Neural Approximation of the Buckling Coefficient of Compression Flange of Box Girder Evenly Loaded Transversely

Beata Potrzeszcz-Sut; Andrzej Szychowski

doi:10.4028/www.scientific.net/AMM.797.137

Paper Titles

Comparison of Steel Trusses Analysed with Different Types of Fire Curves
p.108

Conception of FEM Analysis Using Special Multi-Area Plane State of Stress Elements
p.115

Analysis of the High Buildings Structure
p.125

Simplified Numerical Modelling of a Blast Load Impact
p.131

Neural Approximation of the Buckling Coefficient of Compression Flange of Box Girder Evenly Loaded Transversely
p.137

Adhesion Assessment between Concrete Layers Using the Ultrasonic Pulse Velocity Method
p.145

Recycling of Concrete as the Direction of a Modern and Efficient Building
p.151

The Effect of Adding Selected Nanoparticles on the Mechanical Properties of the Cement Matrix of Self-Compacting Concrete
p.158

Modified Protective Concrete
p.166

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 797Neural Approximation of the Buckling Coefficient...

Neural Approximation of the Buckling Coefficient of Compression Flange of Box Girder Evenly Loaded Transversely

Abstract:

There are situations in the thin-walled steel girders with box intersection, in which the internal wall of compression flange is elastically restrained in the webs of section and along its length occurs the change of normal stresses. Such a wall was modelled, as a bilateral elastically restrained internal plate variably loaded at the length. Explicit formulation of neural formula on buckling coefficient of internal plate at non-linear distribution of longitudinal stress was discussed in this paper. A few structures of neural networks (NN) were envisaged in order to obtain the best of the numerical effectiveness of the final formula. The results noted from the literature were used for the evaluation of neural prediction of coefficient.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 797)

Pages:

137-144

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.797.137

Citation:

Cite this paper

Online since:

November 2015

Authors:

Beata Potrzeszcz-Sut*, Andrzej Szychowski

Keywords:

Internal Wall, Local Buckling, Longitudinal Stress Variation, Neural Networks, Thin-Walled Members

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

* - Corresponding Author

References

[1] A. Szychowski. The stability of compressed flange of box girder with longitudinal stress variation. XII International Conference of Metal Structures ICMS. Wrocław 2011. 202-211.

Google Scholar

[2] A. Szychowski. Buckling of internal walls in thin-walled members. Scientific and Technical Conference ZK2014 – Metal Structures. Kielce-Suchedniów 2014. 81-84.

Google Scholar

[3] B. Potrzeszcz-Sut. A. Szychowski. Neural prediction of internal wall's buckling coefficient of thin-walled member (in polish). 61. Scientific Conference Bydgoszcz-Krynica. Poland 2015 259-266.

Google Scholar

[4] S. Haykin. Neural Networks: A Comprehensive Foundation. Prentice-Hall. Upper Saddle River. N.J. 2 edition. (1999).

Google Scholar

[5] E. Pabisek. Hybrid systems integrating FEM and AMM for the analysis of selected problems of structural and material mechanics (in polish). Monograph 369. Cracov University of Technology. (2008).

Google Scholar

[6] J. Kaliszuk. Reliability analysis of structures and design elements using artificial neural networks (in polish) . Phd thesis. University of Zielona Góra. (2005).

Google Scholar

[7] B. Potrzeszcz-Sut. E. Pabisek. ANN constitutive material model in the shakedown analysis of an aluminum structure. Computer Assisted Methods in Engineering and Science 21(2014) 49-58.

Google Scholar

[8] B. Miller. Fine-tuning the mathematical model of a structure to the physical model (in polish). Phd thesis. Rzeszow University of Technology. (2002).

Google Scholar

[9] M. Pala. A new formulation for distortional buckling stress in cold-formed steel members. Journal of Constructional Steel Research 62 (2006) 716–722.

DOI: 10.1016/j.jcsr.2005.09.011

Google Scholar

[10] Neural Network Toolbox for Use with MATLAB. User's Guide. The MathWorks. Inc. (2011).

Google Scholar

[11] EN 1993 - Eurocode 3: Design of steel structures. EN 1993-1-3: Supplementary rules for cold-formed members and sheeting. EN 1993-1-5: Plated structural elements.

DOI: 10.3403/02338401u

Google Scholar