Artificial Intelligence Review

, Volume 46, Issue 3, pp 289–305 | Cite as

Signal processing and Gaussian neural networks for the edge and damage detection in immersed metal plate-like structures

  • Y. Sidibe
  • F. Druaux
  • D. Lefebvre
  • G. Maze
  • F. Léon


The present study concerns the remote monitoring of immersed plate-like structures as the ones used for marine current turbines. The innovation of this work is the remote damage detection based on a systematic analysis of a small set of ultrasonic measurements limited by the backscattered echoes from the structure edges. The detection and localization are performed by combination of signal processing tools as Hilbert transform, principal component analysis, and thresholding methods and artificial intelligence tools as Gaussian neural networks. The edges of the structure are detected with a Gaussian neural network classifier, and the useful ranges of the measurements are extracted. These ranges are compared with reference signals in order to compute residuals. Finally damage detection is obtained from the magnitude of the residuals. In addition, some geometric parameters such as the incidence angle, the distance between the structure and the emission–reception device, and eventually the damage localization are estimated. The proposed method is validated with laboratory experimental measurements, and the performance is discussed with respect to some significant parameters.


Gaussian neural networks Classification Signal processing Damage detection and localization Acoustic signal 


  1. Attarian V, Cegla F, Cawley P (2012) Long term stability analysis of a guide wave SHM system for plate-like structures. In: 38th annual review of progress in quantitative nondestructive evaluation (QNDE), pp 655–662Google Scholar
  2. Banerjee S, Kundu T (2007) Ultrasonic field modeling in plates immersed in fluid. Int J Solids Struct 44(18–19):6013–6029zbMATHCrossRefGoogle Scholar
  3. Barakat M, Druaux F, Lefebvre D, Khalil M, Mustapha O (2011) Self-adaptive growing neural network classifier for faults detection and diagnosis. Neuro Comput 74(18):3865–3876Google Scholar
  4. Barakat M, Lefebvre D, Khalil M, Druaux F, Mustapha M (2013) Parameter selection algorithm with self adaptive growing neural network classifier for diagnosis issues. Int J Mach Learn Cyber (JMLC) 4:217–233CrossRefGoogle Scholar
  5. Chen JH, Liao CM (2002) Dynamic process fault monitoring based on neural network and PCA. J Process Control 12:277–289CrossRefGoogle Scholar
  6. Ding ZC, Cao MS, Jia HL, Pan LX (2014) Structural dynamics-guided hierarchical neural-networks scheme for locating and quantifying damage in beam-type structures. J Vibro Eng 16(7):3595–3608Google Scholar
  7. Firestone FA, Ling DS (1945) Propagation of waves in plates. Technical report, Sperry products, Danbury, CT, USAGoogle Scholar
  8. Firestone FA, Ling DS (1954) Method and means for generating and utilizing vibration waves in plates, USAGoogle Scholar
  9. Greve DW, Hoon S, Yue CP, Oppenheim IJ (2007) An inductively coupled lamb wave transducer. Sens J IEEE 7(2):295–301CrossRefGoogle Scholar
  10. Harkat MF, Mourot G, Ragot J (2006) An improved PCA scheme for sensor FDI: application to an air quality monitoring net work. J Process Control 16:625–634CrossRefGoogle Scholar
  11. Heckman A, Rovey JL, Chandrashekhara K, Watkins SE, Stutts DS, Banerjee A, Mishra RS (2013) Structural health monitoring data transmission for composite hydrokinetic turbine blades. Adv Shipp Ocean Eng 2(2):50–59Google Scholar
  12. Hoon S, Seuno BK (2010) Development of dual PZT transducers for reference-free crack detection in thin plate structures. IEEE Trans Ultrason Ferroelectr Freq Control 57(1):229–240CrossRefGoogle Scholar
  13. Hui J, Wan XP, Zhao MY (2011) Composite skin/stringer panel damage detection based on modal strain energy and neural network technique. Appl Mech Mater 66–68:322–327CrossRefGoogle Scholar
  14. Hung SL, Kao CY (2002) Structural damage detection using the optimal weights of the approximating artificial neural networks. Earthq Eng Struct Dyn 31(2):217–234CrossRefGoogle Scholar
  15. Kourd Y, Lefebvre D, Guersi N (2013) Fault diagnosis based on neural networks and decision trees: application to DAMADICS. Int J Innov Comput Inf Control 9(8):3185–3196Google Scholar
  16. Lamb H (1917) On waves in an elastic plate. Proc R Soc A Math Phys Eng Sci 93:114–128zbMATHCrossRefGoogle Scholar
  17. Lee JJ, Lee JW, Yi JH (2005) Neural networks-based damage detection for bridges considering errors in baseline finite element models. J Sound Vib 280(3–5):555–578CrossRefGoogle Scholar
  18. Lee BC, Staszewski WJ (2007) Lamb wave propagation modelling for damage detection: damage monitoring strategy. Smart Mater Struct 16:260–274CrossRefGoogle Scholar
  19. Maze G, Leon F, Farid C, Decultot D, Sidibe Y, Druaux F, Lefebvre D (2014) Detection of a straight groove in a metal plate by acoustic scattering in water with applications to marine current turbines. NDT & E Int 65:47–53CrossRefGoogle Scholar
  20. Patton RJ, Lopez-Toribio CJ, Uppal FJ (1999) Artificial intelligence approaches to fault diagnosis for dynamic systems. Int J Appl Math Comput Sci 9(3):471–518zbMATHGoogle Scholar
  21. Pistone E, Bagheri A, Rizzo P (2007) Signal processing for the smart inspection of underwater plates. In: Proceedings of SMART2013. Torino, ItalyGoogle Scholar
  22. Sharma S, Mukherjee A (2014) Damage detection in submerged plates using ultrasonic guided waves. Sadhana 39(5):1009–1034CrossRefGoogle Scholar
  23. Sharma S, Mukherjee A (2015) Ultrasonic guided waves for monitoring corrosion in submerged plates. Struct Control Health Monit 22(1):19–35Google Scholar
  24. Shelke A, Kundu T, Amjad U, Hahn K, Grill W (2011) Mode-selective excitation and detection of ultrasonic guided waves for delamination detection in laminated aluminum plates. IEEE Trans Ultrason Ferroelectr Freq Control 58(3):567–577CrossRefGoogle Scholar
  25. Shu J, Zhang Z, Gonzalez I (2013) The application of a damage detection method using artificial neural network and train-induced vibrations on a simplified railway bridge model. Eng Struct 52:408–421CrossRefGoogle Scholar
  26. Sidibé Y, Lefebvre D, Druaux F, Leon F, Maze G (2013) Active fault diagnosis for immersed structure. IEEE-CODIT, Hammamet, TunisieCrossRefGoogle Scholar
  27. Singh AP, Kamal TS, Kumar S (2005) Development of ANN-based virtual fault detector for Wheatstone bridge-oriented transducers. IEEE Sens J 5(5):1043–1049CrossRefGoogle Scholar
  28. Su ZQ, Ye L (2009) Identification of damage using Lamb waves. Springer, BerlinzbMATHCrossRefGoogle Scholar
  29. Tharrault Y, Mourot G, Ragot J (2008) Fault detection and isolation with robust principal component analysis. In: Proceedings of IEEE MED, Ajaccio, FranceGoogle Scholar
  30. Uppal FJ, Patton RJ, Witczak M (2006) A neuro-fuzzy multiple-model observer approach to robust fault diagnosis based on the DAMADICS benchmark problem. Control Eng Pract 14:699–717CrossRefGoogle Scholar
  31. Vafaei M, Bin A, Azlan A, Ahmad B (2013) Real-time seismic damage detection of concrete shear walls using artificial neural networks. J Earthq Eng 17(1):137–154CrossRefGoogle Scholar
  32. Yam LH, Yan YJ, Jiang JS (2003) Vibration-based damage detection for composite structures using wavelet transform and neural network identification. Compos Struct 60(4):403–412CrossRefGoogle Scholar
  33. Zhang Y, Sidibé Y, Maze G, Leon F, Druaux F, Lefebvre D (2016) Detection of damages in underwater metal plate using acoustic inverse scattering and image processing methods. Appl Acoust 103:110–121CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2016

Authors and Affiliations

  • Y. Sidibe
    • 1
  • F. Druaux
    • 1
  • D. Lefebvre
    • 1
  • G. Maze
    • 2
  • F. Léon
    • 2
  1. 1.Groupe de Recherche en Electronique et Automatique du Havre, GREAHNormandie Université, Université Le HavreLe HavreFrance
  2. 2.Laboratoire Ondes et Milieux Complexes, LOMC UMR CNRS 6294Normandie Université, Université Le HavreLe HavreFrance

Personalised recommendations