• Novel transformation-based response prediction of shear building using interval neural network

    • Fulltext


        Click here to view fulltext PDF

      Permanent link:

    • Keywords


      Interval neural network; shear buildings; response; earthquake; structure.

    • Abstract


      Present paper uses powerful technique of interval neural network (INN) to simulate and estimate structural response of multi-storey shear buildings subject to earthquake motion. The INN is first trained for a real earthquake data, viz., the ground acceleration as input and the numerically generated responses of different floors of multi-storey buildings as output. Till date, no model exists to handle positive and negative data in the INN. As such here, the bipolar data in [−1, 1] are converted first to unipolar form, i.e., to [0, 1] by means of a novel transformation for the first time to handle the above training patterns in normalized form. Once the training is done, again the unipolar data areconverted back to its bipolar form by using the inverse transformation. The trained INN architecture is then used to simulate and test the structural response of different floors for various intensity earthquake data and it is found that the predicted responses given by INN model are good for practical purposes.

    • Author Affiliations


      S Chakraverty1 Deepti Moyi Sahoo1

      1. Department of Mathematics, National Institute of Technology Rourkela, Rourkela 769 008, Odisha, India.
    • Dates

  • Journal of Earth System Science | News

    • Editorial Note on Continuous Article Publication

      Posted on July 25, 2019

      Click here for Editorial Note on CAP Mode

© 2021-2022 Indian Academy of Sciences, Bengaluru.