Localization and identification of structural nonlinearities using cascaded optimization and neural networks

Date

2017-10-01

Author

Koyuncu, A.
Ciğeroğlu, Ender
Özgüven, Hasan Nevzat

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

223
views

0
downloads

In this study, a new approach is proposed for identification of structural nonlinearities by employing cascaded optimization and 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 types of all nonlinearities associated with the nonlinear degrees 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, initially, a feed forward regression neural network is trained, which parametrically identifies the classified nonlinearities. Then, the results obtained are further improved by carrying out an optimization which uses network identified values as starting points. Unlike identification methods available in literature, the proposed approach does not require data collection from the degrees of freedoms where nonlinear elements are attached, and furthermore, it is sufficiently accurate even in the presence of measurement noise. The application of the proposed approach is demonstrated on an example system with nonlinear elements and on a real life experimental setup with a local nonlinearity.

Subject Keywords

Control and Systems Engineering, Signal Processing, Mechanical Engineering, Civil and Structural Engineering, Aerospace Engineering, Computer Science Applications

URI

https://hdl.handle.net/11511/35404

Journal

MECHANICAL SYSTEMS AND SIGNAL PROCESSING

DOI

https://doi.org/10.1016/j.ymssp.2017.03.030

Collections

Department of Mechanical Engineering, Article

Suggestions

OpenMETU
Core

Identification of structural non-linearities using describing functions and the Sherman-Morrison method Ozer, Mehmet Bulent; Özgüven, Hasan Nevzat; Royston, Thomas J. (Elsevier BV, 2009-01-01) In this study, a new method for type and parametric identification of a non-linear element in an otherwise linear structure is introduced. This work is an extension of a previous study in which a method was developed to localize non-linearity in multi-degree of freedom systems and to identify type and parameters of the non-linear element when it is located at a ground connection of the system. The method uses a describing function approach for representing the non-linearity in the structure. The describing ...
Localization and Identification of structural nonlinearities using neural networks Yumer, Mehmet Ersin; Koyuncu, Anıl; Ciğeroğlu, Ender; Özgüven, Hasan Nevzat (2013-02-14) 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 ty...
Model updating of nonlinear structures from measured FRFs Canbaloglu, Guvenc; Özgüven, Hasan Nevzat (Elsevier BV, 2016-12-01) There are always certain discrepancies between modal and response data of a structure obtained from its mathematical model and experimentally measured ones. Therefore it is a general practice to update the theoretical model by using experimental measurements in order to have a more accurate model. Most of the model updating methods used in structural dynamics are for linear systems. However, in real life applications most of the structures have nonlinearities, which restrict us applying model updating techn...
A frequency domain nonparametric identification method for nonlinear structures: Describing surface method Karaagacli, Taylan; Özgüven, Hasan Nevzat (Elsevier BV, 2020-10-01) In this paper a new method called 'Describing Surface Method' (DSM) is developed for nonparametric identification of a localized nonlinearity in structural dynamics. The method makes use of the Nonlinearity Matrix concept developed in the past by using classical describing function theory, which assumes that nonlinearity depends mainly on the response amplitude and frequency dependence is negligible for almost all of the standard nonlinear elements. However, this may not always be the case for complex nonli...
Vibration-based damage identification in beam-like composite laminates by using artificial neural networks Şahin, Melin (SAGE Publications, 2003-01-01) This paper investigates the effectiveness of the combination of global (changes in natural frequencies) and local (curvature mode shapes) vibration-based analysis data as input for artificial neural networks (ANNs) for location and severity prediction of damage in fibre-reinforced plastic laminates. A finite element analysis tool has been used to obtain the dynamic characteristics of intact and damaged cantilever composite beams for the first three natural modes. Different damage scenarios have been introdu...

Citation Formats

A. Koyuncu, E. Ciğeroğlu, and H. N. Özgüven, “Localization and identification of structural nonlinearities using cascaded optimization and neural networks,” MECHANICAL SYSTEMS AND SIGNAL PROCESSING, pp. 219–238, 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/35404.