Cooperative Adaptive Iterative Learning Fault-Tolerant Control Scheme for Multiple Subway Trains

Area of Science:

• Control Systems Engineering
• Artificial Intelligence in Transportation
• Robotics and Automation

Background:

• Subway systems face complex challenges including nonlinear dynamics and actuator faults.
• Ensuring safe headway distances and precise speed tracking is critical for efficient urban transit.
• Existing control methods may struggle with time-varying faults and system nonlinearities.

Purpose of the Study:

• To propose a novel cooperative adaptive iterative learning fault-tolerant control (CAILFTC) algorithm for multiple subway trains.
• To address challenges posed by time-iteration-dependent actuator faults in subway train systems.
• To ensure asymptotic convergence of speed tracking errors and maintain safe headway distances.

Main Methods:

• Utilizing a radial basis function neural network (RBFNN) to model and compensate for unknown nonlinearities.
• Applying a composite energy function (CEF) technique to guarantee system stability and convergence properties.
• Developing a cooperative control strategy for multiple interconnected subway trains.

Main Results:

• The proposed CAILFTC algorithm effectively handles time-iteration-dependent actuator faults.
• Demonstrated asymptotic convergence of all train speed tracking errors along the iteration axis.
• Successfully maintained safe headway distances between neighboring subway trains throughout the simulation.

Conclusions:

• The developed CAILFTC algorithm provides a robust and effective solution for fault-tolerant control of subway trains.
• The integration of RBFNN and CEF techniques ensures reliable performance even with system nonlinearities and faults.
• Simulation results validate the theoretical framework, highlighting its practical applicability in real-world subway operations.