Identification of Crack Location and Depth in a Structure by GMDH- type Neural Networks and ANFIS

Document Type : Persian


1 Professor, Mechanical Engineering Department, Guilan University

2 M.Sc., Mechanical Engineering Department, Guilan University

3 Assistant Professor, Mechanical Engineering Department, Guilan University


The Existence of crack in a structure leads to local flexibility and changes  the stiffness and dynamic behavior of the structure. The dynamic behavior of the cracked structure depends on the depth and the location of the crack. Hence, the changes in the dynamic behavior in the structure due to the crack can be used for identifying the location and depth of the crack. In this study the first three natural eigenfrequencies of a cantilever beam having a transverse open crack have been computed for
10 different depths and 30 different locations by the finite element method. These natural eigenfrequencies have been used as input data for GMDH-type neural networks and adaptive
neuro-fuzzy inference system, ANFIS, for crack location and depth modeling.



[1]  Vandiver J., Detectionof Structural Failure on Fixed Platforms by Measurement of Dynamic Response, Proc. of the 7th Annual Offshore Tech. Conf, 1975, pp. 243–252.
[2]    Gounaris G., Dimarogonas A., A Finite element of a cracked prismatic beam in structural analysis  Computers and Structures, 1988, Vol.28, pp. 309-313.
[3]   Inagaki V., Kanki T., Transverse vibrations of a general cracked rotor bearing system , Mechanical Design (ASME), 1981, Vol. 104, pp. 1-11.
[4]   Leung P., The effects of a transverse Crack on the dynamics of a circular shaft, Rotordynamics’92 International Conference on Rotating Machine Dynamics, 1992.
[5]   Shim M. B., Suh M. W., Crack identification of a planar frame structure based on a synthetic artificial intelligence technique, Int. J. for numerical methods in engineering, Vol.57, 2003, pp. 57-82, 
[6]   Ariman-Zadeh A.,  Darvizeh A., Ahmad-Zadeh V., Hybrid genetic design of GMDH-type          neural networks using singular value decomposition for modeling  and prediction of the explosive cutting process, J. of Engineering manufacture Proceedings of the I MECH E Part B, Vol. 217, 2003, pp. 779 -790.
[7]   Lee C., Fuzzy Logic in Control Systems. Fuzzy Logic Controller, IEEE Transacation on Systems,Man and Cybernetics,  Vol.22(5), pp. 1033-1046, 1990.
[8] Kosko B., Fuzzy Systems as universal approximator, IEEE Transaction on Computer, Vol43(11), 1994, pp.1327-1333.
[9]   Porter B., Nariman-Zadeh N. , Genetic Design of Computed Torque Controllers for Robotic Manipulators, Proc. IEEE.Int. Symp. Intelligent Control, 1995.
]10[  براتی م. ، طراحی سیستمهای فازی جهت مدلسازی رفتار ارتعاشی پوسته های چند لایه مرکب با استفاده از ترکیبی از روش تجزیه مقادیر منفرد و تندترین شیب، دانشگاه گیلان، پایان نامه کارشناسی ارشد،1381.
[11] Golub G.H., Reinesh C., Singular value decomposition and least squares solutions, Numer. Math., Vol. 14(5), 1970, pp. 403-420.
[12]   Nariman-zadeh N., Darvizeh, A., Darvizeh M., Gharababaei H., Modelling of explosive cutting process of plates using GMDH-type neural network and singular value decomposition. J. Materials Processing Technology, Vol. 128, No. 1-3, 2002,
 pp. 80-87.
 [13] Ivakhnenko A.G., Polynomial theory of complex system, IEEE Trans. Syst. Man & Cybern,  SMC-1, 364-378, 1971.