Fast nonsingular terminal sliding mode control for permanent-magnet linear motor via ELM
- PDF / 1,131,982 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 51 Downloads / 242 Views
(0123456789().,-volV)(0123456789(). ,- volV)
EXTREME LEARNING MACHINE AND DEEP LEARNING NETWORKS
Fast nonsingular terminal sliding mode control for permanent-magnet linear motor via ELM Jie Zhang1 • Hai Wang2 Farhad Shahnia2
•
Zhenwei Cao3 • Jinchuan Zheng3 • Ming Yu1 • Amirmehdi Yazdani2
•
Received: 16 January 2019 / Accepted: 5 September 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract In this paper, a novel fast nonsingular terminal sliding mode (FNTSM) control strategy using extreme learning machine (ELM) is proposed for permanent-magnet linear motor systems. It is shown that the developed FNTSM controller is composed of an equivalent control via ELM technique, a compensation control and a reaching control. Distinguished from the traditional ELM for pattern classification, output weights of the proposed ELM are adaptively adjusted by the adaptive law in Lyapunov sense from the global stability point of view, such that the equivalent control of the proposed controller can be flexibly estimated via ELM. Not only can the strong robustness and the faster convergence rate of the closed-loop control be guaranteed, but also the dependence of system dynamics can be further alleviated in the controller design due to the implementation of the ELM. Comparative simulation results are given to validate the robust control performance of the developed controller for both step tracking and sinusoidal tracking purposes. Keywords ELM Equivalent control FNTSM Permanent-magnet linear motor
1 Introduction With the rapid development of automatic control technology and microcomputers, the importance of position accuracy of the various automatic control systems has been highlighted. In this case, the conventional linear motion devices which are composed of rotary motor and conversion mechanism are far from meeting the requirement of modern control systems. Permanent-magnet linear motor (PMLM) can convert electrical energy into linear motion directly without any switching mechanism. Therefore, more and more researchers devote themselves to researching and developing PMLM [1, 2]. The PMLM has many advantages in the control systems, such as faster speed, larger pushing force and higher precision, compared
& Hai Wang [email protected] 1
Hefei University of Technology, Hefei 230009, China
2
Murdoch University, Perth, WA 6150, Australia
3
Swinburne University of Technology, Melbourne, VIC 3122, Australia
with the conventional linear motion devices [3, 4]. The primary control goal of PMLM is to design a controller such that the reference position trajectory can be tracked. However, it is a challenging work to obtain excellent performance and effectiveness due to various parametric uncertainties, nonlinear dynamic and disturbances such as backlash and frictional forces [5, 6]. In the last few decades, in order to solve the control problem of PMLM, numerous studies have been conducted on PMLM and many control strategies have been proposed to improve typical precision positioning requirement.
Data Loading...
