Abstract
In Japan, after Hyogo-ken Nambu Earthquake in 1995, base isolated structures have been spread rapidly. Now, there are about 2800 base isolated buildings (apartment complex is 45%, hospital is 12% of all) and about 4300 base isolated houses in Japan. Base isolation technology was effect in The 2011 off the Pacific coast of Tohoku Earthquake. This paper presents the method of semi-active control design for base isolated structure with oil dampers whose damping coefficient can be available to set in two levels, which is to apply two different damping coefficients based on the proposed control design. The damping coefficients of the oil dampers are different each other. The control objective is reduction of both displacement of a base isolated layer and absolute acceleration of a base isolated building which are trade off relations each other. The layered neural network with Genetic Algorithm (GA) is applied to the semi-active control design. Absolute acceleration of the building and displacement of the isolated layer are the input signals of the neural network, and switching parameter for the damping coefficient is the output signal of the neural network. Genetic Algorithm is used to adjust the neural network parameters which decide the control performance. The target of control design is specified to permit the displacement of base isolated layer to the upper limit and to restrain the increase of building acceleration. We study the control performance of the proposed control method using several kinds of earthquake motions in the computer simulation.