Identification of nonlinearities in structural dynamics by using artificial neural networks and optimization

Koyuncu, Anıl
Many real life engineering structures exhibit nonlinear behavior in practice. Although there are sophisticated methods including the effect of nonlinearities on dynamic response of structures in literature, uncertainties about nonlinear elements make further investigation necessary for modeling nonlinearity, and this is usually achieved by using experimental data taken from real systems. Therefore, identification of nonlinearities -determining location, type and parameters of the nonlinear elements- is critical in dynamical structures. 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 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. Identified parameters are improved utilizing optimization. The application of the proposed approach is demonstrated on an example system with nonlinear elements and a real life experimental setup with a local nonlinearity.


IDER, SK (Elsevier BV, 1991-01-01)
Conventionally kinematical constrains in multibody systems are treated similar to geometrical constraints and are modeled by constraint reaction forces which are perpendicular to constraint surfaces. However, in reality, one may want to achieve the desired kinematical conditions by control forces having different directions in relation to the constraint surfaces. In this paper the conventional equations of motion for multibody systems, subject to kinematical constraints, are generalized by introducing gener...
Prediction of Nonlinear Drift Demands for Buildings with Recurrent Neural Networks
Kocamaz, Korhan; Binici, Barış; Tuncay, Kağan (2021-09-08)
Application of deep learning algorithms to the problems of structural engineering is an emerging research field. Inthis study, a deep learning algorithm, namely recurrent neural network (RNN), is applied to tackle a problemrelated to the assessment of reinforced concrete buildings. Inter-storey drift ratio profile of a structure is a quiteimportant parameter while conducting assessment procedures. In general, procedures require a series of timeconsuming nonlinear dynamic analysis. In this study, an extensiv...
An algorithm to generate toroidal and helical cage structures using pentagons, hexagons and heptagons
Yazgan, E; Tasci, E; Erkoc, A (World Scientific Pub Co Pte Lt, 2004-02-01)
An algorithm to generate toroidal or helical cage structures has been developed. Any toroidal or helical structure can be generated following four stages. In the first stage a Fonseca type unit cell and its symmetrical counterpart is formed which represents one-fifth of a toroid. In the second stage one-fifth fragment of the torus is fully obtained by applying geometry optimization to the structure obtained in the first stage. In the third stage the torus fragment obtained in the second stage is reproduced ...
IDER, SK (1996-01-03)
In this paper inverse dynamics of redundant multibody systems using a minimum number of control forces is formulated. It is shown that the control forces and the task accelerations may become noncausal at certain configurations, yielding the dynamical equation set of the system to be singular. For a given set of tasks, each different set of actuators leads to a different system motion and also to different singular configurations. To avoid the singularities in the numerical solution, the dynamical equations...
Structured neural networks for modeling and identification of nonlinear mechanical systems
Kılıç, Ergin; Dölen, Melik; Koku, Ahmet Buğra; Department of Mechanical Engineering (2012)
Most engineering systems are highly nonlinear in nature and thus one could not develop efficient mathematical models for these systems. Artificial neural networks, which are used in estimation, filtering, identification and control in technical literature, are considered as universal modeling and functional approximation tools. Unfortunately, developing a well trained monolithic type neural network (with many free parameters/weights) is known to be a daunting task since the process of loading a specific pat...
Citation Formats
A. Koyuncu, “Identification of nonlinearities in structural dynamics by using artificial neural networks and optimization,” M.S. - Master of Science, Middle East Technical University, 2013.