Optimization of Urban Rail Automatic Train Operation System Based on RBF Neural Network Adaptive Terminal Sliding Mode Fault Tolerant Control

Aiming at the problem of large tracking error desired curve for automatic train operation (ATO) control strategy, an ATO algorithm based on RBF neural network adaptive terminal sliding mode fault-tolerant (ATSM-FTC-RBFNN) is proposed to realize accurate curve. On one hand, considering state delay trains in operation, a nonlinear dynamic model established mechanism motion mechanics. Then, principle used design algorithm, and introduced enhance adaptability system. other RBFNN adaptively approximate compensate additional resistance disturbance so that with larger can be realized smaller switching gain, performance anti-interference ability system enhanced. Finally, actuator failure input limitation, further The simulation results show process effects saturation, delay, faults synchronously under condition uncertain parameters, external disturbances achieve small