Steel and Composite Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Crack detection in folded plates with back-propagated artificial neural network

  • Oguzhan Das (National Defence University, Air NCO Higher Vocational School, Department of Aeronautics Sciences) ;
  • Can Gonenli (Ege University, Department of Machine Drawing and Construction) ;
  • Duygu Bagci Das (Ege University, Department of Computer Programming)
  • Received : 2021.10.28
  • Accepted : 2023.01.19
  • Published : 2023.02.10
⟨ Previous Next ⟩

Abstract

Localizing damages is an essential task to monitor the health of the structures since they may not be able to operate anymore. Among the damage detection techniques, non-destructive methods are considerably more preferred than destructive methods since damage can be located without affecting the structural integrity. However, these methods have several drawbacks in terms of detecting abilities, time consumption, cost, and hardware or software requirements. Employing artificial intelligence techniques could overcome such issues and could provide a powerful damage detection model if the technique is utilized correctly. In this study, the crack localization in flat and folded plate structures has been conducted by employing a Backpropagated Artificial Neural Network (BPANN). For this purpose, cracks with 18 different dimensions in thin, flat, and folded structures having 150, 300, 450, and 600 folding angle have been modeled and subjected to free vibration analysis by employing the Classical Plate Theory with Finite Element Method. A Four-nodded quadrilateral element having six degrees of freedom has been considered to represent those structures mathematically. The first ten natural frequencies have been obtained regarding healthy and cracked structures. To localize the crack, the ratios of the frequencies of the cracked flat and folded structures to those of healthy ones have been taken into account. Those ratios have been given to BPANN as the input variables, while the crack locations have been considered as the output variables. A total of 500 crack locations have been regarded within the dataset obtained from the results of the free vibration analysis. To build the best intelligent model, a feature search has been conducted for BAPNN regarding activation function, the number of hidden layers, and the number of hidden neurons. Regarding the analysis results, it is concluded that the BPANN is able to localize the cracks with an average accuracy of 95.12%.

Keywords

References

  1. Alexandrino, P.S.L., Gomes, G.F. and Cunha, S.S. (2019), "A robust optimization for damage detection using multiobjective genetic algorithm, neural network and fuzzy decision making", Inverse Prob. Sci. Eng., 28(1), 21-46. https://doi.org/10.1080/17415977.2019.1583225.
  2. Alfano, M. and Pagnotta, L. (2005), Computational Methods and Experimental Measurements, Xii. WIT Press.
  3. Altunisik, A.C., Okur, F.Y. and Kahya, V. (2017), "Automated model updating of multiple cracked cantilever beams for damage detection", J. Construct. Steel Res., 138, 499-512. https://doi.org/10.1016/j.jcsr.2017.08.006
  4. An, H., Youn, B.D. and Kim, H.S. (2022), "A methodology for sensor number and placement optimization for vibration-based damage detection of composite structures under model uncertainty", Compos. Struct., 279, 114863. https://doi.org/10.1016/j.compstruct.2021.114863.
  5. Anysz, H., Zbiciak, A. and Ibadov, N. (2016), "The influence of input data standardization method on prediction accuracy of Artificial Neural Networks", Procedia Eng., 153, 66-70. https://doi.org/10.1016/j.proeng.2016.08.081.
  6. Cancelli, A., Laflamme, S., Alipour, A., Sritharan, S. and Ubertini, F. (2019), "Vibration-based damage localization and quantification in a pretensioned concrete girder using stochastic subspace identification and particle swarm model updating", Struct. Health Monit., 19(2), 587-605. https://doi.org/10.1177/1475921718820015.
  7. Chen, H.G., Yan, Y.J. and Jiang, J.S. (2007), "Vibration-based damage detection in composite wingbox structures by hht", Mech. Syst. Sig. Processing, 21(1), 307-321. https://doi.org/10.1016/j.ymssp.2006.03.013.
  8. Elshafey, A.A., Haddara, M.R. and Marzouk, H. (2010), "Damage detection in offshore structures using neural networks", Marine Struct., 23(1), 131-145. https://doi.org/10.1016/j.marstruc.2010.01.005.
  9. Elshamy, M., Crosby, W.A. and Elhadary, M. (2018), "Crack detection of cantilever beam by natural frequency tracking using experimental and finite element analysis", Alexandria Eng. J., 57(4), 3755-3766. https://doi.org/10.1016/j.aej.2018.10.002.
  10. Gillich, G., Furdui, H., Abdel Wahab, M. and Korka, Z. (2019), "A robust damage detection method based on multi-modal analysis in variable temperature conditions", Mech. Syst. Sig. Processing, 115, 361-379. https://doi.org/10.1016/j.ymssp.2018.05.037.
  11. Gonenli, C. and Das, O. (2021), "Effect of crack location on buckling and dynamic stability in plate frame structures", J. Brazil. Soc. Mech. Sci. Eng., 43(6). https://doi.org/10.1007/s40430-021-03032-2.
  12. Guha Niyogi, A., Laha, M.K., & Sinha, P.K. (1999), "Finite element vibration analysis of laminated composite folded plate structures", Shock Vib., 6(5-6), 273-283. https://doi.org/10.1155/1999/354234.
  13. Guo, X., Zhang, Y., Zhang, W. and Sun, L. (2019), "Theoretical and experimental investigation on the nonlinear vibration behavior of Z-shaped folded plates with inner resonance", Eng. Struct., 182. https://doi.org/10.1016/j.engstruct.2018.12.066.
  14. Hassaine Daouadji, T., Rabahi, A. and Benferhat, R. (2021), "A new model for adhesive shear stress in damaged RC cantilever beam strengthened by composite plate taking into account the effect of creep and shrinkage", Struct. Eng. Mech., 79(5), 531-540. https://doi.org/10.12989/sem.2021.79.5.531.
  15. Jayasundara, N., Thambiratnam, D., Chan, T. and Nguyen, A. (2020), "Damage detection and quantification in deck type arch bridges using vibration based methods and artificial neural networks", Eng. Fail. Anal., 109, 104265. https://doi.org/10.1016/j.engfailanal.2019.104265.
  16. Kourehli, S.S. (2017), "Application of extreme learning machine to damage detection of plate-like structures", Int. J. Struct. Stab. Dyn., 17(07), 1750068. https://doi.org/10.1142/s0219455417500687.
  17. Leissa, A.W. (1969), Vibration of Plates, Office of Technology Utilization, NASA, Washington DC.
  18. Li, R., Wang, P., Yang, Z., Yang, J. and Tong, L. (2018), "On new analytic free vibration solutions of rectangular thin cantilever plates in the symplectic space", Appl. Mathem. Modelling, 53, 310-318. https://doi.org/10.1016/j.apm.2017.09.011.
  19. Manoach, E. and Trendafilova, I. (2008), "Large amplitude vibrations and damage detection of rectangular plates", J. Sound Vib., 315(3), 591-606. https://doi.org/10.1016/j.jsv.2008.02.016.
  20. Minsky, M., Papert, S. and Bottou, L. (2017), Perceptrons: An Introduction to Computational Geometry, The MIT Press Cambridge, Massachusetts, USA.
  21. Mohammadi, H. and Setoodeh, A.R. (2020), "FSDT-based isogeometric analysis for free vibration behavior of functionally graded skew folded plates", Iran. J. Sci. Technol. Transact. Mech. Eng., 44, 841-863. https://doi.org/10.1007/s40997-019-00320-0.
  22. Nasiri, M.R., Mahjoob, M.J. and Aghakasiri, A. (2011), "Damage detection in a composite plate using modal analysis and artificial intelligence", Appl. Compos. Mater., 18(6), 51-?520. https://doi.org/10.1007/s10443-011-9231-x.
  23. Oliver, G.A., Ancelotti, A.C. and Gomes, G.F. (2020), "Neural network-based damage identification in composite laminated plates using frequency shifts", Neural Comput. Appl., 33(8), 3183-3194. https://doi.org/10.1007/s00521-020-05180-3.
  24. Padil, K.H., Bakhary, N., Abdulkareem, M., Li, J. and Hao, H. (2020), "Non-probabilistic method to consider uncertainties in frequency response function for vibration-based damage detection using artificial neural network", J. Sound Vib., 467, 115069. https://doi.org/10.1016/j.jsv.2019.115069.
  25. Pan, J., Zhang, Z., Wu, J., Ramakrishnan, K.R. and Singh, H.K. (2019), "A novel method of vibration modes selection for improving accuracy of frequency-based damage detection", Compos. Part B: Eng., 159, 437-446. https://doi.org/10.1016/j.compositesb.2018.08.134.
  26. Paulraj, M.P., Majid, M.S., Yaacob, S., Rahiman, M.H. and Krishnan, R.P. (2009), "Statistical time energy based damage detection in steel plates using artificial neural networks", 2009 5th International Colloquium on Signal Processing & Its Applications, Kuala Lumpur, Malaysia, March. https://doi.org/10.1109/cspa.2009.5069182
  27. Paulraj, M.P., Mohd Shukry, A.M., Yaacob, S., Adom, A.H. and Krishnan, R.P. (2010), "Structural steel plate damage detection using dft spectral energy and artificial neural network", 2010 6th International Colloquium on Signal Processing & Its Applications, Malacca, Malaysia, May. https://doi.org/10.1109/cspa.2010.5545247.
  28. Paulraj, M.P., Yaacob, S., Majid, M.S.A., Kazim, M.N. and Krishnan, P. (2013), "Structural steel plate damage detection using non destructive testing, frame energy based statistical features and artificial neural networks", Procedia Engineering, 53, 376-386. https://doi.org/10.1016/j.proeng.2013.02.049.
  29. Pereira, S., Magalhaes, F., Gomes, J.P., Cunha, A. And Lemos, J.V. (2021), "Vibration-based damage detection of a concrete arch dam", Eng. Struct., 235, 112032. https://doi.org/10.1016/j.engstruct.2021.112032.
  30. Petyt, M. (2015), Introduction to Finite Element Vibration Analysis, Cambridge University Press, New York, USA.
  31. Prawin, J. (2021), "Real-time reference-free breathing crack identification using ambient vibration data", Struct. Control Health Monit., 29(3), e2903. https://doi.org/10.1002/stc.2903.
  32. Sadamoto, S., Ozdemir, M., Tanaka, S., Bui, T.Q. and Okazawa, S. (2019), "Finite rotation meshfree formulation for geometrically nonlinear analysis of flat, curved and folded shells", Int. J. NonLinear Mech., 119, 103300 https://doi.org/10.1016/j.ijnonlinmec.2019.103300
  33. Shanker, M., Hu, M.Y. and Hung, M.S. (1996), "Effect of data standardization on neural network training", Omega, 24(4), 385-397. https://doi.org/10.1016/0305-0483(96)00010-2.
  34. Shih, H.W., Thambiratnam, D.P. and Chan, T.H.T. (2009), "Vibration based structural damage detection in flexural members using multi-criteria approach", J. Sound Vib., 323(3-5), 645-661. https://doi.org/10.1016/j.jsv.2009.01.019.
  35. Tan, Z.X., Thambiratnam, D.P., Chan, T.H., Gordan, M. and Abdul Razak, H. (2020), "Damage detection in steel-concrete composite bridge using vibration characteristics and artificial neural network", Struct. Infrastruct. Eng., 16(9), 1247-1261. https://doi.org/10.1080/15732479.2019.1696378.
  36. Tanaka, S., Dai, M.J., Sadamoto, S., Yu, T.T. and Bui, T.K. (2019), "Stress resultant intensity factors evaluation of cracked folded structures by 6DOFs flat shell meshfree modeling", Thin-Wall. Struct., 144, 106285. https://doi.org/10.1016/j.tws.2019.106285.
  37. Thakur, B.R., Verma, S., Singh, B.N. and Maiti, D.K. (2020), "Dynamic analysis of folded laminated composite plate using nonpolynomial shear deformation theory", Aeros. Sci. Technol., 106, 106083. https://doi.org/10.1016/j.ast.2020.106083.
  38. Tsou, P. and Shen, M.H.H. (1994), "Structural damage detection and identification using neural networks", AIAA J., 32(1), 176-183. https://doi.org/10.2514/3.11964.
  39. Xu, B. and Xia, H. (2018), "Effect of damage on natural vibration characteristics of large semi-cushion spiral case structure", Arab. J. Sci. Eng., 44, 4063-4074. https://doi.org/10.1007/s13369-018-3251-x.
  40. Yam, L.H., Yan, Y.J. and Wei, Z. (2004), "Vibration-based non destructive structural damage detection", Key Eng. Mater., 270-273, 1446-1453. https://doi.org/10.4028/www.scientific.net/kem.270-273.1446.
  41. Yeung, W.T. and Smith, J.W. (2005), "Damage detection in bridges using neural networks for pattern recognition of vibration signatures", Eng. Struct., 27(5), 685-698. https://doi.org/10.1016/j.engstruct.2004.12.006.
  42. Zhang, Y., Luo, Y., Guo, X. and Li, Y. (2022), "A new damage detection method of single-layer latticed shells based on combined modal strain energy index", Mech. Syst. Sig. Processing, 172, 109011. https://doi.org/10.1016/j.ymssp.2022.109011.