Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/2243
Title: Uncertain Data Based System Identification of Structural Systems by Neural Network Modeling
Authors: Chakraverty, S
Keywords: System identification
Structural Systems
Neural Network
Issue Date: Dec-2014
Citation: 80th Annual Conference Indian Mathematical Society, Indian School of Mines, Dhanbad Jharkhand India, 27-28 Dec 2014.
Abstract: System identification methods of structural dynamics, in general solve inverse vibration problems to identify properties of a structure from measured data. The use of computers and efficient mathematical algorithms allow identification of the process dynamics by evaluating the input and output signals of the system. The result of such process identification is usually a mathematical model by which the dynamic behaviour can be estimated or predicted. Models and parameters of practical application are usually established on the basis of plans, drawings, measurements, observations, experiences, expert knowledge, codes and standards and so on. In general, exact information and precise values of parameters do not exist. Various uncertainties may result from human mistakes, errors in the manufacture and construction and from the lack of information. In order to perform realistic science and engineering analysis and proper safety assessment, the uncertainty in both data and models must be appropriately taken into consideration. Basically these uncertainties may be handled by probabilistic, fuzzy or interval analysis. In probabilistic approach, uncertain variables are considered as random variables with a joint probability density function. Unfortunately, probabilistic methods may not deliver reliable results at the required precision without sufficient data. As such fuzzy and interval theory are becoming powerful tools for many applications in the recent decades. Accordingly, in this paper identification methodologies for structural systems has been proposed using the powerful technique of Artificial Neural Network (ANN) models which can handle uncertain data in term of interval/fuzzy. Identification with crisp data is known and also neural network method has already been used by various researchers for this case. Here, the input and output data may be in uncertain form. Uncertain data is assumed in term of interval/fuzzy and the corresponding problem of system identification through the solution of complex differential equations has been investigated.
Description: Copyright belongs to the proceeding of publisher
URI: http://hdl.handle.net/2080/2243
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
Chakraverty_S1.pdf3.13 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.