Nonlinear modeling and control approach to magnetic levitation ball system using functional weight RBF network-based state-dependent ARX model

Qin, Yuwen; Peng, Hui; Feng, Zhou; Zeng, Xiaoyong; Wu, Jun

doi:10.1016/j.jfranklin.2015.06.014

Cited by 33 publications

(19 citation statements)

References 29 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complete necessary mathematical background of this orthogonal trigonometric polynomials can be found in [18]. The newly obtained generalized quasi-orthogonal polynomials of order k = 1 [20] were used for experimental purposes.…”

Section: Neural Network Activation Functions Based On Orthogonalmentioning

confidence: 99%

“…Reference control model of the levitation system is a neural network in [17] where the embedded linear model is used for network weights forming procedure. A hybrid model of a neural network, which is based on a radial basis function, is designed for modelling a MLS in [18]. The model is capable to control the levitation process and to provide precisely tracking of reference signal.…”

Section: Introductionmentioning

confidence: 99%

“…The model is capable to control the levitation process and to provide precisely tracking of reference signal. Finally, it can be concluded from [1]- [18] that systems which include soft computing techniques inside standard control logics could possess better control performances compared to conventional controllers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural Network Based on Orthogonal Polynomials Applied in Magnetic Levitation System Control

Milovanović¹,

Antić²,

Nikolić³

et al. 2017

ElAEE

View full text Add to dashboard Cite

This paper presents a new approach for improving performances of magnetic levitation system. Controlled parameter is the amplitude which levitated object achieves during movement from one levitation position to another. Two position levitation with improved amplitude performances is obtained by implementing orthogonal neural network in standard levitation control logic. Proposed network is a nonlinear autoregressive neural network with newly developed activation function based on orthogonal polynomials. Performed experiments on a system with default control logic showed that it could not provide stable two position levitation when specified amplitude of the levitation object is greater than 10-4 m. Artificial network was trained using real experimental data and it was based on standard tangent and sigmoid activation functions. Default activation functions were then substituted with a newly developed orthogonal polynomial functions. The amplitude 10-3 m was achieved with stable two position levitation after parameter optimization. It is proven that simple control logic with nonlinear autoregressive neural network and proper activation function can provide improved amplitude performances.

show abstract

Section: Neural Network Activation Functions Based On Orthogonalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Network Based on Orthogonal Polynomials Applied in Magnetic Levitation System Control

Milovanović¹,

Antić²,

Nikolić³

et al. 2017

ElAEE

View full text Add to dashboard Cite

show abstract

“…U(t + j) = U(t + N u À 1)(j ≥ N u ). In (14), the output prediction isŶ tþjjt j| t) is the j-step-ahead predictive output calculated from (11), and d(t) is a disturbance or modeling residual, which is estimated by…”

Section: Mimo Fwrbf-arx Model-based Mpc Strategymentioning

confidence: 99%

“…According to the multi-step-ahead prediction model (11)(12)(13)(14)(15)(16)(17)(18)(19), the output prediction can be derived aŝ whereŶ t ð Þ is the estimated model predictive output vector along the horizon N p , G t is the matrix of the dynamics, and Y 0 (t) is the free response vector. Defining the control increment sequence ΔÛ t ð Þ and the desired output sequenceŶ r t ð Þ as follows…”

Section: Mimo Fwrbf-arx Model-based Mpc Strategymentioning

confidence: 99%

Modeling and Control Approach to Coupled Tanks Liquid Level System Based on Function‐Type Weight RBF‐ARX Model

Feng

Peng

Zeng

et al. 2016

Asian Journal of Control

Self Cite

View full text Add to dashboard Cite

A multi‐input multi‐output (MIMO) FWRBF‐ARX model, which adopts radial basis function (RBF) neural networks with function‐type weights (FWRBF) to approximate the coefficients of the state‐dependent AutoRegressive model with eXogenous input variables (SD‐ARX), is utilized for describing the dynamics of a coupled tanks liquid system. Based on local linearization information of the MIMO FWRBF‐ARX model, a predictive control strategy is proposed. In the algorithm, the control actions of the model predictive control (MPC) are calculated based on the local linearization of the MIMO FWRBF‐ARX model at current working point. Real‐time control experiments are carried out on the coupled tanks liquid system. The detailed comparative experiments demonstrate the feasibility and effectiveness of the proposed modeling and model‐based control strategy for the coupled tanks plant.

show abstract

Modeling of Maglev Yaw System of Wind Turbines and its Robust Trajectory Tracking Control in the Levitating and Landing Process Based on Ndob

Cai

Song

et al. 2018

Asian Journal of Control

View full text Add to dashboard Cite

The yaw system is one of the important parts of the horizontal axis wind turbines. In this paper, a novel maglev yaw system (MYS) is introduced, a novel robust controller based on nonlinear disturbance observer (NDOB) is proposed to improve the dynamic suspension stability of the MYS in its levitating and landing process. First, the dynamic model of the MYS is built and analyzed as well as the model of the force caused by crosswind exerting on the MYS, and then the mathematical model of the MYS is derived from its dynamic model. Second, since the uncertain internal disturbance originated from the MYS itself exists, in order to realize the finite time convergence and improve the robustness of the MYS, a NDOB-based robust controller is designed via like nonsingular terminal sliding mode (LNTSM) method with the aid of backstepping design idea (BDI) to guarantee that the system output asymptotically tracks the reference trajectory, and the levitating and landing velocities of the MYS converge to their expectations globally and asymptotically in finite time. Finally, compared the conventional backstepping control (BC), the extensive simulation results show that the proposed robust controller has a better robustness and the MYS can realize smooth and reliable operations in its levitating and landing process in finite time, therefore the novel robust controller is substantiated to be effective and feasible.Key Words: Maglev yaw system (MYS), finite time, robust control, nonlinear disturbance observer based (NDOB), like nonsingular terminal sliding mode (LNTSM), backstepping design idea (BDI), backstepping control (BC).

show abstract

Nonlinear modeling and control approach to magnetic levitation ball system using functional weight RBF network-based state-dependent ARX model

Cited by 33 publications

References 29 publications

Neural Network Based on Orthogonal Polynomials Applied in Magnetic Levitation System Control

Neural Network Based on Orthogonal Polynomials Applied in Magnetic Levitation System Control

Modeling and Control Approach to Coupled Tanks Liquid Level System Based on Function‐Type Weight RBF‐ARX Model

Modeling of Maglev Yaw System of Wind Turbines and its Robust Trajectory Tracking Control in the Levitating and Landing Process Based on Ndob

Contact Info

Product

Resources

About