Abstract
In this study, a new approach is proposed for identification of structural nonlinearities by employing neural networks. Linear finite element model of the system and frequency response functions measured at arbitrary locations of the system are used in this approach. Using the finite element model, a training data set is created, which appropriately spans the possible nonlinear configurations space of the system. A classification neural network trained on these data sets then localizes and determines the type of nonlinearity associated with the corresponding degree of freedom in the system. A new training data set spanning the parametric space associated with the determined nonlinearities is created to facilitate parametric identification. Utilizing this data set, a feed forward regression neural network is trained, which parametrically identifies the related nonlinearity. The application of the proposed approach is demonstrated on an example system with nonlinear elements. The proposed approach does not require data collection from the degrees of freedoms related with nonlinear elements, and furthermore, the proposed approach is sufficiently accurate even in the presence of measurement noise.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kerschen G, Worden K, Vakakis AF, Golinval JC (2006) Past, present and future of nonlinear system identification in structural dynamisc. Mech Syst Signal Process 20:505–592
Adams DE, Allemang RJ (1988) Survey of nonlinear detection and identification techniques for experimental vibrations. In: International seminar on modal analysis (ISMA 23), Leuven, Belgium
Kerschen G, Worden K, Vakakis AF, Golinval JC (1986) Nonlinear system identification in structural dynamics: current status and future directions. In: 4th International modal analysis conference, vol 1, pp 712–719, Los Angeles, CA,USA
Özer MB, Özgüven HN, Royston TJ (2009) Identification of structural non-linearities using describing functions and the Sherman–Morrison method. Mech Syst Signal Process 23(1):30–44
Aykan M, Özgüven HN (2012) Parametric identification of nonlinearity from incomplete FRF data using describing function inversion. In: Proceedings of SEM IMAC XXX conference, pp 323–334, Jacksonville, FL USA
Göge D, Sinapius M, Füllekrug U, Link M (2005) Detection and description of non-linear phenomena in experimental modal analysis via linearity plots. Int J Nonlinear Mech 40(1):27–48
He J, Ewins DJ (1987) A simple method of interpretation for the modal analysis of non-linear systems. In: 5th international modal analysis conference, pp 626–634, London, England
Adams DE, Allemang RJ (2000) A frequency domain method for estimating the parameters of a non-linear structural dynamic model through feedback. Mech Syst Signal Process 14(4):637–656
Chatterjee A, Vyas NS (2004) Non-linear parameter estimation in multi-degree-of-freedom systems using multi-input Volterra series. Mech Syst Signal Process 18(3):457–489
Masri SF, Caughey TK (1979) A nonparametric identification technique for nonlinear dynamic problems. J Appl Mech 46:433–447 (Introduction Section 3; Sections 3.2, 5.1, 6.1, 6.2)
Richards CM, Singh R (1998) identification of multi-degree-of-freedom non-linear systems under random excitations by the reverse-path spectral method. J Sound Vib 213 673–708 (Sections 3.3, 6.6, 7.1)
Masrit SF, Chassiakosl AG, Caugheys TK (1992) Structure-unknown non-linear dynamic systems: identification through neural networks. 1:45–56
Xie SL, Zhang YH, Chen CH, Zhang XN (2012) Identification of nonlinear hysteretic systems by artificial neural network. Mech Syst Signal Process, 34(1–2) 76–87
Beale MH, Hagan MT, Demuth HB (2012) Neural network toolbox TM user’s guide, The MathWorks, Inc., pp 18–84
Menq C.-H, Griffin JH, Bielak J (1986) The influence of microslip on vibratory response, Part II: a comparison with experimental results. J Sound Vib 107(2) 295–307
Cigeroglu E, Samandari H (2012) Nonlinear free vibration of double walled carbon nanotubes by using describing function method with multiple trial functions. Physica E: Low-dimensional Syst Nanostruct 46:160–173
Yümer ME, Ciğeroğlu E, Özgüven HN (2010) Non-linear forced response analysis of mistuned bladed disk assemblies. ASME turbo expo 2010: power for land, sea, and air (GT2010), pp 757–766, Glasgow, Scotland
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 The Society for Experimental Mechanics, Inc.
About this paper
Cite this paper
Koyuncu, A., Cigeroglu, E., Yumer, M.E., Özgüven, H.N. (2013). Localization and Identification of Structural Nonlinearities Using Neural Networks. In: Kerschen, G., Adams, D., Carrella, A. (eds) Topics in Nonlinear Dynamics, Volume 1. Conference Proceedings of the Society for Experimental Mechanics Series, vol 35. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-6570-6_9
Download citation
DOI: https://doi.org/10.1007/978-1-4614-6570-6_9
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-6569-0
Online ISBN: 978-1-4614-6570-6
eBook Packages: EngineeringEngineering (R0)