A parametric analysis of the patch load behaviour using a neuro-fuzzy system

Abstract

This work presents a parametric analysis to evaluate the behaviour of steel beams subjected to concentrated loads. A neuro-fuzzy system was trained and tested [Fonseca ET. Comportamento de Vigas de Aço Sujeitas a Cargas Concentradas Através de Técnicas de Inteligência Computacional. D.Sc. thesis. Civil Eng. Dept., PUC-Rio. 2003 [in Portuguese]; Fonseca ET, da S. Vellasco PCG, de Andrade SAL, Vellasco MMBR. A neuro-fuzzy system for patch load prediction. In: 7th international conference on the application of artificial intelligence to civil and structural engineering. Egmond aan Zee; 2003 [published in CD-ROM — 18 pages]] to predict patch load results and classify this behaviour. In preceding studies [Fonseca ET, Vellasco MMBR, da S. Vellasco PCG, de Andrade SAL, Pacheco MAC. A neural network system for patch load prediction. Journal of Intelligent and Robotic Systems 2001;31:185–200; Fonseca ET, da S. Vellasco PCG, de Andrade SAL, Vellasco MMBR. A patch load parametric analysis using neural networks. Journal of Constructional Steel Research 2003;59(2):251–67; Fonseca ET, da S. Vellasco PCG, de Andrade SAL, Vellasco MMBR. Neural network evaluation of steel beam patch load capacity. Advances in Engineering Software 2003;34(8):680–705] the performance of neural networks was significantly more accurate than patch load prediction formulae [Lyse I, Godfrey HJ. Investigation of web buckling in steel beams. In: ASCE Transactions, vol. 100, 1935, p. 675–95 [paper 1907]; Bergfelt A. 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, 1979, p. 1–143; CISC, Canadian Institute of Steel Construction. Limit states design of steel structures. CAN/CSA -S16-01; 2001; Eurocode 3, ENV-1993-1-1. Design of steel structures. CEN, European Committee for Standardisation; 1997 [Doc. CEN/TC 250/SC3-N419E]; Roberts TM, Newark ACB. Strength of webs subjected to compressive edge loading. Journal of Structural Engineering, American Society of Civil Engineers 1997;123(2):176–83], although the system did not consider the difference in the beam ultimate limit state. Therefore this paper applies a neuro-fuzzy system to evaluate the ultimate load physical phenomena (yielding, buckling or crippling) as well as the critical load related to each collapse type.