Po-Hung Shen

Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive

A self-constructing fuzzy neural network (SCFNN) which is suitable for practical implementation is proposed. The structure and the parameter learning phases are performed concurrently and online in the SCFNN. The structure learning is based on the partition of input space and the parameter learning is based on the supervised gradient decent method using a delta adaptation law. Several simulation and experimental results are provided to demonstrate the effectiveness of the proposed SCFNN control stratagem with the implementation of a permanent-magnet synchronous motor speed drive. Moreover, the simulation results of time varying and nonlinear disturbances are given to show the dynamic characteristics of the proposed controller over a broad range of operating conditions.

Robust Fuzzy Neural Network Sliding-Mode Control for Two-Axis Motion Control System

A robust fuzzy neural network (RFNN) sliding-mode control based on computed torque control design for a two-axis motion control system is proposed in this paper. The two-axis motion control system is an x-y table composed of two permanent-magnet linear synchronous motors. First, a single-axis motion dynamics with the introduction of a lumped uncertainty including cross-coupled interference between the two-axis mechanism is derived. Then, to improve the control performance in reference contours tracking, the RFNN sliding-mode control system is proposed to effectively approximate the equivalent control of the sliding-mode control method. Moreover, the motions at x-axis and y-axis are controlled separately. Using the proposed control, the motion tracking performance is significantly improved, and robustness to parameter variations, external disturbances, cross-coupled interference, and friction force can be obtained as well. Furthermore, the proposed control algorithms are implemented in a TMS320C32 DSP-based control computer. From the simulated and experimental results due to circle and four leaves reference contours, the dynamic behaviors of the proposed control systems are robust with regard to uncertainties

An adaptive recurrent-neural-network motion controller for X-Y table in CNC Machine

In this paper, an adaptive recurrent-neural-network (ARNN) motion control system for a biaxial motion mechanism driven by two field-oriented control permanent magnet synchronous motors (PMSMs) in the computer numerical control (CNC) machine is proposed. In the proposed ARNN control system, a RNN with accurate approximation capability is employed to approximate an unknown dynamic function, and the adaptive learning algorithms that can learn the parameters of the RNN on line are derived using Lyapunov stability theorem. Moreover, a robust controller is proposed to confront the uncertainties including approximation error, optimal parameter vectors, higher-order terms in Taylor series, external disturbances, cross-coupled interference and friction torque of the system. To relax the requirement for the value of lumped uncertainty in the robust controller, an adaptive lumped uncertainty estimation law is investigated. Using the proposed control, the position tracking performance is substantially improved and the robustness to uncertainties including cross-coupled interference and friction torque can be obtained as well. Finally, some experimental results of the tracking of various reference contours demonstrate the validity of the proposed design for practical applications.

Adaptive fuzzy-neural-network control for a DSP-based permanent magnet linear synchronous motor servo drive

An adaptive fuzzy neural network (AFNN) control system is proposed to control the position of the mover of a field-oriented control permanent magnet linear synchronous motor (PMLSM) servo-drive system to track periodic reference trajectories in this paper. In the proposed AFNN control system, an FNN with accurate approximation capability is employed to approximate the unknown dynamics of the PMLSM, and a robust compensator is proposed to confront the inevitable approximation errors due to finite number of membership functions and disturbances including the friction force. The adaptive learning algorithm that can learn the parameters of the FNN on line is derived using Lyapunov stability theorem. Moreover, to relax the requirement for the value of lumped uncertainty in the robust compensator, which comprises a minimum approximation error, optimal parameter vectors, higher order terms in Taylor series and friction force, an adaptive lumped uncertainty estimation law is investigated. Furthermore, all the control algorithms are implemented in a TMS320C32 DSP-based control computer. The simulated and experimental results due to periodic reference trajectories show that the dynamic behaviors of the proposed control systems are robust with regard to uncertainties

Adaptive wavelet neural network control for linear synchronous motor servo drive

We propose an adaptive wavelet neural network (AWNN) control system to control the position of the mover of a permanent-magnet linear synchronous motor (PMLSM) servo drive system to track periodic reference trajectories. The AWNN control system, uses a wavelet neural network (WNN) with accurate approximation capability to represent the unknown dynamics of the PMLSM. It also uses a robust term to confront the inevitable approximation errors due to the finite number of wavelet basis functions and to disturbances, including the friction force. An adaptive learning algorithm that learns the parameters of weight, dilation, and translation of the WNN on line is based on the Lyapunov stability theorem. To relax the requirement for the bound of uncertainty in the robust term, which comprises a minimum approximation error, optimal parameter vectors, higher order terms in Taylor series, and friction force, an adaptive bound estimation law is used; in the estimation, a simple adaptive algorithm estimates the bound of uncertainty. Our simulated and experimental results for periodic reference trajectories show that the dynamic behavior of the proposed control system is robust with regard to uncertainties. An adaptive wavelet neural network (AWNN) control system is proposed to control the position of the mover of a permanent magnet linear synchronous motor (PMLSM) servo drive system to track periodic reference trajectories in this study. In the proposed AWNN control system, a WNN with accurate approximation capability is employed to approximate the unknown dynamics of the PMLSM, and a robust term is proposed to confront the inevitable approximation errors due to finite number of wavelet basis functions and disturbances including the friction force. The adaptive learning algorithm that can learn the parameters of weight, dilation and translation of the WNN on line is derived using Lyapunov stability theorem. Moreover, to relax the requirement for the bound of uncertainty in robust term, which comprises a minimum approximation error, optimal parameter vectors, higher-order terms in Taylor series and friction force, an adaptive bound estimation law is investigated where a simple adaptive algorithm is utilized to estimate the bound of uncertainty. Furthermore, the simulated and experimental results due to periodic reference trajectories show that the dynamic behaviors of the proposed control systems are robust with regard to uncertainties.

Recurrent Radial Basis Function Network-Based Fuzzy Neural Network Control for Permanent-Magnet Linear Synchronous Motor Servo Drive

We propose a recurrent radial basis function network-based (RBFN-based) fuzzy neural network (FNN) to control the position of the mover of a field-oriented control permanent-magnet linear synchronous motor (PMLSM) to track periodic reference trajectories. The proposed recurrent RBFN-based FNN combines the merits of self-constructing fuzzy neural network (SCFNN), recurrent neural network (RNN), and RBFN. Moreover, it performs the structureand parameter-learning phases concurrently. The structure learning is based on the partition of input space, and the parameter learning is based on the supervised gradient descent method, using a delta adaptation law. Furthermore, all the control algorithms are implemented in a TMS320C32 DSP-based control computer. The simulated and experimental results due to periodic reference trajectories show that the dynamic behaviors of the proposed recurrent RBFN-based FNN control system are robust with regard to uncertainties

A linear synchronous motor drive using robust fuzzy neural network control

A robust fuzzy neural network (RFNN) control system is proposed to control the position of the mover of a permanent magnet linear synchronous motor (PMLSM) drive system to track periodic reference trajectories in this study. In the proposed RFNN control system, a FNN controller is the main tracking controller, which is used to mimic an ideal feedback linearization control law, and a robust controller is proposed to confront the shortcoming of the FNN controller. The ideal feedback linearization control law is designed based on the backstepping technique. Moreover, to relax the requirement for the bound of uncertainty, which comprises a minimum approximation error, optimal parameter vectors and higher-order terms in Taylor series, a RFNN control system with adaptive bound estimation is investigated where a simple adaptive algorithm is utilized to estimate the bound of uncertainty. Furthermore, the experimental results due to periodic reference trajectories show that the dynamic behaviors of the proposed control systems are robust with regard to uncertainties.

Robust fuzzy-neural-network control for two-axis motion control system based on TMS320C32 control computer

In this study, a robust fuzzy-neural-network (RFNN) sliding-mode control based on computed-torque control design for a two-axis motion control system in which the X-Y table is composed of two permanent magnet linear synchronous motor (PMLSM) is proposed. First, a single-axis motion dynamics with the introduction of a lumped uncertainty including cross-coupled interference between the two-axis mechanism is derived. Then, to improve the control performance in reference contours tracking, the RFNN sliding-mode control system is proposed to effectively approximate the equivalent control of the sliding-mode control method based on the derived motion dynamics. Moreover, the motions at X-axis and Y-axis are controlled separately. Using the proposed control, the motion tracking performance is significantly improved and the robustness to parameter variations, external disturbances, cross-coupled interference and friction force can be obtained as well. Furthermore, all the control algorithms are implemented in a TMS320C32 DSP-based control computer. The experimental results due to circle and four leaves reference contours show that the dynamic behaviors of the proposed control systems are robust with regard to uncertainties.

Linear synchronous motor servo drive based on adaptive wavelet neural network

An adaptive wavelet neural network (AWNN) control system is proposed to control the position of the mover of a permanent magnet linear synchronous motor (PMLSM) servo drive system to track periodic reference trajectories in this study. In the proposed AWNN control system, a WNN with accurate approximation capability is employed to approximate the unknown dynamics of the PMLSM, and a robust term is proposed to confront the inevitable approximation errors due to finite number of wavelet basis functions and disturbances including the friction force. The adaptive learning algorithm that can learn the parameters of weight, dilation and translation of the WNN on line is derived using Lyapunov stability theorem. Moreover, to relax the requirement for the bound of uncertainty in robust term, which comprises a minimum approximation error, optimal parameter vectors, higher-order terms in Taylor series and friction force, an adaptive bound estimation law is investigated where a simple adaptive algorithm is utilized to estimate the bound of uncertainty. Furthermore, the experimental results due to periodic reference trajectories show that the dynamic behaviors of the proposed control systems are robust with regard to uncertainties.

Variable-structure control for linear synchronous motor using recurrent fuzzy neural network

A newly designed variable-structure controller using recurrent fuzzy neural network (RFNN) to control the mover position of a permant magnet linear synchronous motor (PMLSM) servo drive is developed in this study. First, a variable-structure adaptive (VSA) controller is adopted to control the mover position of the PMLSM where a simple adaptive algorithm is utilized to estimate the uncertainty bounds. Then, to further improve the rate of convergence of the estimation, a variable-structure controller using RFNN is investigated, in which the RFNN is utilized to estimate the lumped uncertainty real-time. Simulated and experimental results show that the proposed variable-structure controller using RFNN provides high-performance dynamic characteristics and is robust with regard to plant parameter variations and external disturbance. Furthermore, comparing with the VSA controller, smaller control effort is resulted and the chattering phenomenon is reduced by the proposed variable-structure controller using RFNN.