Distributed Learning Control for High-Speed Trains Subject to Operation Safety Constraints

Area of Science:

• Control Engineering
• Robotics
• Systems Science

Background:

• High-speed train (HST) trajectory tracking is crucial for operational safety and passenger comfort.
• Existing control methods often struggle to simultaneously address tracking accuracy and safety constraints.

Purpose of the Study:

• To propose a novel distributed learning control scheme for HSTs using a multiagent system framework.
• To ensure trajectory tracking while satisfying operation safety constraints under different train coupling modes.

Main Methods:

• Development of a multiagent system framework for distributed control.
• Analysis of relative displacement and speed constraints for train carriages.
• Construction of a barrier composite energy function to prove stability and constraint satisfaction.

Main Results:

• The proposed distributed learning control scheme effectively achieves trajectory tracking for HSTs.
• Rigorous mathematical proof demonstrates the convergence of tracking errors.
• Operation safety constraints are satisfied throughout the tracking process.

Conclusions:

• The multiagent-based distributed learning control is a viable approach for safe and accurate HST trajectory tracking.
• The method is robust to different train connection modes (soft and hard).
• Numerical simulations validate the theoretical findings and practical applicability.