An Improvement Intended For Multiple Crack Diagnosis Adopting Combo Artificial Intelligence Technique

  • Authors

    • Jajneswar Nanda
    • Layatitdev Das
    • D R. Parhi
    2018-12-13
    https://doi.org/10.14419/ijet.v7i4.39.23938
  • Multiple cracked shaft, status monitoring, fundamental frequency, and modal values, MANFIS-GA.
  • Abstract: In the existing article, an innovative combination technique has been efficiently implemented to properly recognize the specific position and intensity of the transverse surface crack in a fixed-fixed shaft. The rod is suitably fixed on two modest bearings at both ends including axial and twisting load for the fixed angular arrangement in the longitudinal direction. The fluctuation parametric measure so as expected frequencies, mode shapes are interrogated in the  proximity of two crack depths (bi) with their specific locations (Li) using stress intensity factor. Stress intensity factor is typically an objective function of compliance matrices. It is estimated as implementing one desired end of the shaft as the fixed bearings with the considerable help of an analytical method. The identical shaft is designed precisely to accurately determine the vibration signatures at respective vicinity using correctly an experimental procedure.

    A developed methodology MANFIS-GA (an inverse technique) is implemented correctly to identify the proper position and intensity of possible crack from any one of the direct bearing. Complex MANFIS system consists precisely of four composed ANFIS layer. The possible input to every ANFIS step is adequately equipped with the first three fundamental frequencies along with their modal values. The standard output of the active ANFIS part prognosticates the interim crack positions and desired depths. The interim outputs from four ANFIS (MANFIS) are carefully taken as the specific inputs to the automated G.A. system. The outputs from the modern G.A. system are invariably final crack locations along with crack depths. The potency of the satisfactory MANFIS-GA results is authenticated by correlating the results with the experimental setup. By reasonably interpreting the possible outcomes, it is presumed that this recommended methodology is valid for online and time saving for fault analysis of the cracked structure.

     

     

  • References

    1. [1] M. Mehrjoo, N. Khaji, and M. Ghafory-Ashtiany, Application of genetic algorithm in crack detection of beam-like structures using a new cracked Euler–Bernoulli beam element, Applied Soft Computing, 13(2): p. 867-880, 2013.

      [2] N. T. Khiem, and H. T. Tran, A procedure for multiple crack identification in beam-like structures from natural vibration mode, Journal of Vibration and Control, 20(9): p. 1417-1427, 2014.

      [3] M. Chandrashekhar, and R. Ganguli, Uncertainty handling in structural damage detection using fuzzy logic and probabilistic simulation, Mechanical Systems and Signal Processing, 23(2): p.384-404, 2009.

      [4] K. M. Saridakis, A. C. Chasalevris, C. A. Papadopoulos, and A. J. Dentsoras, Applying neural networks, genetic algorithms and fuzzy logic for the identification of cracks in shafts by using coupled response measurements, Computers & Structures, 86(11-12): p. 1318-1338, 2008.

      [5] M. T. Vakil-Baghmisheh, M. Peimani, M. H. Sadeghi, and M. M. Ettefagh, Crack detection in beam-like structures using genetic algorithms, Applied soft computing, 8(2): p. 1150-1160, 2008.

      [6] S. K. Panigrahi, S. Chakraverty, and B. K. Mishra, Vibration based damage detection in a uniform strength beam using genetic algorithm, Meccanica, 44(6): p. 697, 2009.

      [7] S. K. Singh, and R. Tiwari, Identification of a multi-crack in a shaft system using transverse frequency response functions, Mechanism and machine theory, 45(12): p. 1813-1827, 2010.

      [8] P. Beena, and R. Ganguli, Structural damage detection using fuzzy cognitive maps and Hebbian learning, Applied Soft Computing, 11(1): p. 1014-1020, 2011.

      [9] I. Haryanto, J. D. Setiawan, and A. Budiyono, Structural damage detection using randomized trained neural networks. In Intelligent Unmanned Systems: Theory and Applications, Springer, Berlin, Heidelberg, p. 245-255, 2009.

      [10] D. Lehký, and D. Novák, Neural network based damage detection of dynamically loaded structures, In International Conference on Engineering Applications of Neural Networks, Springer, Berlin, Heidelberg, p. 17-27, 2009.

      [11] M. Dilena, and A. Morassi, Structural health monitoring of rods based on natural frequency and antiresonant frequency measurements, Structural health monitoring, 8(2): p. 149-173, 2009.

      [12] B. Chomette, and J. J. Sinou, Crack detection based on optimal control, Journal of vibration and control, 18(11): p. 1737-1749, 2012.

      [13] R. A. Saeed, A. N. Galybin, and V. Popov, Crack identification in curvilinear beams by using ANN and ANFIS based on natural frequencies and frequency response functions, Neural computing and applications, 21(7): p. 1629-1645, 2012.

      [14] F. AlThobiani, A. Ball, and B. K. Choi, An application to transient current signal based induction motor fault diagnosis of Fourier–Bessel expansion and simplified fuzzy ARTMAP, Expert Systems with Applications, 40(13): p. 5372-5384, 2013.

      [15] L. Rubio, B. Muñoz-Abella, and G. Loaiza, Static behaviour of a shaft with an elliptical crack, Mechanical Systems and Signal Processing, 25(5): p. 1674-1686, 2011.

  • Downloads

  • How to Cite

    Nanda, J., Das, L., & R. Parhi, D. (2018). An Improvement Intended For Multiple Crack Diagnosis Adopting Combo Artificial Intelligence Technique. International Journal of Engineering & Technology, 7(4.39), 230-237. https://doi.org/10.14419/ijet.v7i4.39.23938