Using neural network and genetic algorithm to obtain maximum response of mistuned system

Abstract

Ideally, bladed disk systems are tuned and all blades are identical but, in practice there always exist small, random differences among the blades. Mistuning, imperfections in cyclical symmetry of bladed disks is an inevitable and perilous occurrence due to many factors including manufacturing tolerances and wear in service. It can cause some unpredictable phenomena such as dramatic difference in forced vibration response. In this paper first a finite element model of bladed disk system with 24 blades were created in ANSYS. The model is then used to calculate the frequency response of the blades for the tuned system. Next, two hundred experiments, with different density for each blade, were selected in a specified range. For each test case calculations were performed and the maximum response was obtained. Then, by integrating neural networks and genetic algorithm the worst frequency response of the mistuned bladed-disk system was calculated. The problem of finding the worst specification is formulated as an optimization problem subjected to constraints such as the manufacturing tolerances. Based on the calculated parameters, a new model was created and the maximum response of the mistuned system was calculated. The results indicate that the responses obtained from the neural network and genetic algorithm have reasonable accuracy and are in good agreement with responses obtained from the ANSYS and shows the efficiency of the method

Keywords

References

[1] Yoo HH, Kim JY, Inman DJ (2003) Vibration localization of simplified mistuned cyclic structures undertaking external harmonic force. J Sound Vib 261: 859–870.
[2] Rao JS (1991) Turbomachine blade vibration. Whiley, New Dehl.
[3] You H (1995) Forced vibration characteristics of bladed disc assemblies. PhD Thesis, Imperial College of Science, Tecnology & Medicines, University of London.
[4] Petrov EP (1988) Determination the worst blade mistuning upon forced vibration of impellers using the nonlinear programming methods. Abstracts of the conference mathematical simulation of processes and structures of power and transport turbines in CAD-CAM systems, Gotvald, Ukraine 3: 71–72.
[5] Petrov EP, Ewins DJ (2003) Analysis of the worst mistuning patterns in bladed disk assemblies. J Turbomach 125(4): 623–632.
[6]  Whitehead DS (1966) Effects of mistuning on the vibration of turbomachinary blades. J Mech Eng Sci 8: 15–21.
[7] Whitehead DS (1976) Effects of mistuning on forced vibration of blades with mechanical coupling. J Mech Eng Sci, Vol. 18, No. 6.
[8] Wagner JT (1967) Coupling of turbomachine blade vibrations through the rotor. ASME, J. Eng. Power, Vol. 89, No. 4.
[9] Dye RCF, Henry TA (1969) Vibration amplitudes of compressor blades resulting from scatter in blade natural frequencies. ASME J Eng Power 91: 182–187.
[10] Ewins DJ (1969) The effect of detuning upon the forced vibration of bladed disks. J Sound Vib 9: 65–79.
[11] Ewins D, Han ZC (1984) Resonant vibration levels of a mistuned bladed disk. ASME J Vib. Acoust 106: 211–217.
[12] Afolabi DH (1982) Vibration of mistuned bladed disc assembly. PhD thesis, Imperial College of Science, Technology & Medicines, University of London.
[13] Afolabi DH (1982) A note on the rogue failure of turbine blades. J. Sound Vib. 122(3): 535–545.
[14] Afolabi DH (1988) Vibration amplitudes of mistuned blades. ASME, J. Turbomach, 110: 251–257.
[15] King ME, Layne PA (1998) Dynamic of nonlinear cyclic systems with structural irregularity. Nonlinear Dynam 15: 225–244.
[16] Petrov EP, Sanliturk KY, Ewins DJ (2002) A new method for dynamic analysis of mistuned bladed disks based on the exact relationship between tuned and mistuned systems. Transactions of the ASME 124: 586–597.
[17] Bladh R, Castanier MP, Christophe P (2000) Component mode modeling of mistuned bladed disk vibration. 5th National Turbine Engine High Cycle Fatigue Conference, Chandler, Arizona.
[18] Lim SH (2005) Dynamic analysis and design strategies for mistuned bladed disk. PhD thesis, University of Michigan, Mechanical Department.
[19] Chiu YJ, Huang ShCh (2007) The influence on coupling vibration of a rotor system due to a mistuned blade length. J Mech Sci 49: 522–532.
[20] Chan YJ, Ewins DJ (2010) Management of the variability of vibration response levels in mistuned bladed discs using robust design concepts. Part 1 Parameter design, J Mech Syst Signal Pr 24: 2777–2791.
[21] Bladh R, Castanier MP, Pierre C (2001) Component-Mode-Based reduced order modeling techniques for mistuned bladed disks—Part II. Application, J Eng Gas Turb Power 123: 100–108.
[22] Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning, Reading, MA: Addison-Wesley.
[23] Gallinari P, Thiria S, Badran F, Fogelman-Soulie F (1991) On the relations between discriminant analysis and multilayer perceptrons. Neural Networks 4: 349–360.
[24] EL-Bayoumy LE, Srinivasan AE (1975) Influence of mistuning on rotor blade vibration. AIAA Journal 13: 460–464.
[25] Griffin JH, Hoosac TM (1984) Model development and statistical investigation of turbine blade mistuning. J. Vib Acoust Stress 106: 204–210.
[26] Sanliturk KY, Imregun M, Ewins DJ (1992) Statistical analysis of random mistuning of bladed assemblies. J. Mech. Eng. C432 (110): 51–57.
[27] Rahimi M, Ziaei-Rad, S (2010) Uncertainty treatment in forced response calculation of mistuned bladed disk. J. Math Comput Simulat, 80: 1746–1757.
Journal of Solid and Fluid Mechanics
Volume 1, Issue 2 - Serial Number 2
September and October 2011
Pages 37-46

Files

Share

How to cite

Statistics