Control of the Magnetic Suspension System with a Three-degree-of-freedom Using RBF Neural Network Controller

Saberi, Mohammad; Altafi, Hamid; Alizadeh, Seyyed Morteza

doi:10.7763/ijcee.2012.v4.462

Cited by 4 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… average levitation (AL) -performances are similar with performances obtained from three control logics (Section II),  stabilized levitation (SL) -one position levitation performances were improved (obtained in [15]),  no levitation state (NLS) -levitation of the ball was not performed,  levitation with motions (LWM) -two position levitation was obtained.…”

Section: Newly Developed Neural Network and Experimental Resultssupporting

confidence: 53%

“…Usage of a feedforward network with one hidden layer in levitation control logic is presented in [14]. An intelligent method is proposed for controlling three degrees of freedom of magnetic suspension system in [15]. Educational paper [16] describes a real-time digital control environment with a magnetic levitation device usage, optimized for neural network implementation.…”

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

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: Newly Developed Neural Network and Experimental Resultssupporting

confidence: 53%

Section: Introductionmentioning

confidence: 99%

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

“…The selection of node m at node n has the probability P Y mn (t), as shown in (18). This relation is used by the ants, for complete construction of the solution, in each generation of the algorithm.…”

Section: A Ant Colony Optimization (Aco)mentioning

confidence: 99%

“…Experiments performed on a system with predefined control signals has shown that the levitation amplitude of the designated levitation object upon surpassing 10 −4 m doesn't provide sustainable double levitation. The neural network has been developed on the basis of standard sigmoid and tangent functions by utilizing the real observational evidence [18]- [22]. Default activation functions were replaced with new orthogonal polynomial functions [23]- [25].…”

Section: Introductionmentioning

confidence: 99%

Design and Control of Magnetic Levitation System by Optimizing Fractional Order PID Controller Using Ant Colony Optimization Algorithm

Mughees

Mohsin

2020

IEEE Access

View full text Add to dashboard Cite

MAGnetic LEVitation (Maglev) is a multi-variable, non-linear and unstable system that is used to levitate a ferromagnetic object in free space. This paper presents the stability control of a levitating object in a magnetic levitation plant using Fractional order PID (FOPID) controller. Fractional calculus, which is used to design the FOPID controller, has been a subject of great interest over the last few decades. FOPID controller has five tunning parameters including two fractional-order parameters (λ and µ). The mathematical model of the Maglev plant is obtained by using first principle modeling and the laboratory model (CE152). Maglev plant and FOPID controller both have been designed in MATLAB-Simulink. The designed model of the Maglev system can be further used in the process of controller design for other applications. The stability of the proposed system is determined via the Routh Hurwitz stability criterion. Ant Colony Optimization (ACO) algorithm and Ziegler Nichols method has been used to finetune the parameters of FOPID controller. FOPID controller output results are compared with the traditional IOPID controller for comparative analysis. FOPID controller, due to its extra tuned parameters, has shown extremely efficient results in comparison to the traditional IOPID controller.

show abstract

“…By the characteristic of open loop instability concerned to magnetic levitation systems, it is essential the development of efficient controllers to manipulate the position of objects under this situation, influencing the safeness and comfort of the passengers using a transportation under this working principle [5].…”

Section: Introductionmentioning

confidence: 99%

PID Control Design for a Maglev Train System

Gilson¹,

José

2013

AMM

View full text Add to dashboard Cite

This document presents an application of a PID (proportional, integral and derivative) controller designed by the pole placement technique and applied to a Maglev (Magnetic Levitation) train system plant. The linearization with Taylor Series is demonstrated including the development of the formulas to calculate the parameters of the controllers to three operation points and the performance of each controller is tested under disturbances, and switching controllers between the plants for different operating conditions.

show abstract

Control of the Magnetic Suspension System with a Three-degree-of-freedom Using RBF Neural Network Controller

Cited by 4 publications

References 15 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

Design and Control of Magnetic Levitation System by Optimizing Fractional Order PID Controller Using Ant Colony Optimization Algorithm

PID Control Design for a Maglev Train System

Contact Info

Product

Resources

About