Comparison of machine learning methods for crack localization. (English) Zbl 1431.74065
Summary: In this paper, the Haar wavelet discrete transform, the artificial neural networks (ANNs), and the random forests (RFs) are applied to predict the location and severity of a crack in an Euler-Bernoulli cantilever subjected to the transverse free vibration. An extensive investigation into two data collection sets and machine learning methods showed that the depth of a crack is more difficult to predict than its location. The data set of eight natural frequency parameters produces more accurate predictions on the crack depth; meanwhile, the data set of eight Haar wavelet coefficients produces more precise predictions on the crack location. Furthermore, the analysis of the results showed that the ensemble of 50 ANN trained by Bayesian regularization and Levenberg-Marquardt algorithms slightly outperforms RF.
MSC:
| 74K10 | Rods (beams, columns, shafts, arches, rings, etc.) |
| 65T60 | Numerical methods for wavelets |
| 68T05 | Learning and adaptive systems in artificial intelligence |
| 74H45 | Vibrations in dynamical problems in solid mechanics |
Keywords:
Euler-Bernoulli beam; free vibration; cracks; Haar wavelet; backpropagation network; random forestReferences:
| [1] | M. Attar, A transfer matrix method for free vibration analysis and crack identification of stepped beams with multiple edge cracks and different boundary conditions, Internat. J. Mech. Sci 57(1) (2012), 19-33. |
| [2] | M. H. Beale, M. T. Hagan, and H. B. Demuth, Neural Network ToolboxTM User’s Guide, in: The MathWorks, Inc., Massachusetts, 2016, pp. 131, 914. |
| [3] | L. Breiman, Random forests, Machine Learning 45(1) (2001), 5-32. · Zbl 1007.68152 |
| [4] | S. Caddemi and I. Cali‘o, Exact solution of the multi-cracked Euler-Bernoulli column, Internat. J. Solids Structures 45(5) (2008), 1332-1351. · Zbl 1169.74457 |
| [5] | S. Caddemi and A. Morassi, Multi-cracked Euler-Bernoulli beams: Mathematical modeling and exact solutions, Internat. J. Solids Structures 50(6) (2013), 944-956. |
| [6] | A. D. Dimarogonas, S. A. Paipetis, and T. G. Chondros, Analytical Methods in Rotor Dynamics, Elsevier Applied Science, 1986. · Zbl 1283.74002 |
| [7] | U. Eroglu and E. Tufekci, Exact solution based finite element formulation of cracked beams for crack detection, Internat. J. Solids Structures 96 (2016), 240-253. |
| [8] | F. A. Farret, M. Simoes, and D. Brandao, Electronic Instrumentation for Distributed Generation and Power Processes, CRC Press, Boca Raton FL, 2017. |
| [9] | L. J. Hadjileontiadis, E. Douka, and A. Trochidis, Fractal dimension analysis for crack identification in beam structures, Mech. Syst. Signal Process. 19(3) (2005), 659-674. |
| [10] | S. J. S. Hakim, A. H. Razak, and S. A. Ravanfar, Fault diagnosis on beam-like structures from modal parameters using artificial neural networks, Measurement: Journal of the International Measurement Confederation. 76 (2015), 45-61. |
| [11] | Y. He, D. Guo, and F. Chu, Using genetic algorithms and finite element methods to detect shaft crack for rotor-bearing system, Math. Comp. Simulation 57(1-2) (2001), 95-108. · Zbl 1079.74638 |
| [12] | P. Konar and P. Chattopadhyay, Bearing fault detection of induction motor using wavelet and support vector machines (SVMs), Appl. Soft Comput. 11(6) (2011), 4203- 4211. |
| [13] | M. A. Mahmoud and M. A. A. Kiefa, Neural network solution of the inverse vibration problem, NDT & Internat. 32(2) (1999), 91-99. |
| [14] | J. Majak, M. Pohlak, K. Karjust, M. Eerme, J. Kurnitski, and B. S. Shvartsman, New higher order Haar wavelet method: Application to FGM structures, Compos. Structures 201 (2018), 72-78. |
| [15] | B. P. Nandwana and S. K. Maiti, Modelling of vibration of beam in presence of inclined edge or internal crack for its possible detection based on frequency measurements, Engrg. Fracture Mech. 58(3) (1997), 193-205. |
| [16] | N. Papaeconomou and A. Dimarogonas, Vibration of cracked beams, Comput. Mech. 5(2) (1989), 88-94. · Zbl 0695.73020 |
| [17] | P. F. Rizos, N. Aspragathos, and A. D. Dimarogonas, Identification of crack location and magnitude in a cantilever beam from the vibration modes, J. Sound Vibration 138(3) (1990), 381-388. |
| [18] | M. B. Rosales, C. P. Filipich, and F. S. Buezas, Crack detection in beam-like structures, Engrg. Structures 31(10) (2009), 2257-2264. |
| [19] | M. Rucka and K. Wilde, Application of continuous wavelet transform in vibration based damage detection method for beams and plates, J. Sound Vibration 297(3) (2006), 536-550. |
| [20] | M. Rucka and K. Wilde, Crack identification using wavelets on experimental static deflection profiles, Engrg. Structures 28(2) (2006), 279-288. |
| [21] | M. K. Sutar, S. Pattnaik, and J. Rana, Neural based controller for smart detection of crack in cracked cantilever beam, in: 4th International Conference on Materials Processing and Characterzation 2(4-5) (2015), pp. 2648-2653. |
| [22] | J. M. Twomey and A. E. Smith, Performance measures, consistency, and power for artificial neural network models, Math. Comput. Modelling 21(1) (1995), 243-258. |
| [23] | K. Worden, W. J. Staszewski, and J. J. Hensman, Natural computing for mechanical systems research: A tutorial overview, Mech. Systems Signal Process. 25(1) (2011), 4-111. |
| [24] | Y. J. Yan, L. Cheng, Z. Y. Wu, and L. H. Yam, Development in vibration-based structural damage detection technique, Mech. Systems Signal Process. 21(5) (2007), 2198- 2211. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
