Localized genetically optimized wavelet neural network for semi-active control of buildings subjected to earthquake

Abstract

Control algorithm is one of the most important aspects in successful control of buildings against earthquake. In recent years, because of their capabilities, soft computing methods, stemmed from human brain abilities, have become of particular interest to researchers. In this paper, a wavelet neural network-based semi-active control model is proposed in order to provide accurately computed input voltage to the magneto rheological dampers to generate the optimum control force of structures. This model is optimized by a localized genetic algorithm and then applied to a nine-story benchmark structure subjected to 1.5× El Centro earthquake. The results show an average of 43% reduction of maximum drift in the controlled structure versus the uncontrolled one. The capability of the controller is also validated by applying other far-field and near-field earthquakes. The capability and efficiency of the proposed model are demonstrated in terms of drift, acceleration and base shear reduction. The proposed wavelet neural network is also compared with a tangent hyperbolic-based feed forward neural network, linear quadratic Gaussian, clipped optimal controller, and genetic algorithm-based fuzzy inference systems to show the superiority of the proposed controller. Copyright © 2016 John Wiley & Sons, Ltd.