Abstract
In this research, a multiple adaptive neurofuzzy inference system (MANFIS) for fault diagnosis of rotating multi-damage cantilever rotor partially immersed in the viscous fluid environment was proposed. Theoretical, experimental, and finite element methods are employed to ascertain the dynamic responses of a damaged and undamaged cantilever rotor shaft that is partially submerged in a viscous fluid medium. Influence coefficient methods are used to compute the transverse directional (i.e., x and y-axis) natural frequency and amplitude of the rotating multi- cracked cantilever rotor shaft with attached mass (i.e., disk) at the free end. To assess the impact of fluid forces, the Navier–Stokes equation was used. The overall combined framework of fuzzy logic inference system and neural networks is used in the platform of neurofuzzy model. It is very useful tool to estimate the damage identification of the rotor shaft system. Relative crack size and position are the output of the multiple ANFIS controller. In order to determine the robustness of the suggested multiple adaptive neurofuzzy inference system, the final computed results from the multiple ANFIS have been compared with the findings acquired from the experimental investigation.
Similar content being viewed by others
Abbreviations
- A :
-
Cross-sectional area of rotor
- ANFIS:
-
Artificial neurofuzzy interference system
- D :
-
Rotor shaft diameter
- a :
-
Depth of crack
- ɛ :
-
Eccentricity (i.e., mass of disk from its center)
- E :
-
Young’s modulus elasticity
- C ij :
-
Element of compliance matrix
- h :
-
Height of rectangular strip
- F y :
-
Forces of fluid at y-axis in rotor
- F x :
-
Forces of fluid at x-axis in rotor
- I :
-
Moment of inertia
- K ij :
-
Local flexibility matrix of crack element
- J :
-
Strain energy release rate
- i :
-
Variable
- P i :
-
Nodal forces on the crack element
- K s :
-
Rotor shaft stiffness
- RD :
-
Radius of disk
- L :
-
Length of shaft
- m :
-
Fluid mass displaced by the shaft per unit length
- M D :
-
Disk mass
- M*:
-
Dimensionless parameter (m/ms)
- R 1 :
-
Radius of rotor shaft
- RMSE:
-
Root mean square error
- R 2 :
-
Radius of viscous fluid container
- m s :
-
Mass of shaft per unit length
- T D :
-
Thickness of disk
- q :
-
Gap ratio (R2−R1/R1)
- v :
-
Tangential flow velocity
- u :
-
Radial flow velocity
- β :
-
Relative depth of crack (a/D)
- α :
-
Relative position of crack (Lcrack/L)
- ɛ :
-
ɛ1/R1
- ɛ 1 :
-
Eccentricity along x-direction
- ɛ 2 :
-
Eccentricity along y-direction
- Ω:
-
Angular velocity of whirling
- δ :
-
Whirling radius
- ν :
-
Kinematics viscosity of fluid
- ω n :
-
Natural frequency
- ω :
-
Rotating speed of rotor
- ω yy :
-
Critical speed at y-direction
- ω xx :
-
Critical speed at x-direction
References
Ye, Z., Sadeghian, A., Wu, B.: Mechanical fault diagnostics for induction motor with variable speed drives using Adaptive Neuro-fuzzy Inference System. Electr. Power Syst. Res. 76(9), 742–752 (2006)
Kuo, H.C., Chang, H.K.: A new symbiotic evolution-based fuzzy-neural approach to fault diagnosis of marine propulsion systems. Eng. Appl. Artif. Intell. 17(8), 919–930 (2004)
Eslamloueyan, R.: Designing a hierarchical neural network based on fuzzy clustering for fault diagnosis of the Tennessee-Eastman process. Appl. Soft Comput. 11(1), 1407–1415 (2011)
Zio, E., Gola, G.: A neuro-fuzzy technique for fault diagnosis and its application to rotating machinery. Reliab. Eng. Syst. Saf. 94(1), 78–88 (2009)
Yang, B.S., Oh, M.S., Tan, A.C.C.: Fault diagnosis of induction motor based on decision trees and adaptive neuro-fuzzy inference. Expert Syst. Appl. 36(2), 1840–1849 (2009)
Beena, P., Ganguli, R.: Structural damage detection using fuzzy cognitive maps and Hebbian learning. Appl. Soft Comput. 11(1), 1014–1020 (2011)
Salahshoor, K., Khoshro, M.S., Kordestani, M.: Fault detection and diagnosis of an industrial steam turbine using a distributed configuration of adaptive neuro-fuzzy inference systems. Simul. Model. Pract. Theory 19(5), 1280–1293 (2011)
Sadeghian, M., Fatehi, A.: Prediction and detection of the process fault in a cement rotary kiln by locally linear neuro-fuzzy technique. J. Process Control 21(2), 302–308 (2011)
Zhu, F., Deng, Z., Zhang, J.: An integrated approach for structural damage identification using wavelet neuro-fuzzy model. Expert Syst. Appl. 40(18), 7415–7427 (2013)
Bachi, I.O., Abdulrazzaq, N., He, Z.: Neuro fuzzy model for predicting the dynamic characteristics of beams. Acta Mech. Solida Sin. 27(1), 85–96 (2014)
Zhang, L., Xiong, G., Liu, H., Zou, H., Guo, W.: Bearing fault diagnosis using multi- scale entropy and adaptive neuro-fuzzy inference. Expert Syst. Appl. 37(8), 6077–6085 (2010)
Nikolić, V., Petkovic, D., Yeeb, P.L., Shamshirband, S., Zamani, M., Cojbasic, Z., Motamedi, S.: Potential of of neuro-fuzzy methodology to estimate noise level of wind turbines. Mech. Syst. Signal Process. 66(67), 715–722 (2016)
Chen, B., Matthews, P.C., Tavner, P.J.: Wind turbine pitch faults prognosis using a- priori knowledge-based ANFIS. Expert Syst. Appl. 40(17), 6863–6876 (2013)
Saee, R.A., Galybin, A.N., Popov, V.: 3D fluid–structure modelling and vibration analysis for fault diagnosis of Francis turbine using multiple ANN and multiple ANFIS. Mech. Syst. Signal Process. 34, 259–276 (2013)
Vassilopoulos, A.P., Bedi, R.: Adaptive neuro-fuzzy inference system in modelling fatigue life of multidirectional composite laminates. Comput. Mater. Sci. 43, 1086–1093 (2008)
Pawar, R.S., Sawant, S.H.: An overview of vibration analysis of cracked cantilever beam with non-linear parameters and harmonic excitations. Int. J. Innov. Technol. Explor. Eng. 8(3), 53–55 (2014)
Petkovic, D., Issa, M., Pavlovic, N.D., Zentner, L., Cojbasic, Z.: Adaptive neurofuzzy Controller For adaptive Compliant robotic gripper. Expert Syst. Appl. 0957–417439, 13295–13304 (2012)
Matsubara, M., Rahnejat, H., Gohar, R.: Computational modelling of precision spindles supported by ball bearings. Int. J. Mach. Tools Manuf. 28(4), 429–442 (1988)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
The membership functions for P, Q, R, S and T considered in ‘layer 1’ are the bell-shaped functions (Fig. 11) and are defined as follows:
where \(b_{h}\), \(c_{h}\), \(a_{h}\) are the parameters for fuzzy membership function. The parameter has been altered by the bell-shaped function. The alteration of contour of bell-shaped function is required according to the dataset for the considered problem.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yadao, A.R. Investigation of damaged structure in altered viscous fluid medium using multiple adaptive neurofuzzy inference system (MANFIS). Acta Mech 235, 543–563 (2024). https://doi.org/10.1007/s00707-023-03751-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00707-023-03751-8