DOI QR코드

DOI QR Code

Application of artificial neural network for determination of wind induced pressures on gable roof

  • Kwatra, Naveen (Department of Civil Engineering, Thapar Institute of Engineering & Technology) ;
  • Godbole, P.N. (Department of Civil Engineering, University of Roorkee) ;
  • Krishna, Prem (Department of Civil Engineering, University of Roorkee)
  • Published : 2002.02.25

Abstract

Artificial Neural Networks (ANN) have the capability to develop functional relationships between input-output patterns obtained from any source. Thus ANN can be conveniently used to develop a generalised relationship from limited and sometimes inconsistent data, and can therefore also be applied to tackle the data obtained from wind tunnel tests on building models with large number of variables. In this paper ANN model has been developed for predicting wind induced pressures in various zones of a Gable Building from limited test data. The procedure is also extended to a case wherein interference effects on a gable roof building by a similar building are studied. It is found that the Artificial Neural Network modelling is seen to predict successfully, the pressure coefficients for any roof slope that has not been covered by the experimental study. It is seen that ANN modelling can lead to a reduction of the wind tunnel testing effort for interference studies to almost half.

References

  1. Tieleman, H.W., Reinhold, T.A. and Hajj, M.R. (1999), "Pressure characteristics for separated flows", Proc. of 10th Int. Conf. on Wind Engineering, Copenhagen, Denmark, 1731-1738.
  2. Xu, Y.L., Mehta, K.C. and Reardon, G.F. (1995), "Fatigue of metal roof cladding subject to wind loading. Part I: Fatigue-related characteristics of roof pressures", Proc. of 9th Int. Conf. on Wind Engineering, New Delhi, 26-46.
  3. Rumelhart, D.E. and McCelland, J.E. (eds.) (1986), Parallel Distributed Processing. 1, MIT Press, Cambridge, MA.
  4. Sandri, P. and Mehta, K.C. (1995), "Using a backpropagation neural network for predicting wind induced damage to buildings", Proc. of 9th Int. Conf. on Wind Engineering, New Delhi, 1989-1999.
  5. Tieleman, H.W., Reinhold, T.A and Hajj, M.R. (1997), "Wind tunnel simulation requirements to assess wind loads on low-rise buildings", Proc. of 2 EACWE, Genova, Italy, 1093-1100.
  6. IS:875 (Part 3) (1987), "Code of practice for design loads (other than earthquake) for buildings and structures, part 3 wind loads", Bureau of Indian Standards, New Delhi.
  7. Peterka, J.A. (1983), "Selection of local peak pressure coefficients for wind tunnel studies of buildings", J. Wind Eng. Ind. Aerod., 13, 477-488. https://doi.org/10.1016/0167-6105(83)90166-6
  8. Box, G.E.P. and Cox, D.R. (1964), "An analysis of transformation", J. Royal Statistical Soc., 26, 211-252.
  9. Cermak, J.E., and Cocharan, L.S. (1992), "Physical modelling of atmospheric surface layer", J. Wind Eng. Ind. Aerod., 41-44, 935-946.
  10. Girma, T.B. (1999), "Application of cascade-correlation learning network for determination of wind pressure distribution in buildings", Proc. of 10th Int. Conf. on Wind Engineering, Copenhagen, Denmark, 1491-1496.
  11. Kwatra, Naveen, Godbole, P.N. and Prem Krishna (1999), "Application of artificial neural network for determination of wind induced pressures on gable roofs", Proc. of 10th Int. Conf. on Wind Engineering, Copenhagen, Denmark, 1825-1829.
  12. Khanduri, A.C., Bedard, C. and Stathopoulos, T. (1995), "Neural network modelling of wind-induced interference effects", Proc. of 9th Int. Conf. on Wind Engineering, New Delhi, 1341-1352.

Cited by

  1. Damage Detection for Framed RCC Buildings using ANN Modeling vol.16, pp.4, 2007, https://doi.org/10.1177/1056789506065939
  2. Rapid prediction of long-term deflections in composite frames vol.18, pp.3, 2015, https://doi.org/10.12989/scs.2015.18.3.547
  3. Prediction of wind loads on a large flat roof using fuzzy neural networks vol.28, pp.1, 2006, https://doi.org/10.1016/j.engstruct.2005.08.006
  4. Prediction of wind properties in urban environments using artificial neural network vol.107, pp.3-4, 2012, https://doi.org/10.1007/s00704-011-0506-9
  5. Designing laboratory wind simulations using artificial neural networks vol.120, pp.3-4, 2015, https://doi.org/10.1007/s00704-014-1201-4
  6. Dynamic along wind response of tall buildings using Artificial Neural Network pp.1573-7543, 2018, https://doi.org/10.1007/s10586-018-2027-0
  7. Computing dynamic across-wind response of tall buildings using artificial neural network pp.1573-0484, 2018, https://doi.org/10.1007/s11227-018-2708-8