Keywords: patch load, steel structures, neuro-fuzzy systems, web buckling, web crippling, yielding.

This paper presents a parametric analysis to evaluate the behaviour of steel beams subjected to concentrated loads. A neuro-fuzzy system was trained and tested [1] using experimental data, to predict and classify this behaviour. In preceding studies [2] results obtained by a neural network system have been compared to experimental data and existing design formulae, leading to accurate critical load predictions. The performance of neural networks was actually significantly more accurate than patch load prediction formulae [3,4,5,6,7]. Despite the accuracy of the results, the system did not explicitly consider the fundamental difference in the beam ultimate limit state associated to the structural collapse (web and flange yield, web buckling and web crippling).

This work presents a neuro-fuzzy network [1] trained to classify the evaluated beams according to its pertinence to a specific structural response. Afterwards, the pertinence values established are used by a neural network to produce the beam ultimate patch load resistance and execute a parametric analysis.

It is also important to observe that the present study is the first comprehensive structural investigation of the patch load phenomena in terms of the three ultimate limit states. Although, the authors would like to clarify that this paper had no intention of being a definite solution to the complex patch load phenomena that have been investigated since the beginning of the last century. The main intention was to introduce a new approach for a better understanding of the patch load structural response. Another aim of this paper was to present innovative conclusions and directions to a problem that have been exhaustively studied by traditional methods. The next steps of this investigation will utilize this valuable information to develop a less conservative design equation to be incorporated in steel design standards.

1

E.T. Fonseca et al, "A parametric analysis of the patch load behavior using neuro-fuzzy systems", Journal of Constructional Steel Research, Volume 63, Pages 194-210, 2007. doi:10.1016/j.jcsr.2006.04.005

2

E.T. Fonseca et al, "A patch load parametric analysis using neural networks",Journal of Constructional Steel Research, 59, 2, 251-267, 2003. doi:10.1016/S0143-974X(02)00024-X

3

I. Lyse, H.J. Godfrey, "Investigation of Web Buckling in Steel Beams", ASCE Transactions, 100, paper 1907, pp. 675-695, 1935.

4

A. Bergfelt, "Patch Loading on Slender Web. Influence of Horizontal and Vertical Web Stiffeners on the Load Carrying Capacity", Chalmers University of Technology, Publication. S79:1, Goteborg, pp. 1-143, 1979.

5

CISC, Canadian Institute of Steel Construction, "Limit States Design of Steel Structures", CAN/CSA -S16-01, 2001.

6

Eurocode 3, ENV-1993-1-1, "Design of Steel Structures", CEN, European Committee for Standardisation, Doc. CEN/TC 250/SC3-N419E, 1997.

7

T. M. Roberts; A.C.B. Newark, "Strength of Webs Subjected to Compressive Edge Loading", Journal of Structural Engineering, American Society of Civil Engineers, 123(2), pp. 176 -183, 1997. doi:10.1061/(ASCE)0733-9445(1997)123:2(176)

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £62 +P&P)