Neural network technology for identifying defect sizes in half-plane based on time and positional scanning

Introduction. The selected research topic urgency is due to the need for a quick assessment of the condition and reliability of materials used in various designs. The work objective was to study parameters of the influence of the defect on the response of the surface of the medium to the shock effect. The solution to the inverse problem of restoring the radius of a defect is based on the combination of a computational approach and the use of artificial neural networks (ANN). The authors have developed a technique for restoring the parameters of a defect based on the computational modeling and ANN.

Materials and Methods. The problem is solved in the flat setting through the finite element method (FEM). In this paper, we used the linear equations of the elasticity theory with allowance for energy dissipation. The finite element method implemented in the ANSYS package was used as a method for solving the boundary value problem. MATLAB complex was used as a simulation of the application process (ANN). Results. A finite element model of a layered structure has been developed in a flat formulation of the problem in the ANSYS package. The problem of determining unsteady vibrations under pulsed loading for different radius variations of the defect is solved. Positional scanning of the research object is applied. Graphical dependences of the vibration amplitudes of points on the surface on the defect radius are plotted.

Discussion and Conclusions. As a result of studying the dependences of vibration responses on the defect radius, the authors have developed an approach to restore this parameter in a flat structure based on a combination of the FEM and ANN. The research has shown that the amount of data used is sufficient for successful training of the constructed ANN model and identification of a hidden defect in the structure.

1. Неразрушающие методы контроля / под ред. В. Я. Кершенбаума. — Москва : Наука и техника. — 1992. — 656 с.

2. Белокур, И. П. Дефектология и неразрушающий контроль / И. П. Белокур. — Киев : Выща школа. — 1990. — 208 с.

3. Интегральный диагностический признак идентификации повреждений в элементах стержневых конструкций / В. А. Акопьян, А. В. Черпаков, Е. В. Рожков, А. Н. Соловьев // Контроль. Диагностика. — 2012. — № 7. — С. 50–56.

4. Капцов, А. В. Определение параметров плоской эллиптической трещины в изотропном линейно упругом теле по результатам одного испытания на одноосное растяжение / А. В. Капцов, Е. И. Шифрин, П. С. Шушпанников // Известия Российской академии наук. Механика твердого тела. — 2012. — № 4. — С. 71– 88.

5. Sedov, A. V. Adaptive-spectral method of monitoring and diagnostic observability of static stresses of elements of mechanical constructions / A. V. Sedov, V. V. Kalinchuk, O. V. Bocharova // IOP Conference Series: Earth and Environmental Science. — 2017. — 87(8). — P. 082043.

6. Соловьев, А. Н. Ультразвуковая локация внутренних трещи ноподобных дефектов в составном упругом цилиндре с применением аппарата искусственных нейронных сетей / А. Н. Соловьев, Б. В. Соболь, П. В. Васильев // Дефектоскопия. — 2016. — Т. 52, № 3. — С. 3–9.

7. Xia, J. Estimation of near-surface shear-wave velocity by inversion of Rayleigh waves / J. Xia, R. D. Miller, C. B. Park // Geophysics. — 1999. — Vol. 64, no. 3. — P. 691–700.

8. Esipov, Y. V. Criteria for identification of stress state of periodic rod construction based on ferroelectric sensors of deformation / Y. V. Esipov, V. M. Mukhortov, I. I. Pojda // Piezoelectrics and Related Materials: Investigations and Applications. — 2012. — P. 283−291.

9. Evtushenko, S. I. Identification of soils, grounds and lands strata using the acoustic spectral analysis / S. I. Evtushenko, V. A. Lepikhova, N. V. Lyashenko [et al.] // IOP Conf. Series: Materials Science and Engineering. — 2020. — Vol. 913. — P. 052043. DOI:10.1088/1757-899X/913/5/052043

10. Ильгамов, М. А. Диагностика повреждений балки на шарнирных опорах / М. А. Ильгамов, А. Г. Хакимов // Строительная механика инженерных конструкций и сооружений. — 2010. — № 2. — С. 42–48.

11. Park, C. B. Combined use of active and passive surface waves / C.B. Park, R.D. Miller, N. Ryden [et al.] // Journal of Environmental & Engineering Geophysics. — 2005. — Vol. 10, no. 3. — P. 323−334.

12. Brigante, M. Acoustic Methods for the Nondestructive Testing of Concrete: A Review of Foreign Publications in the Experimental Field / M. Brigante, M. A. Sumbatyan // Russian Journal of Nondestructive Testing. — 2013. — Vol. 49, no. 2. — P. 100–111.

13. Park, C. B. Roadside passive multichannel analysis of surface waves (MASW) / C. B. Park, R. D. Miller // Journal of Environmental & Engineering Geophysics. — 2008. — Vol. 13, no. 1. — P. 1–11.

14. Lyapin, A. A. Improving Road Pavement Characteristics / A. A. Lyapin, I. A. Parinov, N. I. Buravchuk [et al.] // Springer, Cham. — 2020. — 254 p. DOI: 10.1007/978-3-030-59230-1

15. Haykin, S. Neural Networks: a comprehensive foundation / S. Haykin. — 2nd ed. — Prentice Hall. — 1998. — 842 p.

16. Krasnoshchekov, A. A. Identification of crack-like defects in elastic structural elements on the basis of evolution algorithms / A. A. Krasnoshchekov, B. V. Sobol, A. N. Solov'ev [et al.] // Russian Journal of Nondestructive Testing. — 2011. — 47(6). — 412−419.

17. Waszczyszyn, Z. Neural networks in mechanics of structures and materials – new results and prospects of applications / Z. Waszczyszyn, L. Ziemianski // Computers and Structures.— 2001. — Vol. 79, iss. 22−25. — P. 2261−2276.

18. Зиновьев, А. Ю. Визуализация многомерных данных / А. Ю. Зиновьев. — Красноярск : Изд-во Красноярского государственного технического университета. — 2000. — 180 c.

19. Liu, S.W. Detection of cracks using neural networks and computational mechanics / S.W. Liu, J.H. Huang, J.C. Sung [et al.] // Computer Methods in Applied Mechanics and Engineering. — 2002. — Vol. 191, iss. 25−26. — P. 2831−2845. DOI: 10.1016/S0045-7825(02)00221-9

20. Khandetsky, V. Signal processing in defect detection using back-propagation neural networks / V. Khandetsky, I. Antonyuk // NDT&E International. — 2002. — Vol. 35, iss. 7. — P. 483−488.

21. Xu, Y.G. Adaptive multilayer perceptron networks for detection of cracks in anisotropic laminated plates / Y.G. Xu [et al.] // International Journal of Solids and Structures. — 2001. — Vol. 38. — P. 5625−5645.

22. Fang, X. Structural damage detection using neural network with learning rate improvement / X. Fang, H. Luo, J. Tang // Computers and Structures. — 2005.  Vol. 83. — P. 2150–2161.

23. Hernandez-Gomez, L. H. Locating defects using dynamic strain analysis and artificial neural networks / L. H. Hernandez-Gomez, J. F. Durodola, N. A. Fellows [et al.] // Applied Mechanics and Materials. — 2005. — Iss. 3−4. — P. 325−330.

24. Soloviev, A. Identification of crack-like defect and investigation of stress concentration in coated bar / A. Soloviev, B. Sobol, P. Vasiliev // In: Springer Proceedings in Physics. — 2019. — Iss. 4. — P. 165−174.

25. Pozharskii, D.A. Periodic crack system in a layered elastic wedge / D.A. Pozharskii, V.N. Sobol’, P.V. Vasil’ev // Mechanics of Advanced Materials and Structures. — 2020. — Vol. 27(4). — P. 318−324.

26. Cherpakov, A.V. The Study of Stratification of Multilayer Structures Based on Finite Element Modeling and Neural Network Technologies / A. V. Cherpakov, P. V. Vasiliev, A. N. Soloviev [et al.] // Advanced Materials. Proc. Int. Conf. on Physics and Mechanics of New Materials and Their Applications, PHENMA 2019. — 2020. — P. 439−447. DOI: 10.1007/978-3-030-45120-2

27. Ватульян, А. О. Обратные задачи в механике деформируемого твердого тела / А. О. Ватульян. — Москва : Физматлит. — 2007. — 224 с.

28. Многократное рассеяние ультразвуковых волн на системе пространственных дефектов канонической формы (теория и эксперимент) / Н. В. Боев, Х. М. Эль-Мараби, В. А. Вдовин, В. М. Зотов // Вестник Донского государственного технического университета. — 2012. — № 12 (3). — С. 5–10.

29. Lyapin, A. Structural Monitoring of Underground Structures in Multi-Layer Media by Dynamic Methods / A. Lyapin, A. Beskopylny, B. Meskhi // Sensors. — 2020. — 20(18). — P. 5241. DOI: 10.3390/s20185241

30. Идентификация параметров повреждений в упругом стержне с использованием конечноэлементного и экспериментального анализа мод изгибных колебаний / А. В. Черпаков, В. А. Акопьян, А. Н. Соловьев [и др.] // Вестник Донского государственного технического университета. — 2011. — Т. 11, № 3 (54). — С. 312–318.

31. Cherpakov, A.V. Simulation of wave processes in the multilayer structure surface layer properties identification by the finite element method / A. V. Cherpakov, O. V. Shilyaeva, M. N. Grigoryan [et al.] // IOP Conf. Ser.: Mater. Sci. Eng. — 2019. — Vol.698. — P. 066021.

32. Cogranne, R. Statistical detection of defects in radiographic images using an adaptive parametric model / R. Cogranne, F. Retraint // Signal Processing. — 2014. — Vol. 96, part B. — P. 173−189.

33. Ватульян, А. О. Поперечные колебания балки с локализованными неоднородностями. / А. О. Ватульян, А. В. Осипов // Вестник Донского государственного технического университета. — 2012. — №12(8). — С. 34–40.

34. Shevtsov, S. N. Piezoelectric Actuators and Generators for Energy Harvesting / S. N. Shevtsov, A. N. Soloviev, I. A. Parinov [et al.] // Heidelberg, Springer. — 2018. — 182 p.

35. Васильченко, К. Е. К расчету амплитудно-частотных характеристик задач об установившихся колебаниях на основе кластерных технологий в ACELAN / К. Е. Васильченко, А. В. Наседкин, А. Н. Соловьев // Вычислительные технологии. — 2005. — Т. 10, № 1. — С. 10–20. 36.

36. Krasil’nikov, V.A. Introduction to Physical Acoustics / V.A. Krasil’nikov, V.V. Krylov // Moscow: Nauka, 1984. — 400 p.

37. Kingma, D. P. Adam: A Method for Stochastic Optimization / D. P. Kingma, J. Ba // Proc. 3rd International Conference for Learning Representation, San Diego. 2015.