Interval response data based system identification of multi storey shear buildings using interval neural network modelling

Abstract

This paper uses artificial neural network (ANN) technique for the identification of structural parameters of multistorey shear buildings. First, the identification has been done using response of the structure subject to ambient vibration with interval initial condition. Then, forced vibration with horizontal displacement in interval form has been used to investigate the identification procedure. The neural network has been trained by a methodology so as to handle interval data. This is because, in general we may not get the corresponding input and output values exactly (in crisp form) but we may only have the uncertain information of the data. These uncertain data are assumed in term of interval and the corresponding problem of system identification is investigated. The model has been developed for multistorey shear structure and the procedure is tested for the identification of the stiffness parameters of simple example problem using the prior values of the design parameters.