Damping in buildings: Its neural network model and AR model

Q. S. Li, D. K. Liu, J. Q. Fang, A. P. Jeary, C. K. Wong

    Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

    58 Citations (Scopus)

    Abstract

    The results of full scale measurements of damping as well as other researches on damping show that damping in buildings exhibits randomness and amplitude dependent behaviour in the case of tall buildings subjected to dynamic loading. In this paper, based on full scale measurements of damping in a tall building, a time series analysis method (TSA) is employed to obtain the relationship between damping and vibration amplitude. Then, two models of damping in a tall building, the artificial neural network (ANN) model and the auto-regressive (AR) model, are established by employing ANN and AR methods, and used to predict the damping values at high amplitude level, which are difficult to obtain from field measurements. In order to get high accuracy, a genetic algorithm strategy is employed to aid in training the ANN. Comparison analysis of the neural network model and the AR model of damping is made, and the results are presented and discussed. (C) 2000 Elsevier Science Ltd. All rights reserved.
    Original languageEnglish
    Pages (from-to)1216-1223
    JournalEngineering Structures
    Volume22
    Issue number9
    DOIs
    Publication statusPublished - Sept 2000

    Research Keywords

    • AR model
    • Artificial neural networks
    • Damping
    • Full-scale measurements
    • Genetic algorithm
    • Tall buildings

    Fingerprint

    Dive into the research topics of 'Damping in buildings: Its neural network model and AR model'. Together they form a unique fingerprint.

    Cite this