High Performance Structural Vibration Control by a Preview of the Future Seismic Waveform Generated With a Wave Transmission Network and an AI-Based Estimation System

Abstract

We propose a new active vibration control strategy based on the future seismic waveform information obtained in remote observation sites. The waveform information in the remote site is transmitted by a waveform transmission network to the structure under control. The waveform transmission network is realized by interconnecting multiple controlled structures and observation sites. By using the future waveform information obtained through the network, we propose a control law realizing fairly higher control performance over the conventional structural control methodologies. A preview control law consisting of the state-feedback and feedforward control (preview action) is adopted. For the preview action, future values of the disturbance in some time interval are necessary. However, because the future value of the earthquake waveform is unknown, the preview action contributing the performance improvement is generally impossible. To get over this difficulty, an AI-based wave estimation system to estimate the future earthquake waveform is proposed. The wave estimation system is a multi-layered artificial neural network (ANN). Through a small scale simulation study with a recorded earthquake event in Japan, we show that the proposed control method achieves much higher control performance over the conventional LQ-based active control.