Premium
Non‐linear system identification of the versatile‐typed structures by a novel signal processing technique
Author(s) -
Zhang Jian,
Sato Tadanobu,
Iai Susumu
Publication year - 2007
Publication title -
earthquake engineering and structural dynamics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.218
H-Index - 127
eISSN - 1096-9845
pISSN - 0098-8847
DOI - 10.1002/eqe.660
Subject(s) - identification (biology) , support vector machine , computer science , algorithm , power (physics) , system identification , signal processing , linear model , linear regression , signal (programming language) , mathematical optimization , artificial intelligence , data mining , mathematics , machine learning , digital signal processing , botany , physics , quantum mechanics , biology , programming language , measure (data warehouse) , computer hardware
Abstract Non‐linear structural identification problems have raised considerable research efforts since decades, in which the Bouc–Wen model is generally utilized to simulate non‐linear structural constitutive characteristic. Support vector regression (SVR), a promising data processing method, is studied for versatile‐typed structural identification. First, a model selection strategy is utilized to determine the unknown power parameter of the Bouc–Wen model. Meanwhile, optimum SVR parameters are selected automatically, instead of tuning manually. Consequently, the non‐linear structural equation is rewritten in linear form, and is solved by the SVR technique. A five‐floor versatile‐type structure is studied to show the effectiveness of the proposed method, in which both power parameter known and unknown cases are investigated. Copyright © 2007 John Wiley & Sons, Ltd.