Control of magnetic levitation system using recurrent neural network-based adaptive optimal backstepping strategy

In this paper, a novel approach is proposed for adjusting the position of a magnetic levitation system using projection recurrent neural network-based adaptive backstepping control (PRNN-ABC). The principles of designing magnetic levitation systems have widespread applications in the industry, including in the production of magnetic bearings and in maglev trains. Levitating a ball in space is carried out via the surrounding attracting or repelling magnetic forces. In such systems, the permissible range of the actuator is significant, especially in practical applications. In the proposed scheme, the procedure of designing the backstepping control laws based on the nonlinear state-space model is carried out first. Then, a constrained optimization problem is formed by defining a performance index and taking into account the control limits. To formulate the recurrent neural network (RNN), the optimization problem is first converted into a constrained quadratic programming (QP). Then, the dynamic model of the RNN is derived based on the Karush-Kuhn-Tucker (KKT) optimization conditions and the variational inequality theory. The convergence analysis of the neural network and the stability analysis of the closed-loop system are performed using the Lyapunov stability theory. The performance of the closed-loop system is assessed with respect to tracking error and control feasibility.

[1]  Sitian Qin,et al.  A recurrent neural network with finite-time convergence for convex quadratic bilevel programming problems , 2017, Neural Computing and Applications.

[2]  Chuandong Li,et al.  A Recurrent Neural Network for Solving Bilevel Linear Programming Problem , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[3]  D. Kinderlehrer,et al.  An introduction to variational inequalities and their applications , 1980 .

[4]  Xiangbo Xu,et al.  Internal model control for reduction of bias and harmonic currents in hybrid magnetic bearing , 2019, Mechanical Systems and Signal Processing.

[5]  N. Boonsatit,et al.  Adaptive Fast Terminal Sliding Mode Control of Magnetic Levitation System , 2016 .

[6]  Yanjun Shen,et al.  Finite-time recurrent neural networks for solving nonlinear optimization problems and their application , 2016, Neurocomputing.

[7]  Syuan-Yi Chen,et al.  Robust Dynamic Sliding-Mode Control Using Adaptive RENN for Magnetic Levitation System , 2009, IEEE Transactions on Neural Networks.

[8]  Mohamed Zribi,et al.  Sliding mode control of a magnetic levitation system , 2004, Mathematical Problems in Engineering.

[9]  Mir Behrad Khamesee,et al.  Real-time control of a magnetic levitation device based on instantaneous modeling of magnetic field , 2008 .

[10]  Kit Yan Chan,et al.  T–S Fuzzy-Model-Based Output Feedback Tracking Control With Control Input Saturation , 2018, IEEE Transactions on Fuzzy Systems.

[11]  Tahereh Binazadeh,et al.  Robust time-varying output tracking control in the presence of actuator saturation , 2018, Trans. Inst. Meas. Control.

[12]  Robain De Keyser,et al.  Fractional order control of unstable processes: the magnetic levitation study case , 2015 .

[13]  Qingshan Liu,et al.  A One-Layer Recurrent Neural Network with a Discontinuous Activation Function for Linear Programming , 2008, Neural Computation.

[14]  Jun Wang,et al.  A dual neural network for constrained joint torque optimization of kinematically redundant manipulators , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[15]  Ahmed El Hajjaji,et al.  Modeling and nonlinear control of magnetic levitation systems , 2001, IEEE Trans. Ind. Electron..

[16]  Alon Kuperman.  Uncertainty and disturbance estimator-assisted control of a two-axis active magnetic bearing , 2016 .

[17]  Romeo Ortega,et al.  State Observers for Sensorless Control of Magnetic Levitation Systems , 2017, Autom..

[18]  WangJun,et al.  A one-layer recurrent neural network for constrained nonconvex optimization , 2015 .

[19]  Yunong Zhang,et al.  Infinity-norm acceleration minimization of robotic redundant manipulators using the LVI-based primal-dual neural network , 2009 .

[20]  Jun Wang,et al.  A Novel Recurrent Neural Network for Solving Nonlinear Optimization Problems With Inequality Constraints , 2008, IEEE Transactions on Neural Networks.

[21]  Peng Shi,et al.  Finite-time command filtered backstepping control for a class of nonlinear systems , 2018, Autom..

[22]  Jun Wang,et al.  A one-layer recurrent neural network for constrained nonconvex optimization , 2015, Neural Networks.

[23]  Mohammad Farrokhi,et al.  Robust chattering-free optimal sliding-mode control using recurrent neural networks: An H∞-based approach , 2019 .

[24]  Shubao Liu,et al.  A Simplified Dual Neural Network for Quadratic Programming With Its KWTA Application , 2006, IEEE Transactions on Neural Networks.

[25]  Didier Dumur,et al.  Explicit nonlinear predictive control for a magnetic levitation system , 2010 .

[26]  Junqi Xu,et al.  Adaptive Neural-Fuzzy Robust Position Control Scheme for Maglev Train Systems With Experimental Verification , 2019, IEEE Transactions on Industrial Electronics.

[27]  Jovitha Jerome,et al.  LQR based Optimal Tuning of PID Controller for Trajectory Tracking of Magnetic Levitation System , 2013 .

[28]  Amor Chowdhury,et al.  Improved adaptive fuzzy backstepping control of a magnetic levitation system based on Symbiotic Organism Search , 2017, Appl. Soft Comput..

[29]  Xuyang Lou,et al.  A novel neural network for solving convex quadratic programming problems subject to equality and inequality constraints , 2016, Neurocomputing.

[30]  Yunong Zhang,et al.  Bi‐criteria optimal control of redundant robot manipulators using LVI‐based primal‐dual neural network , 2010 .

[31]  Yousef Alipouri,et al.  Constrained generalised minimum variance controller design using projection-based recurrent neural network , 2017 .

[32]  Wei Zhou,et al.  Backstepping Based Adaptive Control of Magnetic Levitation System , 2013 .

[33]  Yongzhi Jing,et al.  Compensation of gap sensor for high-speed maglev train with RBF neural network , 2013 .

[34]  Jun Wang,et al.  A Bi-Projection Neural Network for Solving Constrained Quadratic Optimization Problems , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[35]  Zhaobo Chen,et al.  Sliding mode control with deep learning method for rotor trajectory control of active magnetic bearing system , 2018, Trans. Inst. Meas. Control.

[36]  Changchun Hua,et al.  Backstepping Control for Nonlinear Time-Delay System via L-K Function , 2018 .

[37]  Qingshan Liu,et al.  A Projection Neural Network for Constrained Quadratic Minimax Optimization , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[38]  Michal Kvasnica,et al.  Real-time implementation of an explicit MPC-based reference governor for control of a magnetic levitation system , 2017 .

[39]  Edwin Lughofer,et al.  Modeling and control with neural networks for a magnetic levitation system , 2017, Neurocomputing.

[40]  Jun Wu,et al.  Nonlinear modeling and control approach to magnetic levitation ball system using functional weight RBF network-based state-dependent ARX model , 2015, J. Frankl. Inst..

[41]  Rong-Jong Wai,et al.  Design of backstepping particle-swarmoptimisation control for maglev transportation system , 2010 .

[42]  Monson H. Hayes,et al.  Statistical Digital Signal Processing and Modeling , 1996 .

[43]  Chenguang Yang,et al.  Model Predictive Control of Nonholonomic Chained Systems Using General Projection Neural Networks Optimization , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[44]  Rong-Jong Wai,et al.  Backstepping Fuzzy-Neural-Network Control Design for Hybrid Maglev Transportation System , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[45]  Faa-Jeng Lin,et al.  Intelligent Adaptive Backstepping Control System for Magnetic Levitation Apparatus , 2007, IEEE Transactions on Magnetics.