RNN-Embedding Compensation Fault Tolerant Control for High-Speed Trains With Actuator Saturation

• Published in: IEEE transactions on intelligent transportation systems pp. 1 - 12
• Main Authors: Hao, Zixu, Liu, Yumei, Hu, Ting, Liu, Pengcheng, Liu, Ming
• Format: Journal Article
• Language: English
• Published: IEEE 01.01.2025
• Subjects: actuator faults; Actuators; Adaptation models; adaptive control; Design methodology; Fault tolerant systems; Fault-tolerant control; high-speed trains (HSTs); Lyapunov methods; Neural networks; Nonlinear dynamical systems; Recurrent neural networks; Target tracking; Uncertainty
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2025.3589395

In this paper, a recurrent neural network (RNN) embedding compensation control scheme for a high-speed train (HST) subject to unknown dynamic, unknown disturbances, actuator faults and asymmetric nonlinear actuator saturation is investigated. The adaptive non-singular fast terminal sliding mode fault-tolerant controller with mix basis function approximator (MBF) and disturbance observer (DOB) is proposed as base controller of RNN-embedding compensation control. The MBF is used to approximate unknown dynamic terms in HST system and eliminate the asymmetric nonlinear actuator saturation. The DOB is used to observe unknown disturbances. Then, RNN-embedding compensation control scheme are proposed to optimize the performance of the base controller. The RNN-embedding compensation controller based on uniformly ultimately bounded Lyapunov stability is embedded to the base controller and the equivalent objective function is given to optimize the RNN. Finally, simulation results based on a real train dynamic model are presented to show the proposed schemes' effectiveness and feasibility.