Nonlinear Internal Model Control for Bearingless Induction Motor Based on Neural Network Inversion

Wang, Zheng-Qi; Liu, Xianxing

doi:10.1016/s1874-1029(13)60043-9

Cited by 20 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Substituting (12), (13), and (14) into (1), (2), and (10), then the state equations of the BLIM system can be derived as follows:̇1…”

Section: Inverse System Decouplingmentioning

confidence: 99%

“…In addition, to improve the control performance of the torque system, the rotor flux orientation is usually adopted. About the inverse system decoupling control strategy of the BLIM based on the rotor flux orientation, there has been some research progress [13][14][15]. But for the magnetic suspension system, the air gap flux-linkage of the torque system is required in the model of magnetic suspension force.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Decoupling Control Strategy of BLIM considering Rotor Mass Eccentricity

2018

Journal of Control Science and Engineering

View full text Add to dashboard Cite

A BLIM, i.e., bearingless induction motor, is a multivariable, nonlinear, and strong coupling object; to achieve its high performance magnetic suspension operation control and overcome the influence of the rotor mass eccentricity, a decoupling control strategy considering the rotor mass eccentricity is proposed. Firstly, the mathematical model of the torque system based on the rotor flux orientation and the mathematical model of the magnetic suspension system based on the air gap flux orientation are presented; on this basis, the inverse system decoupling control method of the BLIM is researched. Then, according to the frequency characteristics of the unbalanced displacement, an unbalance vibration compensator is designed, which can generate a compensation force to suppress or eliminate the unbalanced displacement. Simulation experimental results have shown that the decoupling control among the rotor flux-linkage, motor speed, and two radial displacement components can be achieved; in the steady state, the unbalanced displacement can be basically eliminated, while, during the mutation process of motor speed, the unbalanced displacement can be suppressed effectively.

show abstract

“…Substituting (12), (13), and (14) into (1), (2), and (10), then the state equations of the BLIM system can be derived as follows:̇1…”

Section: Inverse System Decouplingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Decoupling Control Strategy of BLIM considering Rotor Mass Eccentricity

2018

Journal of Control Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Because of the robust and compact structure, the bearingless induction motor has become a hot research topic , , but there exists a complicated electromagnetic coupling in the bearingless induction motor . To achieve its high performance control, it is necessary to realize the dynamic decoupling between different variables.…”

Section: Introductionmentioning

confidence: 99%

“…The inverse system method is applicable for the linearization decoupling of a multivariable, nonlinear and strong coupling object. Under the rotor, air gap and stator flux orientation conditions, references have studied the inverse system decoupling methods of the bearingless induction motor. Furthermore, in order to improve the antidisturbance ability, a robust servo regulator is designed for each pseudolinear system ; however, there are no further studies on the effects of motor parameters on the control performance.…”

Section: Introductionmentioning

confidence: 99%

Sliding mode variable structure control strategy of bearingless induction motor based on inverse system decoupling

Zhang

2018

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

A bearingless induction motor is a multivariable, nonlinear and strong coupling object. To achieve its dynamic decoupling control with high performance and improve the system stability, a sliding mode variable structure (SMVS) control strategy based on inverse system decoupling is proposed. First, taking the stator current as the control variable, by means of inverse system method, the bearingless induction motor system is decoupled into four pseudolinear subsystems, including motor speed subsystem, rotor flux‐linkage subsystem and two radial displacement component subsystems. Then, according to the SMVS control theory, the regulator is designed for each subsystem. To overcome the chattering problem of the system, an exponential reaching law is introduced to the SMVS regulator; based on Lyapunov theory, system stability is analyzed. From the simulation experimental results, it is clear that the system has better dynamic decoupling control performance, a stronger ability to resist load disturbance and stronger robustness to the variation of motor parameters. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

“…For example, a MLP was applied for optimizing the gains of a Proportional-Integral-Derivative (PID) controller to act as the controller of an IMC system [3]. In addition, an IMC structure, which uses a NN with 22 hidden nodes, was utilized for the control of an induction motor [4]. In another work, an IMC structure with a large MLP network was exploited for the control of nonlinear systems.…”

Section: Introductionmentioning

confidence: 99%

Internal Model Control Using a Self-Recurrent Wavelet Neural Network Trained by an Artificial Immune Technique for Nonlinear Systems

Lutfy¹,

Majeed²

2018

ETJ

View full text Add to dashboard Cite

This paper presents a Self-Recurrent Wavelet Neural Network (SRWNN)-based Internal Model Control (IMC) for nonlinear systems. As the internal model, a Nonlinear Autoregressive Moving Average (NARMA-L2) is employed for obtaining a forward system model. Then, this model is directly used to formulate the control law. The proposed SRWNN-based IMC is an enhanced version of a previously published Wavelet Neural Network (WNN)-based IMC scheme. Particularly, the enhancement was attained by considering three modifications, which include the use of an initialization phase for the parameters of the wavelon layer, the utilization of self-feedback connections in the wavelon layer, and the exploitation of RASP1 as the mother wavelet function. The modified Micro Artificial Immune System (modified Micro-AIS) is employed as the training method. From the simulation results, the efficiency of the suggested methodology have been proved concerning control precision and disturbance rejection ability. Moreover, the superiority of the SRWNN over the WNN and the Multilayer Perceptron (MLP) as the IMC controllers has been confirmed from a comparative study. Furthermore, the modified Micro-AIS has accomplished better results compared to the Genetic Algorithm (GA) concerning control precision.

show abstract

Nonlinear Internal Model Control for Bearingless Induction Motor Based on Neural Network Inversion

Cited by 20 publications

References 10 publications

Decoupling Control Strategy of BLIM considering Rotor Mass Eccentricity

Decoupling Control Strategy of BLIM considering Rotor Mass Eccentricity

Sliding mode variable structure control strategy of bearingless induction motor based on inverse system decoupling

Internal Model Control Using a Self-Recurrent Wavelet Neural Network Trained by an Artificial Immune Technique for Nonlinear Systems

Contact Info

Product

Resources

About