Robust fast nonsingular terminal sliding mode control strategy for electronic throttle based on extreme learning machine
Youhao Hu, Hai Wang, Zhenwei Cao, Zhihong Man, Ming Yu, Zhaowu Ping · 2019
This paper proposes an extreme-learning-machine-based robust fast nonsingular terminal sliding mode control (FNTSMC) strategy for an electronic throttle (ET) system. Distinguished from the conventional implementations of sliding mode control (SMC), the prior knowledge of disturbance bound is not required but estimated by the novel neural networks titled as extreme learning machine (ELM) which features in the fast learning rate and excellent generalization. The unique of the proposed control strategy lies on that both the sliding variable and system state enjoy a finite-time convergence without the information of predetermined bound of system nonlinearities and disturbances. The comparative simulations are conducted to verify the effectiveness and robustness of the proposed control strategy.