Non-linear system identification of the versatile-typed structures by a novel signal processing technique

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.