Recurrent Fuzzy Neural Network Control Research Articles

The fuzzy neural network control scheme with H tracking characteristic of space robot system with dual-arm after capturing a spin spacecraft

In this paper, the dynamic evolution for a dual-arm space robot capturing a spacecraft is studied, the impact effect and the coordinated stabilization control problem for post-impact closed chain system are discussed. At first, the pre-impact dynamic equations of open chain dual-arm space robot are established by Lagrangian approach, and the dynamic equations of a spacecraft are obtained by Newton-Euler method. Based on the results, with the process of integral and simplify, the response of the dual-arm space robot impacted by the spacecraft is analyzed by momentum conservation law and force transfer law. The closed chain system is formed in the post-impact phase. Closed chain constraint equations are obtained by the constraints of closed-loop geometry and kinematics. With the closed chain constraint equations, the composite system dynamic equations are derived. Secondly, the recurrent fuzzy neural network control scheme is designed for calm motion of unstable closed chain system with uncertain system parameter. In order to overcome the effects of uncertain system inertial parameters, the recurrent fuzzy neural network is used to approximate the unknown part, the control method with H&#x221E tracking characteristic. According to the Lyapunov theory, the global stability is demonstrated. Meanwhile, the weighted minimum-norm theory is introduced to distribute torques guarantee that cooperative operation between manipulators. At last, numerical examples simulate the response of the collision, and the efficiency of the control scheme is verified by the simulation results.

Design of a robust adaptive sliding mode control using recurrent fuzzy wavelet functional link neural networks for industrial robot manipulator with dead zone

This paper addresses the problem of trajectory tracking control for industrial robot manipulators (IRMs) in the presence of external disturbances and uncertain dynamics. A novel robust adaptive recurrent fuzzy wavelet functional link neural network (RFWFLNN) controller based on dead-zone compensator is proposed in order to improve the position tracking performance. To handle the unknown dynamics of the IRMs, the robust adaptive RFWFLNNs are applied to approximate the unknown dynamics. The online learning laws and estimation of the dead zone are determined by using Lyapunov stability theory and the approximation theory. In addition, the robust SMC is applied to eliminate the estimation errors and disturbances of the IRM control system. Therefore, the RFWFLNN controller for IRMs can guarantee not only the robustness and stability but also the position tracking performance. Some simulations and experiments performed on three-link IRMs are provided to prove the robustness and effectiveness of the RFWFLNNs. The superiority of the RFWFLNN controller is also demonstrated based on comparisons with fuzzy wavelet neural networks and PID controllers.

Decoupling control for wastewater treatment process based on recurrent fuzzy neural network

AbstractDue to the characteristics of strong coupling and high nonlinearity in the control process, an intelligent decoupling control strategy based on recurrent fuzzy neural network (RFNN) is proposed in this paper to control the wastewater treatment process (WWTP). Firstly, the architecture of the RFNN controller is designed with a mechanism analysis of WWTP. Secondly, a decoupling strategy in combination with a gradient descent search algorithm is used to decouple the control loop of dissolved oxygen (DO) concentration and nitrate nitrogen (SNO) concentration. Finally, stability analysis based on a Lyapunov function is investigated. The proposed approach has been applied to the WWTP simulation model. Compared to model predictive control, echo state network‐based HDP (E‐HDP), conventional RFNN, and neural network on‐line modelling and controlling methods, the proposed method has better control performance.

Antlion Algorithm Optimized Fuzzy PID Supervised On-line Recurrent Fuzzy Neural Network Based Controller for Brushless DC Motor

In this paper, Antlion algorithm optimized Fuzzy PID supervised on-line Recurrent Fuzzy Neural Network based controller is proposed for the speed control of Brushless DC motor. Learning parameters of the supervised on-line recurrent fuzzy neural network controller, i.e., learning rate (η), dynamic factor (α), and number nodes (Ni) are optimized using Genetic algorithm, Particle Swarm optimization, Ant colony optimization, Bat algorithm, and Antlion algorithm. The proposed controller is tested with different operating conditions of the Brushless DC motor, such as varying load conditions and varying set speed conditions. The time domain specifications such as rise time, overshoot, undershoot, settling time, recovery time, and steady state error and also integral performance indices such as root mean square error, integral of absolute error, integral of squared error, and integral of time multiplied absolute error are measured and compared for above optimized controller. Simulation results show Antlion algorithm optimized Fuzzy PID supervised on-line recurrent fuzzy neural network based controller has proved to be superior than other considered controllers in all aspects. In addition, the experimental verification of proposed control system is presented to test the effectiveness of the proposed controller with different operating conditions of the Brushless DC motor.

Fuzzy supervised online coactive neuro‐fuzzy inference system‐based rotor position control of brushless DC motor

In this study, fuzzy supervised online coactive neuro-fuzzy inference system (CANFIS)-based rotor position controller is presented for brushless DC (BLDC) motor. An online learning algorithm is employed for updating premises and consequent parameters of the CANFIS controller. The rotor position control of BLDC motor is simulated using MATLAB/Simulink Toolbox. The dynamic response of the BLDC motor with proposed controller is measured for standard sinusoidal reference input. The effectiveness of the proposed controller performance is compared with fuzzy proportional-integral derivative controller, adaptive neuro-fuzzy inference system controller and supervised recurrent fuzzy neural network controller. The proposed controller is able to solve the problem of non-linearities and uncertainty due to reference input changes of BLDC motor and guarantees fast and accurate dynamic response to a remarkable steady-state performance. Also, experimental hardware results are presented to demonstrate the validity and effectiveness of the proposed control scheme using field programmable gate array chip. Experimental results show that the proposed control scheme can achieve a more favourable tracking performance without the chattering phenomena in the control effort.

Intelligent position control of permanent magnet synchronous motor using recurrent fuzzy neural cerebellar model articulation network

A recurrent fuzzy neural cerebellar model articulation network (RFNCMAN) control is proposed in this paper for position servo drive systems to track various periodical position references with robustness. The adopted position servo drive system is designed using a six-phase PMSM and equipped with a fault-tolerant control scheme. First, an ideal computed torque controller is designed for the tracking of the rotor position reference command. Since the uncertainties of the PMSM position servo drive system are difficult to know in advance, it is impossible to design an ideal computed control law for practical applications. Therefore, the RFNCMAN is proposed to mimic the ideal computed torque controller with a compensated controller to compensate the approximation error. In the RFNCMAN, a recurrent fuzzy cerebellar model articulation network (RFCMAN) is adopted in the first dimension to enhance the online learning rate and localisation learning capability. Moreover, a general recurrent fuzzy neural network (RFNN) is adopted in the second dimension to enhance the generalisation performance and to reduce the required memory and rule numbers. Finally, the proposed position control system is implemented in a 32-bit floating-point DSP. The effectiveness of the proposed RFNCMAN control system is verified by some experimental results.

Robot Path Planning Based on Chaos Concise Differential Evolution and RFNN Control

In order to reduce the memory footprint and energy consumption of embedded microcontroller in mobile robot, the concise differential evolution algorithm based on chaotic local search (CDE-CLS) is proposed for online optimization of recurrent fuzzy neural network (RFNN) controller in robot path planning so that the robot can be adaptive real-time ob- stacle avoidance. The CDE-CLS algorithm reduces the memory footprint of the controller using virtual population and in- creases the ability to explore help to fast convergence introducing a simple and efficient chaotic local fine search and in- hibit premature convergence perturbing the virtual population. Contrast tests on the typical Benchmark functions verify the global convergence and stability of the algorithm comparing with other concise evolutionary algorithm. Finally, the simulation result on the robot path planning controller shows the effectiveness of the proposed method.

Adaptive position tracking control system based on recurrent fuzzy wavelet neural networks for robot manipulators

In this article, we propose an adaptive recurrent fuzzy wavelet neural network control strategy to improve high-accuracy position tracking for robot manipulators. In order to deal with the unknown knowledge of the robot system problems, the adaptive recurrent fuzzy wavelet neural networks are applied in the main controller to approximate the unknown dynamics without the requirement of prior knowledge. In addition, an adaptive robust control law is also developed to eliminate uncertainties that consist of estimation errors and disturbances from the robot control system. The design of the adaptive online learning algorithms is determined using the Lyapunov stability theorem. Therefore, the proposed controller proves that it can guarantee not only the stability and robustness but also the tracking performance of the robot manipulators control system. The effectiveness and robustness of the proposed method are demonstrated by comparative simulation and experimental results.

3-Dimensional sliding mode adaptive MIMO recurrent fuzzy neural network control for two-link manipulator system

A novel methodology of 3-dimensional sliding mode adaptive multi-inputs multi-outputs (MIMO) recurrent fuzzy neural network (SAMRFNN) control for two-link manipulator system is proposed. This control scheme consists of a sliding mode (SM) controller and a 3-dimensional adaptive multi-inputs multi-outputs (MIMO) recurrent fuzzy neural network (AMRFNN) controller. The SM controller is to cope with uncertain dynamics of system and external disturbances; and the AMRFNN controller is used to approach the ideal controller of SM controller such as to stabilize the system. The Lyapunov theorem based adaptive laws are derived to tune the SAMRFNN parameters such that the stability and convergence of those can be guaranteed. In the simulations, persistency excitation (PE) effects and results of all parameters have been discussed and demonstrated; meanwhile, better effectiveness and performances of the proposed SAMRFNN control are demonstrated by comparisons with the adaptive fuzzy neural network (AFNN) control and state feedback control.

Three-Degree-of-Freedom Dynamic Model Based IT2RFNN Control for Gantry Position Stage

A three-degree-of-freedom (3-DOF) dynamic model based interval type-2 recurrent fuzzy neural network (IT2RFNN) control system is proposed in this study for a gantry position stage. To consider the effect of inter-axis mechanical coupling, a Lagrangian equation based 3-DOF dynamic model for gantry position stage is derived first. Then, to minimize the synchronous error and tracking error of the gantry position stage, the 3-DOF dynamic model based IT2RFNN control system is proposed. In this approach, the adaptive learning algorithms of the IT2RFNN on-line are derived from the Lyapunov stability theorem. Finally, some experimental results of optical inspection application are illustrated to show the validity of the proposed control approach.

Embedded Differential Evolution Algorithm for Recurrent Fuzzy Neural Network Controller Optimization

A chaos concise differential evolution algorithm (CcDE) is proposed for the embedded controller with limited memory, which introduces chaotic local search based on basic differential evolution algorithm to increase exploring and prevent premature convergence. Using virtual population and Gaussian sampling, the CcDE becomes simple and reduces the memory requirements at run time. Experimental simulation on optimizing parameters of the recurrent fuzzy neural network shows that the proposed CcDE can obtain better performance than other concise algorithm.

The hybrid RFNN control for a PMSM drive electric scooter using rotor flux estimator

The hybrid recurrent fuzzy neural network (HRFNN) control permanent magnet synchronous motor (PMSM) drive system using rotor flux estimator is developed for controlling electric scooter in order to raise robustness and reduce interference and cost of encoder in this paper. First, the dynamic models of a PMSM drive system were derived in according to electric scooter. The proportional integral (PI) controller used for speed controller cannot able to process for the electric scooter due to existence of nonlinear uncertainty. The HRFNN control system using rotor flux estimator was developed to control electric scooter driven by PMSM in order to conquer disadvantage for PI controller and reduce interference and cost of encoder. The rotor flux estimator consists of the estimation algorithm of rotor flux position and speed based on the back electromagnetic force (EMF) to provide the feedback signal for HRFNN control system. The HRFNN control system consists of the supervisor control, the RFNN and the compensated control with adaptive law. To show the effectiveness of the proposed controller, comparative studies with PI controller are demonstrated by experimental results.

Intelligent control for long-term ecological systems

An intelligent control methodology for a long-term ecological systems is developed in this paper. This intelligent control methodology is called as robust recurrent fuzzy neural network control RRFNNC. This control methodology is used to deal with multi-biomass ecological system which is an uncertain nonlinear system subject to unpredictable but bounded disturbances. This RRFNNC system is comprised of a recurrent fuzzy neural network RFNN controller and a robust controller. The RFNN controller is used to approximate an ideal controller; and the robust controller is designed to compensate for the approximation error between the RFNN controller and the ideal controller. The proposed RRFNNC system is applied to keep the multi-biomasses of ecological system within a stay small neighborhood of the unique nontrivial optimal equilibrium state of the undisturbed exploited ecosystem. For the simulation results of accumulative yield of harvest, more harvest can be obtained by applying the proposed RRFNNC system when compared with state feedback control.

Supervisory recurrent fuzzy neural network control for vehicle collision avoidance system design

This paper develops an intelligent method called supervisory recurrent fuzzy neural network (SRFNN) control to deal with the vehicle collision avoidance system (VCAS), which is an uncertain nonlinear model-free system. This SRFNN control system is composed of a recurrent fuzzy neural network (RFNN) controller and a supervisory controller. The RFNN controller is investigated to mimic an ideal controller, and the supervisory controller is designed to compensate for the approximation error between the RFNN controller and the ideal controller. This SRFNN control is employed to keep the VCAS within a safety range to avoid traffic accidences. The simulation results show the performance and effectiveness of the proposed control system are better than that obtained by formal formula-based control.

Supervisory Recurrent Fuzzy Neural Network Control for Disturbed Nonlinear System

Supervisory Recurrent Fuzzy Neural Network Control for Disturbed Nonlinear System

Switching Based Recurrent Fuzzy Neural Network Control Design

Switching Based Recurrent Fuzzy Neural Network Control Design

Supervisory Recurrent Fuzzy Neural Network Guidance Law Design for Autonomous Underwater Vehicle

A guidance law, based on supervisory recurrent fuzzy neural network control (SRFNNC), is proposed for the autonomous underwater vehicle (AUV) guidance systems. This SRFNNC system is comprised of a recurrent fuzzy neural network (RFNN) controller and a supervisory controller. The RFNN controller is used to mimic an ideal controller and the supervisory controller is designed to compensate for the approximation error between the RFNN controller and the ideal controller. The proposed design method is applied to investigate the active acoustic homing guidance of an AUV, which is affected by sonar propagation time-delay and measurement noise. A comparison is made for the proposed SRFNNC, a proportional navigation (PN) and a sliding-mode control (SMC) guidance laws. Simulation results show that the proposed SRFNNC guidance law is more robust and can obtain smaller miss distance than the PN and SMC guidance laws.

The hybrid RFNN control for a PMSM drive system using rotor flux estimator

The hybrid recurrent fuzzy neural network (HRFNN) control permanent magnet synchronous motor (PMSM) drive system using rotor flux estimator is developed to control electric motorcycle in this paper. First, the dynamic models of a PMSM drive system and electric motorcycle are built through experimental tests and parameter measurements. Then, a HRFNN control system using rotor flux estimator is developed to control PMSM drive system in order to drive electric motorcycle. The rotor flux estimator consists of the estimation algorithm of rotor flux position and speed based on the back electromagnetic force (EMF). Moreover, the HRFNN controller consists of the supervisor control, RFNN and variable structure control (VSC) is applied to PMSM drive system using rotor flux estimator. The parameters of RFNN are trained to control command current in order to achieve different output torque of various speeds. The electric motorcycle is operated to provide constant disturbance torque. Finally, the effectiveness of the ...

The Hybrid RFNN Control for a PMSM Drive Electric Scooter Using Rotor Flux Estimator

The hybrid recurrent fuzzy neural network (HRFNN) control for permanent magnet synchronous motor (PMSM) drive system using rotor flux estimator is developed to control electric scooter in this paper. First, the dynamic models of a PMSM drive system were derived in according to electric scooter. Owing to the load of electric scooter exited many uncertainties, for example, nonlinear friction force of the transmission belt, and so forth. The electric scooter with nonlinear uncertainties made the PI controller to disable speed tracking control. Moreover, in order to reduce interference of encoder and cost down, an HRFNN control system using rotor flux estimator was developed to control PMSM drive system in order to drive electric scooter. The rotor flux estimator consists of the estimation algorithm of rotor flux position and speed based on the back electromagnetic force (EMF) in order to supply with HRFNN controller. The HRFNN controller consists of the supervisor control, RFNN, and compensated control with adaptive law is applied to PMSM drive system. The parameters of RFNN are trained according to different speeds in electric scooter. The electric scooter is operated to provide disturbance torque. To show the effectiveness of the proposed controller, comparative studies with PI controller are demonstrated by experimental results.

Robust-tracking control for robot manipulator with deadzone and friction using backstepping and RFNN controller

This study deals with a robust non-smooth non-linearity compensation scheme for the direct-drive robot manipulator with an asymmetric deadzone, dynamic friction in joints and between the environmental contact space and end-effector and uncertainty. A model-free recurrent fuzzy neural network (RFNN) control system to approximate the ideal backstepping control law is designed to replace the traditional model-based adaptive controller, which requires information on the robots dynamics in advance. The simple dead-zone estimator and friction compensator based on the elasto-plastic friction model are developed in order to estimate unknown dead-zone width and friction parameters. The Lyapunov stability analysis yields the adaptive laws of the RFNN controller as well as the estimators of a dead-zone width and an elasto-plastic friction parameter. The validity of the proposed control scheme is confirmed from simulated results for free and constrained direct-drive robots with a deadzone in joint actuator, dynamic friction in joints and contact surfaces of the end-effector and uncertainty.