Parameter-Insensitive Non-Repetitive Iterative Learning Operation Control of High-Speed Train Subject to Safety Constraints

The periodic operation pattern of high-speed train (HST) grants the immense potential for iterative learning control (ILC) approach regulating the displacement and velocity, but the non-repetitive uncertainties caused by carrying loads, random disturbances, etc., may weaken the capability of controller. Further, the typical operating situations of rail transit, e.g., station entrance/exit, slowdown sections, can compress the safety margin of HST, increasing the difficulty of precise tracking. In this paper, an adaptive ILC scheme is proposed for HST subject to the safety constraints, where the unknown iteration-varying parameters and the modeling inaccuracies are handled deliberately. Our technical route could be divided into two phases. The transformation mechanism of tracking errors, that can convert the control problem of constrained systems into an unconstrained form, is first established to guarantee that HST is always located within the safety zone. On this basis, the iterative learning controller is devised through integrating the hyperbolic tangent function and iteration-related sequence, where the neural network is leveraged to approximate the unmodeled lumps. The main innovative features lie in that, the iteration-dependent terms of control system are evolved into the parametric compensation components of controller and the iterative convergence parts, while the nested structure of control law is built to accommodate the iteration-variation of loads. As a result, the proposed approach can theoretically achieve the zero-error tracking of HST in the presence of the non-repetitive uncertainties and safety constraints, which indicates the better performance and practicability than the existing ones.