Li-Tao Teng

Intelligent Sliding-Mode Control Using RBFN for Magnetic Levitation System

An intelligent sliding-mode control system using a radial basis function network (SMCRBFN) is proposed to control the position of a levitated object of a magnetic levitation system to compensate the uncertainties including the friction force in this study. First, the dynamic model of the magnetic levitation system is derived. Then, a sliding-mode approach is proposed to compensate the uncertainties that occurred in the magnetic levitation system. Moreover, to relax the requirement of uncertainty bound in the design of a traditional sliding-mode control system and further increase the robustness of the magnetic levitation system, a radial basis function network estimator is proposed to estimate the uncertainties of the system dynamics online. The effectiveness of the proposed control scheme is verified by some experimental results. With the proposed SMCRBFN system, the position of the levitated object of the magnetic levitation system possesses the advantages of good transient control performance and robustness to uncertainties for tracking periodic trajectories

Adaptive control with hysteresis estimation and compensation using RFNN for piezo-actuator

Because the control performance of a piezoactuator is always severely deteriorated due to hysteresis effect, an adaptive control with hysteresis estimation and compensation using recurrent fuzzy neural network (RFNN) is proposed in this study to improve the control performance of the piezo-actuator. A new hysteresis model by modifying and parameterizing the hysteresis friction model is proposed. Then, the overall dynamics of the piezo-actuator is completed by integrating the parameterized hysteresis model into a mechanical motion dynamics. Based on this developed dynamics, an adaptive control with hysteresis estimation and compensation is proposed. However, in the designed adaptive controller, the lumped uncertainty E is difficult to obtain in practical application. Therefore, a RFNN is adopted as an uncertainty observer in order to adapt the value of the lumped uncertainty E on line. And, some experimental results show that the proposed controller provides high-performance dynamic characteristics and is robust to the variations of system parameters and external load

Intelligent Adaptive Backstepping Control System for Magnetic Levitation Apparatus

We propose an intelligent adaptive backstepping control system using a recurrent neural network (RNN) to control the mover position of a magnetic levitation apparatus to compensate for uncertainties, including friction force. First, we derive a dynamic model of the magnetic levitation apparatus. Then, we suggest an adaptive backstepping approach to compensate disturbances, including the friction force, occurring in the motion control system. To further increase the robustness of the magnetic levitation apparatus, we propose an RNN estimator for the required lumped uncertainty in the adaptive backstepping control system. We further propose an online parameter training methodology, derived by the gradient descent method, to increase the learning capability of the RNN. The effectiveness of the proposed control scheme has been verified by experiment. With the proposed adaptive backstepping control system using RNN, the mover position of the magnetic levitation apparatus possesses the advantages of good transient control performance and robustness to uncertainties for the tracking of periodic trajectories

Adaptive displacement control with hysteresis modeling for piezoactuated positioning mechanism

An adaptive displacement control with hysteresis modeling for a piezoactuated positioning mechanism is proposed in this paper because the dynamic performance of piezosystems is often severely deteriorated due to the hysteresis effect of piezoelectric elements. First, a new mathematical model based on the differential equation of a motion system with a parameterized hysteretic friction function is proposed to represent the dynamics of motion of the piezopositioning mechanism. As a result, the mathematical model describes a motion system with hysteresis behavior due to the hysteretic friction. Then, by using the developed mathematical model, the adaptive displacement tracking control with the adaptation algorithms of the parameterized hysteretic function and of an uncertain parameter is proposed. By using the proposed control approach on the displacement control of the piezopositioning mechanism, the advantages of the asymptotical stability in displacement tracking, high-performance displacement response, and robustness to the variations of system parameters and disturbance load can be provided. Finally, experimental results are illustrated to validate the proposed control approach for practical applications.

Hybrid controller with recurrent neural network for magnetic levitation system

We propose a hybrid controller using a recurrent neural network (RNN) to control a levitated object in a magnetic levitation system. We describe a nonlinear dynamic model of the system and propose a computed force controller, based on feedback linearization, to control the position of the levitated object. To relax the requirement of the lumped uncertainty in the design of the computed force controller, an RNN functions as an uncertainty observer to adapt the lumped uncertainty on line. The computed force controller, the RNN uncertainty observer, and a compensated controller are embodied in a hybrid controller, which is based on Lyapunov stability. The computed force controller, with the RNN uncertainty observer, is the main tracking controller, and the compensated controller compensates the minimum approximation error of the RNN uncertainty observer. To ensure the convergence of the RNN, the adaptation law of the RNN is modified by using a projection algorithm. Experimental results illustrate the validity of the proposed control design for the magnetic levitation system.

An Induction Generator System Using Fuzzy Modeling and Recurrent Fuzzy Neural Network

A frequency controlled three-phase induction generator (IG) system using ac-dc power converter is developed in this study. The electric frequency of the IG is controlled using the indirect field-oriented control mechanism. Moreover, an ac-dc power converter is adopted to convert the electric power generated by a three-phase IG from variable-frequency and variable-voltage to constant dc voltage. The rotor speed of the IG, the dc-link voltage and current of the power converter are detected simultaneously to yield maximum power output of the IG through dc-link power control. In this study, first, the indirect field-oriented mechanism is designed for the control of the IG. Then, a novel fuzzy modeling is developed to determine the flux control current and the maximum output power of the IG according to the rotor speed and the desired terminal voltage of the IG. Moreover, an online training recurrent fuzzy neural network (RFNN) with backpropagation algorithm is introduced as the tracking controller of dc-link power. Furthermore, some experimental results are provided to show the effectiveness of the proposed IG system using the RFNN controller for the dc-link power control. Finally, the control performance of the dc-link voltage control using the RFNN is also discussed by some experimental results

A Robust Recurrent Wavelet Neural Network Controller With Improved Particle Swarm Optimization for Linear Synchronous Motor Drive

A robust recurrent wavelet neural network (RWNN) controller is proposed in this study to control the mover of a permanent magnet linear synchronous motor (PMLSM) servo drive to track periodic reference trajectories. First, the dynamic model of the PMLSM drive system is derived. Next, a perfect control law designed in the sense of feedback linearization is derived. However, in the perfect control law, the exact values of the system parameters, external force disturbance, and friction force are unknown in practical applications. Therefore, an RWNN is proposed to mimic the perfect control law and a robust compensator is proposed to compensate the approximation error. Moreover, the online learning algorithms of the connective weights, translations, and dilations of the RWNN are derived using Lyapunov stability and back-propagation (BP) method. Furthermore, an improved particle swarm optimization (IPSO) is adopted in this study to adapt the learning rates of the RWNN to improve the learning capability. Finally, the control performance of the proposed robust RWNN controller with IPSO is verified by some simulated and experimental results.

Adaptive Backstepping Control System for Magnetic Levitation Apparatus Using Recurrent Neural Network

An adaptive backstepping control system using a recurrent neural network (RNN) is proposed to control the mover position of a magnetic levitation apparatus to compensate the uncertainties including the friction force in this study. First, the dynamic model of the magnetic levitation apparatus is derived. Then, an adaptive backstepping approach is proposed to compensate disturbances including the friction force occurring in the motion control system. Moreover, to further increasing of the robustness of the magnetic levitation apparatus, a RNN uncertainty estimator is proposed to estimate the required lumped uncertainty in the adaptive backstepping control system. Furthermore, an on-line parameter training methodology, which is derived using the gradient descent method, is proposed to increase the learning capability of the RNN. The effectiveness of the proposed control scheme is verified by some experimental results. With the proposed adaptive backstepping control system using RNN, the mover position of the magnetic levitation apparatus possesses the advantages of good transient control performance and robustness to uncertainties for the tracking of periodic trajectories.