In this study, to improve the speed tracking performance of the switched reluctance motor (SRM), a control scheme combining fast terminal sliding mode (FTSM) control and radial basis function (RBF) neural network is proposed. First, the convergence characteristic of the FTSM control is derived, and a basic control scheme is designed to ensure the fast convergence of SRM speed tracking errors. Second, the RBF neural network with adaptive parameters is introduced to replace the equivalent control law, which avoids the requirement for the precise mathematical model information of the system. At the same time, considering the network approximation error and unknown external disturbances, an adaptive control law with variables gain is designed. The chattering phenomenon is suppressed and the robustness of the system is enhanced. The updated law of the controller and the stability of the closed-loop system are derived based on the Lyapunov stability theory. Finally, the simulation and experimental results of the SRM drive system show that the proposed control scheme has an excellent performance in terms of tracking accuracy, response speed, and robustness. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

中文翻译：

---

基于径向基函数神经网络的开关磁阻电机速度跟踪自适应快速终端滑模控制

在这项研究中，为了提高开关磁阻电机（SRM）的速度跟踪性能，提出了一种结合快速终端滑模（FTSM）控制和径向基函数（RBF）神经网络的控制方案。首先推导了FTSM控制的收敛特性，设计了一种基本的控制方案来保证SRM速度跟踪误差的快速收敛。其次，引入参数自适应的RBF神经网络替代等效控制律，避免了对系统精确数学模型信息的要求。同时，考虑网络逼近误差和未知外部干扰，设计了变增益自适应控制律。抑制了抖动现象，增强了系统的鲁棒性。基于Lyapunov稳定性理论推导了控制器的更新律和闭环系统的稳定性。最后，SRM驱动系统的仿真和实验结果表明，所提出的控制方案在跟踪精度、响应速度和鲁棒性方面具有优异的性能。© 2022 日本电气工程师协会。由 Wiley Periodicals LLC 出版。