Computational & Technology Resources
an online resource for computational,
engineering & technology publications 

CivilComp Proceedings
ISSN 17593433 CCP: 92
PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON SOFT COMPUTING TECHNOLOGY IN CIVIL, STRUCTURAL AND ENVIRONMENTAL ENGINEERING Edited by: B.H.V. Topping and Y. Tsompanakis
Paper 28
Prediction of Structural Behaviour with Recurrent Neural Networks for Fuzzy Data S. Freitag, W. Graf, M. Kaliske and J.U. Sickert
Institute for Structural Analysis, Technische Universität Dresden, Germany S. Freitag, W. Graf, M. Kaliske, J.U. Sickert, "Prediction of Structural Behaviour with Recurrent Neural Networks for Fuzzy Data", in B.H.V. Topping, Y. Tsompanakis, (Editors), "Proceedings of the First International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering", CivilComp Press, Stirlingshire, UK, Paper 28, 2009. doi:10.4203/ccp.92.28
Keywords: recurrent neural network, fuzzy process, modelfree prediction, timedependent structural behaviour, fractional rheological model, textile reinforced concrete.
Summary
The longterm behaviour of civil engineering structures depends on a variety of environmental influences such as applied loadings, temperature and weathering. This results in uncertain timedependent deformations and stress rearrangements inside the structure.
These phenomena can be incorporated into a timedependent structural analysis.
A clear separation of longterm effects with respect to individual environmental influences and the formulation of an associated mechanical model are difficult due to the limited amount of experiments and not yet complete physicalmechanical insight.
As an alternative, a novel method for the numerical prediction of timedependent structural responses under consideration of uncertain action processes is proposed, which combines neural computing and mapping of fuzzy data (fuzzy analysis [1]).
If a structural process is observed experimentally with the help of measurement devices, it is not possible to assign precise values to the observed events. That means, data uncertainty occurs which may result from scaledependent effects, varying boundary conditions which are not considered, inaccuracies in the measurements, and incomplete sets of observations. Therefore, measured results are more or less characterized by data uncertainty which originates in imprecision. In this contribution, the imprecision is modelled by means of the uncertainty data model fuzziness. Timedependent structural parameters are quantified as fuzzy processes. A modelfree concept based on neural networks is employed to extract and to evaluate information obtained from experiments. Artificial neural networks are utilized for the approximation of timedependent effects of the structural behaviour. Structural processes obtained by experiments or numerical analyses are mapped onto timedependent structural responses. Therefore, the neural network requires a temporal signal processing. Suitable network types for this purpose are recurrent neural networks. They are trained with uncertain values obtained by discretization of fuzzy processes. That is, the input and output training data sets contain fuzzy values. However, also intervals and deterministic numbers may be processed as special cases beside fuzzy intervals and fuzzy numbers. Three types of mapping with recurrent neural networks for fuzzy data are introduced. A prediction and a training algorithm are presented. Beside fuzzy input and output values, also fuzzy network parameters are considered in the new approach. An efficient solution of the mapping with recurrent artificial neural networks for fuzzy data is obtained utilizing alphacuts [1] and interval arithmetic. The developed numerical prediction method is verified with a fractional rheological material model [2]. Uncertain timedependent stressstraindependencies obtained by numerical monitoring are trained. The resulting networks for fuzzy data are utilized for the prediction of further stressstraindependencies. The capabilities of the presented approach are demonstrated by means of an example. The longterm displacement of a textile strengthened reinforced concrete plate is predicted based on uncertain experimentally obtained data. References
purchase the fulltext of this paper (price £20)
go to the previous paper 
