Abstract
This paper presents a response evaluator as a semi-active control method for base isolated building in long-period earthquake response analysis. The absolute acceleration of each story and relative displacement of an isolated layer are the input signals and switching parameter for the damping coefficient is the output signal of the response evaluator. The response evaluator is designed by a multilayered neural network, and a genetic algorithm is used to adjust the neural network parameters which decide the performance of the response evaluator. Four oil dampers are installed at the isolated layer and each damping coefficient of the dampers is set to different value to correspond to various characteristics of earthquake motions, then the total damping force of the isolated layer is multi-step values regardless of using the oil dampers with two-step damping coefficient. By the numerical simulation with the proposed semi-active control method, both the acceleration of each story and the displacement of isolated layer which are trade-off relations with each other are reduced compared with the acceleration in case of all damping coefficient small (soft) and the displacement of isolated layer in case of all damping coefficient large (hard).
