Direct decentralized neural control for nonlinear MIMO magnetic levitation system

A direct modified Elman neural networks (MENNs)-based decentralized controller is proposed to control the magnets of a nonlinear and unstable multi-input multi-output (MIMO) levitation system for the tracking of reference trajectories. First, the operating principles of a magnetic levitation system with two moving magnets are introduced. Then, due to the exact dynamic model of the MIMO magnetic levitation system is not clear, two MENNs are combined to be a direct MENN-based decentralized controller to deal with the highly nonlinear and unstable MIMO magnetic levitation system. Moreover, the connective weights of the MENNs are trained online by back-propagation (BP) methodology and the convergence analysis of the tracking error using discrete-type Lyapunov function is provided. Based on the direct and decentralized concepts, the computational burden is reduced and the controller design is simplified. Furthermore, the experimental results show that the proposed control scheme can control the magnets to track various periodic reference trajectories simultaneously in different operating conditions effectively.

[1]  H.A. Toliyat,et al.  Artificial-neural-network-based sensorless nonlinear control of induction motors , 2005, IEEE Transactions on Energy Conversion.

[2]  D. T. Psent,et al.  Training of Elman networks and dynamic system modelling , .

[3]  D. L. Trumper,et al.  Linearizing control of magnetic suspension systems , 1997, IEEE Trans. Control. Syst. Technol..

[4]  Shuzhi Sam Ge,et al.  Adaptive neural control of uncertain MIMO nonlinear systems , 2004, IEEE Transactions on Neural Networks.

[5]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[6]  Rong-Jong Wai,et al.  Fuzzy neural network position controller for ultrasonic motor drive using push-pull DC-DC converter , 1999 .

[7]  Thomas R. Grochmal,et al.  Precision Tracking of a Rotating Shaft With Magnetic Bearings by Nonlinear Decoupled Disturbance Observers , 2007, IEEE Transactions on Control Systems Technology.

[8]  Amar Goléa,et al.  Fuzzy model reference adaptive control , 2002, IEEE Trans. Fuzzy Syst..

[9]  Liu Hongmei,et al.  Fault Diagnosis Based on Improved Elman Neural Network for a Hydraulic Servo System , 2006, 2006 IEEE Conference on Robotics, Automation and Mechatronics.

[10]  Jin-Ho Seo,et al.  Design and analysis of the nonlinear feedback linearizing control for an electromagnetic suspension system , 1996, IEEE Trans. Control. Syst. Technol..

[11]  David W. L. Wang,et al.  Designing stable MIMO fuzzy controllers , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Li-Chen Fu,et al.  A novel dual-axis repulsive Maglev guiding system with permanent magnet: modeling and controller design , 2003 .

[13]  Yie-Chien Chen,et al.  A model reference control structure using a fuzzy neural network , 1995 .

[14]  M. Ono,et al.  Japan's superconducting Maglev train , 2002 .

[15]  J. Kaloust,et al.  Nonlinear robust control design for levitation and propulsion of a maglev system , 2004 .

[16]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[17]  H.-k. Chiang,et al.  Integral variable-structure grey control for magnetic levitation system , 2006 .

[18]  Ming Liu,et al.  Decentralized control of robot manipulators: nonlinear and adaptive approaches , 1999, IEEE Trans. Autom. Control..

[19]  Chih-Chiang Cheng,et al.  Design of adaptive sliding surfaces for systems with mismatched perturbations to achieve asymptotical stability , 2007 .

[20]  D. J. Ballance,et al.  MIMO nonlinear PID predictive controller , 2002 .

[21]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[22]  Min Wang,et al.  Robust neuro-fuzzy sensor-based motion control among dynamic obstacles for robot manipulators , 2003, IEEE Trans. Fuzzy Syst..

[23]  Xiang Li,et al.  Chaotifying linear Elman networks , 2002, IEEE Trans. Neural Networks.

[24]  D. M. Rote,et al.  A review of dynamic stability of repulsive-force maglev suspension systems , 1998 .

[25]  C.-S. Chiu.  Robust adaptive control of uncertain MIMO non-linear systems - feedforward Takagi-Sugeno fuzzy approximation based approach , 2005 .

[26]  Paul I. Ro,et al.  Magnetic servo levitation by sliding-mode control of nonaffine systems with algebraic input invertibility , 2005, IEEE Transactions on Industrial Electronics.

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

[28]  Min Chen,et al.  Control Approaches to the Suppression of Machining Chatter Using Active Magnetic Bearings , 2007, IEEE Transactions on Control Systems Technology.

[29]  Zi-Jiang Yang,et al.  Adaptive robust nonlinear control of a magnetic levitation system via DSC technique , 2001, Autom..

[30]  William Gerard Hurley,et al.  Electromagnetic design of a magnetic suspension system , 1997 .

[31]  Xinghuo Yu,et al.  Terminal sliding mode control of MIMO linear systems , 1997 .

[32]  Jun Tang,et al.  A fuzzy-Gaussian neural network and its application to mobile robot control , 1996, IEEE Trans. Control. Syst. Technol..

[33]  Quanmin Zhu,et al.  Backstepping-enhanced decentralised PID control for MIMO processes with an experimental study , 2007 .