Neural network identification of building natural periods with various splitting up of the patterns into training and testing sets

Krystyna Kuźniar

Krystyna Kuźniar Pedagogical University of Cracow

Abstract

The paper deals with an application of neural networks for computation of fundamental natural periods of buildings with load-bearing walls. The identification problem is formulated as a relation between structural and soil parameters and the fundamental period of building. The patterns are based on long-term tests performed 6n actual structures. Various splitting up of the set of patterns into training and testing sets are considered in the analysis. The carried out analysis leads to conclusion that, even in "the worst" case of randomly selected testing patterns, the natural periods of vibrations of buildings are obtained with accuracy quite satisfactory for engineering practice.

Keywords

References

[1] R. Ciesielski, K. Kuźniar, E. Maciąg, T. Tatara. Empirical formulae for fundamental natural periods of buildings with load bearing walls. Arch. Civil Engrg., 38(4): 291- 299, 1992.
[2] S. Haykin. Neural Networks - A Compressive Foundation, 2nd ed. Prentice Hall, Upper Saddle River, NY, 1999.
[3] K. Kuźniar, E. Maciąg, Z. Waszczyszyn. Computation of natural periods of vibrations of medium-height prefabricated buildings by neural networks. Arch. Civil Engrg., 46: 515-523, 2000.
[4] K. Kuźniar, Z. Waszczyszyn. Neural analysis of vibration problems of real flat buildings and data pre-processing. Engrg. Struct., 24: 1327-1335, 2002.
[5] E. Maciąg. Experimental evaluation of changes of dynamic properties of buildings on different grounds. Earth. Engrg. Struct. Dyn., 14: 925-932, 1986.