基于FNTSM-ELM的机器人执行器控制策略

Control Strategy for Position Control of Robotic Actuator via FNTSM-ELM

针对机器人执行器系统强非线性及参数不确定性,提出了一种极限学习机(ELM)自适应误差估计的快速非奇异终端滑模(FNTSM)控制算法。通过使用快速非奇异终端滑模面和输出跟踪结构,同时从闭环系统全局稳定性的角度出发,利用Lyapunov稳定性意义自适应调整ELM的输出权值,给出了闭环稳定性和有限时间收敛性,保证了系统的快速误差收敛特性和高跟踪精度,实现对系统集总不确定性上界的自适应误差估计。提出的控制方法不仅可以实现有限时间误差收敛,而且不需要预知集总不确定性界。仿真结果证明,所提出的控制方法与现有自适应滑模等控制方法相比,在跟踪以及抗干扰能力方面的显著性能。

Aiming at the strong nonlinearity and parameter uncertainty of robot actuator system, a fastnonsingular terminal sliding mode(FNTSM) control algorithm based on limit learning machine(ELM) adaptive errorestimation is proposed. The fast terminal sliding mode surface and the output tracking structure with the outputweights of the ELM were adaptively adjusted in Lyapunov sense from the perspective of global stability of the closedloop system to improve performance of the position tracking, accomplish the adaptive estimation of the lumped uncer-tainty bound and realize the closed-loop stability and finite-time convergence. The proposed control strategy can thusnot only realize the finite-time error convergence but also need no prior knowledge of lumped uncertainty. The simula-tion results verify the excellent tracking performance and anti-interference ability of the proposed control in compari-son with other existing control methods.