Adaptive Neural Network Nonsingular Fast Terminal Sliding Mode Control for Permanent Magnet Linear Synchronous Motor

Zhao, Ximei; Fu, Dongxue

doi:10.1109/access.2019.2958569

Cited by 37 publications

(25 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the traditional rotating motor needs the complex transmission mechanisms, which virtually results in many shortcomings such as complex structure and low efficiency [7,8,9,10]. However, the simplification of the transmission link will lead to a series of uncertain factors acting on the actuator, thus increasing the difficulty of control [11,12,13].…”

Section: Introductionmentioning

confidence: 99%

High-precision motion control method for permanent magnet linear synchronous motor

Zhao

Yuan

2021

IEICE Electron. Express

Self Cite

View full text Add to dashboard Cite

In this paper, aiming at the known or unknown uncertainties in permanent magnet linear synchronous motor (PMLSM) servo system, an intelligent backstepping terminal sliding mode control (IBTSMC) method is proposed for accurate position tracking of the servo system. The designed controller makes use of the advantage of backstepping terminal sliding mode control theory to ensure fast convergence and robustness. Finally, the stability analysis is carried out by using Lyapunov stability theory, and the effectiveness of the designed control scheme is proved by experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

High-precision motion control method for permanent magnet linear synchronous motor

Zhao

Yuan

2021

IEICE Electron. Express

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, due to the lack of accurate modeling for system disturbances, the traditional SMC methods may not be sufficient in high speed and high accuracy systems, and thereby it is necessary to combine the SMC with additional compensators for disturbances suppression. Many improvements of SMC with additional compensation terms have been introduced, such as recursive least squares (RLS) compensator [23], disturbance observer [25], and neural networks [26,27]. Among them, the neural network compensator is widely used for suppressing disturbances, due to the model-free characteristics.…”

Section: Introductionmentioning

confidence: 99%

“…Yuen [26] has proposed a data-driven linear neural network to improve the tracking accuracy of an industrial PMLSM. In [27], an adaptive neural network non-singular fast terminal sliding mode control method was presented. A radial basis function (RBF) neural network was used to estimate the upper bound of PMLSM uncertainties.…”

Section: Introductionmentioning

confidence: 99%

Multi-Kernel Neural Network Sliding Mode Control for Permanent Magnet Linear Synchronous Motors

Wang

Ding

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In this paper, a multi-kernel neural network sliding mode control (MNNSMC) method is proposed to enhance the position tracking performance and disturbance suppression capability of permanent magnet linear synchronous motors (PMLSMs). The designed MNNSMC strategy consists of two parts, a sliding mode control with a dynamic boundary layer and a multi-kernel neural network (MNN). In the former, the dynamic boundary layer is utilized to guarantee that the sliding mode variable converges to the sliding manifold asymptotically. In the latter, disturbances are introduced into the design of kernel functions to further approximate and compensate for the internal and external disturbances, such as parameter variations, positioning force, friction, and un-modeled nonlinearities of PMLSMs. The stability of the proposed MNNSMC strategy is analyzed and proved based on Lyapunov Theorem. Experiments are conducted on a PMLSM servo drive system to validate the effectiveness of the presented MNNSMC method, and results show that the proposed scheme has significant improvement on the position tracking performance, disturbance suppression capability, and robustness of the PMLSM system compared with an existing method.INDEX TERMS PMLSM, disturbance suppression, multi-kernel neural network, dynamic boundary layer, sliding mode control.

show abstract

“…The Radial Basis Function Neural Networks (RBFNNs) have been extensively used in this regard. In [26], Terminal SMC was improved by using an adaptive RBNN to estimate unknown function in the model of Permanent Magnet Linear Synchronous Motor, and the adaptive law was used to estimate the upper bound of the model's uncertainty. In another work [27], the authors used RBF in the design process of terminal SMC.…”

Section: Introductionmentioning

confidence: 99%

Design of Sliding Mode Control for Complex Nonlinear Models: A Numerical Approach

Rehan

Al‐Durra

2020

IEEE Access

View full text Add to dashboard Cite

In this work, a numerical approach of formulating Sliding Model Control (SMC) is proposed to deal with complex nonlinear models of certain physical systems. Analytical formulation of SMC for such models is not possible as SMCs require algebraic manipulation of system equations, which is not achievable when the system model has strong nonlinearities. For such models, it is proposed to solve the SMC design using a numerical method that deals with numerical values instead of variables or functions in the equations. Mostly, SMC control law is dependent on the bounds of variables that are present in the mathematical expression of time derivatives of the sliding variable. To compute these bounds, a numerical approach is carried out using uncertainty bounds of the system's parameters. Also, a numerical approach is used to compute time derivatives of nonlinear functions that are required in the formulation of SMC. Various forms of SMCs are investigated in this respect, including the basic first-order SMC and a second-order SMC. The proposed framework is generalized as well, making it compatible with a wide range of nonlinear models whose algebraic manipulation is not possible. A prototype example of a nonlinear model of a boiler is used as a proof-of-concept. The simulation results are promising and prove the efficacy of the proposed approach.

show abstract

Adaptive Neural Network Nonsingular Fast Terminal Sliding Mode Control for Permanent Magnet Linear Synchronous Motor

Cited by 37 publications

References 24 publications

High-precision motion control method for permanent magnet linear synchronous motor

High-precision motion control method for permanent magnet linear synchronous motor

Multi-Kernel Neural Network Sliding Mode Control for Permanent Magnet Linear Synchronous Motors

Design of Sliding Mode Control for Complex Nonlinear Models: A Numerical Approach

Contact Info

Product

Resources

About