Abstract
This work presents the application of Artificial Neural Networks to forecast the ultimate resistance of steel beams subjected to patch loads. A single design formula for this structural engineering problem is very difficult to obtain, due to the influence of several independent parameters. On the other hand, creating new experimental data in laboratory is very time consuming and expensive. This work demonstrates that new data can be obtained from a neural network system composed of four Back Propagation networks. The proposed neural network system presented a maximum error value lower than 15%, while the existing formulas errors were over 20%. These results confirmed the possibility of using this methodology to generate new trustworthy data. These data, coupled with experiments found in the literature, can surely help the development of a more consistent and accurate design formula.
Similar content being viewed by others
References
Anderson, D., Hines, E. L., Arthur, S. J., and Eiap, E. L.: Application of artificial neural networks to prediction of minor axis steel connections, in: B. H. V. Topping and A. I. Khan (eds), Neural Networks and Combinatorial Optimization in Civil and Structural Engineering, Civil-comp Press, 1993, pp. 31-38.
Bagchi, D. and Rockey, K.: Post buckling behaviour of a Web plate under partial edge loading, in: Proc. of the 3rd Internat. Spec. Conf. on Cold Formed Struct., Vol. 1, University of Missouri, Rolla, MO, 1975, pp. 251-254.
Bento, J. P., Carvalho, A. F., Leal, A. M., and Ndumu, D.: Economical buildings evaluation using artificial neural networks, in: I. MacLeod (ed.), Applications of Artificial Intelligence in Structural Engineering III, Ross Priory, Scotland, UK, 1996, pp. 101-102.
Bento, J. P. and Ndumu, D.: Application of neural networks to the earthquake resistant analysis of structures, in: I. MacLeod (ed.), Applications of Artificial Intelligence in Structural Engineering III, Ross Priory, Scotland, UK, 1996, pp. 111-112.
Bento, J., Ndumu, D., and Dias, J.: Application of neural networks to the seismic analysis of structures, in: H. Dajian and M. Haihong (eds), Computational Methods in Engineering and Science: Theory and Application, South China University of Technology Press, China, pp. 72-81; and in: M. Heinisuo (ed.), Applications of Artificial Intelligence in Structural Engineering-IV, Tampere University of Technology, Finland, 1997, pp. 165-172.
Bergfelt, A.: Studies on slender plate girders without intermediate stiffeners: I. Shear test results II.Web crippling, in: R.Massonet (ed.), IABSE Coll. Proc. p70, Vol. 11, London, 1971, pp. 67-83.
Bergfelt, A.: Patch Loading on Slender Web Influence of Horizontal and Vertical Web Stiffeners on the Load Carrying Capacity, Division of Steel and Timber Structures, Chalmers University of Technology, Publ. S79:1, Goteborg, 1979, pp. 1-143.
Bergfelt, A.: Girder Web Stiffening for Patch Loading, Division of Steel and Timber Structures, Chalmers University of Technology, Publ. S83:1, Goteborg, 1983, pp. 1-78.
Bergfelt, A. and Hovik, J.: Thin-walled deep plate girders under static loads, in: IABSE Congress, New York, 1968, pp. 465-477.
Bishop, C. M.: Neural networks and their applications, Rev. Sci. Intrum. 65(6) (1994), 1803-1832.
Drdacky, M. and Novotny, R.: Partial edge load-carrying capacity tests of thick plate girder Webs, Acta Technica CSAV 87(5) (1977), 614-620.
Dubas, P. and Gheri, E.: Behavior of Webs under concentrated loads acting between vertical stiffeners, Commission 8.3, Eur. Convention for Constructional Steelwork, Zurich, Switzerland, 1975.
Fonseca, E. T., Vellasco, M., Vellasco, P., and Andrade, S.: A neural network evaluation of the patch load phenomenon, in: Internat. Conf. on Enhancement and Promotion of Computational Methods in Engineering and Science, Macao 2-5, 1999.
Haykin, S.: Neural Networks-A Comprehensive Foundation, Mcmillan College Publishing Company, Inc., 1998.
Hecht-Nielsen, H.: Neurocomputing, Addison-Wesley, San Diego, CA, 1989.
Hopfield, J.: Neural networks and physical systems with emergent collective computational abilities, Proc. National Acad. Sci. 79 (1982), 2554-2558.
Hornik, K., Stinchcombe, M., and White, H.: Multilayer feedforward networks are universal approximators, Neural Networks 2 (1989), 359-366.
Kennedy, S. J., Kennedy, D. J. L., Prabha, K. R., and Prowse D.: The bearing resistance of Webs: A plate post-buckling strength problem, in: 1997 Annual Technical Session and Meeting, Structural Stability Research Council, Toronto, June 9-11, 1997.
Ketchun, M. Z. and Draffin, J. O.: Strength of light I-beams, University of Illinois Engrg. Experimental Station Bull., No. 241, Champaign III, 1932.
Kohonen, T.: Self-Organizating Maps, Springer, Berlin, 1997.
Lima, L. R. O., Vellasco, M., Vellasco, P., and Andrade, S. A. L.: Avaliação de ligações vigacoluna em estruturas de aço utilizando redes neurais (in portuguese), Internal repport, Electrical Engineering Department, PUC-RIO, 1999.
Lyse, I. and Godfrey, H. J.: Investigation of Web buckling in steel beams, ASCE Trans. 100, paper 1907 (1935), 675-695.
NeuralWare, Neuralworks Predict for Excel 7.0-User Manual, NeuralWare, Inc., 1994.
Roberts, T. M.: Slender plate girders subjected to edge loading, in: Proc. of Inst. of Civil Engrg., Part 2, Vol. 71, 1981, pp. 805-819.
Roberts, T. M.: Patch loading in plate girders, in: R. Narayanan (ed.), Plated Structures-Stability and Strength, Elsevier Applied Science Publishers, London, 1983, pp. 77-102.
Roberts, T. M., and Chong, C. K.: Collapse of plate girders under edge loading, ASCE J. Struct. Div. 107(ST8) (1981), 1503-1509.
Roberts, T. M. and Newark, A. C. B.: Strength of webs subjected to compressive edge loading, J. Structural Engrg. 123(2) (1997), 176-183.
Roberts, T. M. and Rockey, K. C.: A mechanism solution for the collapse load of slender plate girders when subjected to in-plane patch loading, in: Proc. of Inst. of Civil Engrg., Part 2, Vol. 67, 1979, pp. 155-175.
Rumelhart, D. E. and McClelland, J. L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1/2, MIT Press, Cambridge, MA, 1986.
Silva, L. F., Vellasco, M., Vellasco, P., and Andrade, S.: Classificação e projeto automático de ligações viga-coluna em estruturas de aço utilizando redes neurais e o método das componentes (in portuguese), Internal Repport, Electrical Engineering Department, PUC-RIO, 1999.
Skaloud, M. and Drdacky, M.: Ultimate Load Design of Webs of Steel Plated Structures-Part 3: Webs under Concentrated Loads, Staveb. Casopis, Vol. 23, C3, Veda Bratislava, 1975, pp. 140-160.
Treleaven, P., Pacheco, M., and Vellasco, M.: VLSI architectures for neural networks, IEEE Micro 9(6) (1989), 8-27.
Vellasco, P. C. G. S.: Local Web buckling in tapered composite beams, PhD Thesis, Imperial College, London, 1992.
Vellasco, P. C. G. S., Hobbs, R. E., and Dowling, P. J.: Patch load instability, in: Internat. Conf. on Integrity Evaluation and Life Extension of Industrial Equipments, IEV93, Pouso Alto, Brazil, 1993, pp. 87-90.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fonseca, E.T., Vellasco, M.M.B.R., Pacheco, M.A.C. et al. A Neural Network System for Patch Load Prediction. Journal of Intelligent and Robotic Systems 31, 185–200 (2001). https://doi.org/10.1023/A:1012027726962
Issue Date:
DOI: https://doi.org/10.1023/A:1012027726962


