An operation support system based on database-driven on-demand predictive control

It is an important issue to support adequately operators in manual control systems. In this paper, we propose an operation support system based on database-driven on-demand predictive control. It is an application of the so-called just-in-time modeling method (also called model-on-demand) to predictive control. The effectiveness of the proposed method is illustrated by simulation of a braking system of trains.