6033567
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
S. Sengupta, S. Basak, R. Peters, Particle swarm optimization: a survey of historical and recent developments with hybridization perspectives. Mach. Learn. Knowl. Extr. 1(1), 157–191 (2018). https://doi.org/10.3390/make1010010
R. Mendes, P. Cortez, M. Rocha, J. Neves, Particle swarms for feedforward neural network training, in Proceedings of the 2002 International Joint Conference on Neural Networks, 2002. IJCNN’02, vol. 2, pp. 1895–1899 (IEEE, 2002)
L.R. Völtz, Fault diagnosis in composite structures using artificial neural network and principal component analysis. Master’s thesis, Santa Catarina State University - UDESC, Joinville, Santa Catarina, Brazil (2019)
J. Bezanson, A. Edelman, S. Karpinski, V.B. Shah, Julia: a fresh approach to numerical computing. SIAM Rev. 59(1), 65–98 (2017)
C.G. Looney, Advances in feedforward neural networks: demystifying knowledge acquiring black boxes. IEEE Trans. Knowl. Data Eng. 8(2), 211–226 (1996). https://doi.org/10.1109/69.494162
I. Silva, D.H. Spatti, R.A. Flauzino, Artificial Neural Networks for Engineering and Applied Sciences. (Artliber, São Paulo, 2010) (in Portuguese)
M.S. Pereira, E.M. Bezerra, Utilization of neural networks in prediction of aeronautical compounds behaviour under shearing, in Meeting of Cientific Iniciation and Post-graduate Program of ITA, São José dos Campos (2007) (in Portuguese)
R. De Medeiros, D. Vandepitte, V. Tita, Structural health monitoring for impact damaged composite: a new methodology based on a combination of techniques. Struct. Health Monit. 17(2), 185–200 (2018). https://doi.org/10.1177/147592171668844
S.D. Sharma, Performance evaluation of the signal processing based transfer learning algorithm for the fault classification at different datasets. J. Fail. Anal. Prev. (2023). https://doi.org/10.1007/s11668-023-01648-1
P. Gangsar, R. Tiwari, Multiclass fault taxonomy in rolling bearings at interpolated and extrapolated speeds based on time domain vibration data by svm algorithms. J. Fail. Anal. Prev. 14, 826–837 (2014). https://doi.org/10.1007/s11668-014-9893-4
Funding
The authors acknowledge the financial support of the Santa Catarina State Research and Innovation Funding Agency, Brazil (FAPESC process number: 2017TR1747, 2021TR843, 48/2021, 2023TR563), Coordination for the Improvement of the Higher Level Personnel, Brazil (CAPES Finance Code 001), and PROMOP (Programa de Bolsas de Monitoria de Pós-Graduação) of the Santa Catarina State University, Brazil. Ricardo De Medeiros acknowledges the financial support of the National Council for Scientific and Technological Development (CNPq process number: 304795/2022-4). Eduardo Lenz Cardoso acknowledges the financial support of the National Council for Scientific and Technological Development, Brazil (CNPq process number: 303900/2020-2). The authors would like to thank Navy Technological Centre (CTM - Brazil) for manufacturing the composite plates specimens. The authors would like to thank Julio Zago and Guilherme Zago for the data acquisition for the rolling bearings.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Rosenstock Völtz, L., Janczkowski Fogaça, M., Lenz Cardoso, E. et al. Optimising Hyperparameters of Artificial Neural Network Topology for SHM Damage Detection and Identification. J Fail. Anal. and Preven. 24, 955–975 (2024). https://doi.org/10.1007/s11668-024-01888-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11668-024-01888-9