A Novel Automatic Train Operation Algorithm Based on Iterative Learning Control Theory

This paper applies iterative learning control (ILC) theory into the automatic train operation (ATO) system to make the train drive itself consistently with the given guidance trajectory (including velocity trajectory and coordinate trajectory). Different from other studies before, this ILC-based algorithm makes full use of the available information obtained from previous running cycles to adjust the current driving strategy. Through rigorous analysis, it is shown that the train controlled by the ILC based ATO system can effectively track the guidance trajectory without deviation after repeating the same trip enough times. And then, safety requirement, a crucial factor in the railway system, is taken into consideration and well disposed. At last, the numerical simulation verifies the validity of the proposed algorithm.