Recurrent Fuzzy Wavelet Neural Network Research Articles

Intelligent Backstepping Control of Permanent Magnet-Assisted Synchronous Reluctance Motor Position Servo Drive with Recurrent Wavelet Fuzzy Neural Network

An intelligent servo drive system for a permanent magnet-assisted synchronous reluctance motor (PMASynRM) that can adapt to the control requirements considering the motor’s nonlinear and time-varying natures is developed in this study. A recurrent wavelet fuzzy neural network (RWFNN) with intelligent backstepping control is proposed to achieve this. In this study, first, a maximum torque per ampere (MTPA) controlled PMASynRM servo drive is introduced. A lookup table (LUT) is created, which is based on finite element analysis (FEA) results by using ANSYS Maxwell-2D dynamic model to determine the current angle command of the MTPA. Next, a backstepping control (BSC) system is created to accurately follow the desired position in the PMASynRM servo drive system while maintaining robust control characteristics. However, designing an efficient BSC for practical applications becomes challenging due to the lack of prior uncertainty information. To overcome this challenge, this study introduces an RWFNN as an approximation for the BSC, aiming to alleviate the limitations of the traditional BSC approach. An enhanced adaptive compensator is also incorporated into the RWFNN to handle potential approximation errors effectively. In addition, to ensure the stability of the RWFNN, the Lyapunov stability method is employed to develop online learning algorithms for the RWFNN and to guarantee its asymptotic stability. The proposed intelligent backstepping control with recurrent wavelet fuzzy neural network (IBSCRWFNN) demonstrates remarkable effectiveness and robustness in controlling the PMASynRM servo drive, as evidenced by the experimental results.

Recurrent Wavelet Fuzzy Neural Network-Based Reference Compensation Current Control Strategy for Shunt Active Power Filter

The usage of a shunt active power filter (SAPF) is one of the helpful means to mitigate the reactive power and harmonic current of a power grid. The compensation performance of the SAPF is related to the accuracy of the reference voltage extraction from the utility grid, the control stability of the DC-link voltage regulation, and the synchronization between the source voltage and the reference compensation current. To modify the performance of the SAPF for the harmonic compensation, the control strategy of the SAPF reference compensation current based on the recurrent wavelet fuzzy neural network (RWFNN) is proposed in this paper. There are three sections in the proposed control strategy, including the regulated fundamental positive-sequence extraction (section A), DC-link voltage regulation (section B), and calculation of reference compensation current (section C). By regulating the analysis mechanism with the variation of fundamental frequency in the section A, the accurate reference voltage would be obtained. The control stability for the regulation of the DC-link voltage can be accomplished by applying the RWFNN-based controller in the section B. With the synchronized reference voltage in the section A and the estimated control current in the section B, the reference compensation current can be correctly obtained in the section C. From the case studies with the real-time simulator produced by OPAL-RT Technologies Inc., the effectiveness of proposed control strategy for the SAPF reference compensation current can be verified.

Decentralized Adaptive Fault-Tolerant Cooperative Control for Multiple UAVs with Input Saturation and State Constraints

This paper proposes a fault-tolerant cooperative control (FTCC) scheme for multiple UAVs in a distributed communication network against input saturation, full-state constraints, actuator faults, and unknown dynamics. Firstly, by considering physical limitations, an auxiliary control signal is designed to simplify the analysis process. Secondly, to avoid the difficulty in the back-stepping design caused by full-state constraints, virtual control signals are constructed to transform constrained variables, while the dynamic surface control is adopted to avoid the phenomenon of “differential explosion.” Thirdly, a disturbance observer (DO) is designed to estimate the unknown uncertainty caused by parameter uncertainty and actuator fault. Moreover, a recurrent wavelet fuzzy neural network (RWFNN) is used to compensate for the estimation errors of DO. Finally, it is proved that all states are uniformly ultimately bounded (UUB) by Lyapunov and invariant set theory. The effectiveness of the proposed scheme is further demonstrated by the simulation results.

Seamless Switching and Grid Reconnection of Microgrid Using Petri Recurrent Wavelet Fuzzy Neural Network

A Petri recurrent wavelet fuzzy neural network (PetriRWFNN) controller and a simple presynchronization estimation are proposed for the operations of seamless switching and grid reconnection in a microgrid system. The microgrid using master/slave control consists of a storage system, photovoltaic (PV) system and loads, and can be operated in either grid-connected mode or islanded mode. Since the different control algorithm is adopted in the master distributed generator at different operation modes, the transient deterioration in voltage and active power output of the microgrid system is obvious during the mode switching. Moreover, when the microgrid is operated in islanded mode and the power grid returns to normal operation, the microgrid cannot directly reconnect with the power grid to avoid a large inrush of current and failed grid reconnection due to the asynchronous angle between the islanded microgrid and the grid angle. Therefore, a novel PetriRWFNN controller is proposed to improve the transient responses of the voltage and active power of the microgrid during mode switching. The network structure and the online learning algorithm of the proposed PetriRWFNN are introduced in detail. Furthermore, a simple and fast presynchronization estimation for grid reconnection during the switching from the islanded mode to the grid-connected mode is also proposed in this article. Finally, some experimental results are provided to certify the effectiveness and feasibility of the microgrid system using the proposed PetriRWFNN controller and presynchronization estimation for the operations of seamless switching and grid reconnection.

Fractional-Order Adaptive Fault-Tolerant Synchronization Tracking Control of Networked Fixed-Wing UAVs Against Actuator-Sensor Faults via Intelligent Learning Mechanism.

This article presents an enhanced fault-tolerant synchronization tracking control scheme using fractional-order (FO) calculus and intelligent learning architecture for networked fixed-wing unmanned aerial vehicles (UAVs) against actuator and sensor faults. To increase the flight safety of networked UAVs, a recurrent wavelet fuzzy neural network (RWFNN) learning system with feedback loops is first designed to compensate for the unknown terms induced by the inherent nonlinearities, unexpected actuator, and sensor faults. Then, FO sliding-mode control (FOSMC), involving the adjustable FO operators and the robustness of SMC, are dexterously proposed to further enhance flight safety and reduce synchronization tracking errors. Moreover, the dynamic parameters of the RWFNN learning system embedded in the networked fixed-wing UAVs are updated based on adaptive laws. Furthermore, the Lyapunov analysis ensures that all fixed-wing UAVs can synchronously track their references with bounded tracking errors. Finally, comparative simulations and hardware-in-the-loop experiments are conducted to demonstrate the validity of the proposed control scheme.

Voltage Regulation Using Recurrent Wavelet Fuzzy Neural Network-Based Dynamic Voltage Restorer

Dynamic voltage restorers (DVRs) are one of the effective solutions to regulate the voltage of power systems and protect sensitive loads against voltage disturbances, such as voltage sags, voltage fluctuations, et cetera. The performance of voltage compensation with DVRs relies on the robustness to the power quality disturbances and rapid detection of voltage disturbances. In this paper, the recurrent wavelet fuzzy neural network (RWFNN)-based controller for the DVR is developed. With positive-sequence voltage analysis, the reference signal for the DVR compensation can be accurately obtained. In order to enhance the response time for the DVR controller, the RWFNN is introduced due to the merits of rapid convergence and superior dynamic modeling behavior. From the experimental results with the OPAL-RT real-time simulator (OP4510, OPAL-RT Technologies Inc., Montreal, Quebec, Canada), the effectiveness of proposed controller can be verified.

Recurrent fuzzy wavelet neural network variable impedance control of robotic manipulators with fuzzy gain dynamic surface in an unknown varied environment

In this paper, an intelligent variable impedance control combined with a fuzzy gain dynamic surface is proposed to improve the interaction of the robot manipulator with an unknown varied environment. The parameters of the proposed variable impedance are adapted by optimization an introduced cost function using a recurrent fuzzy wavelet network. The stability conditions for the varying inertial, stiffness and damping are presented to guarantee the stability of the variable impedance. Additionally, a fuzzy dynamic surface method is developed to tune the gains of the dynamic surface as a robust controller. The proposed fuzzy gain dynamic surface is used to force the end-effector of the manipulator to track the desired impedance profile in the presence of large disturbances. Using Lyapunov's method, the stability of the mentioned closed-loop system is proved. Finally, by using a designed simulator for IRB120 (ABB) robot, several simulations are carried out to verify the performance of the proposed method for the execution of various tasks in an unknown varied environment in the presence of large disturbances.

Improved LVRT Performance of PV Power Plant Using Recurrent Wavelet Fuzzy Neural Network Control for Weak Grid Conditions

An intelligent control method using recurrent wavelet fuzzy neural network (RWFNN) is proposed to improve the low-voltage ride through (LVRT) performance of a two-stage photovoltaic (PV) power plant under grid faults for the weak grid conditions. The PV power plant comprises an interleaved DC/DC converter and a three-level neutral-point clamped (NPC) smart inverter, in which the output active and reactive powers of the inverter can be predetermined in accordance with grid codes of the utilities. Moreover, for the purpose of improving the control performance of the PV power plant to handle the grid faults for the weak grid conditions, a new RWFNN with online training is proposed to replace the traditional proportional-integral (PI) controller for the active and reactive powers control of the smart inverter. Furthermore, the proposed controllers are implemented by two floating-point digital signal processors (DSPs). From the simulation and experimental results, excellent control performance for the tracking of active and reactive powers under grid faults for the weak grid conditions can be achieved by using the proposed intelligent control method.

INS/GNSS integration using recurrent fuzzy wavelet neural networks

In recent years, aided navigation systems through combining inertial navigation system (INS) with global navigation satellite system (GNSS) have been widely applied to enhance the position, velocity, and attitude information of autonomous vehicles. In order to gain the accuracy of the aided INS/GNSS in GNSS gap intervals, a heuristic neural network structure based on the recurrent fuzzy wavelet neural network (RFWNN) is applicable for INS velocity and position error compensation purpose. During frequent access to GNSS data, the RFWNN should be trained as a highly precise prediction model equipped with the Kalman filter algorithm. Therefore, the INS velocity and position error data are obtainable along with the lost intervals of GNSS signals. For performance assessment of the proposed RFWNN-aided INS/GNSS, real flight test data of a small commercial unmanned aerial vehicle (UAV) were conducted. A comparison of test results shows that the proposed NN algorithm could efficiently provide high-accuracy corrections on the INS velocity and position information during GNSS outages.

A novel Robust Adaptive Control Using RFWNNs and Backstepping for Industrial Robot Manipulators with Dead-Zone

This paper proposes a novel robust adaptive-backstepping-recurrent-fuzzy-wavelet-neural-networks controller (ABRFWNNs) based on dead zone compensator for Industrial Robot Manipulators (IRMs) in order to improve high correctness of the position tracking control with the presence of the unknown dynamics, and disturbances. To deal on the unknown dynamics of the robot system problems, the proposed controller used recurrent-fuzzy-wavelet-neural-networks (RFWNNs) to approximate the unknown dynamics. The online adaptive control training laws and estimation of the dead-zone are determined by Lyapunov stability theory and the approximation theory. In this method, the robust sliding-mode-control (SMC) is constructed to optimize parameter vectors, solve the approximation error and higher order terms. Therefore, the stability, robustness, and desired tracking performance of ABRFWNNs for IRMs are guaranteed. The simulations and experiments performed on three-link IRMs are provided in comparison with fuzzy-wavelet-neural-networks (FWNNs) and proportional-integral-derivative (PID) to demonstrate the robustness and effectiveness of the ARBFWNNs.

Adaptive ORFWNN-Based Predictive PID Control

This paper proposes a new adaptive proportional–integral–derivative (PID) control method using predictive control and output recurrent fuzzy wavelet neural network (ORFWNN) for a group of nonlinear digital time-delay dynamic systems. The presented controller, called ORFWNN-APPID controller, is rigorously derived and proved by including an ORFWNN identifier with online parameter learning and identification, and an adaptive ORFWNN-based predictive PID controller to achieve precise setpoints tracking and disturbance rejection. The effectiveness and superiority of the constructed ORFWNN-APPID control approach are well demonstrated by performing numerical simulations on step-like disturbance rejection and precise setpoint tracking of two well-known digital nonlinear processes. The practicability of the presented method is illustrated by carrying out two experimental results on a real PET temperature control process.

Energy-Saving Dynamic Bias Current Control of Active Magnetic Bearing Positioning System Using Adaptive Differential Evolution

This paper proposes an evolutionary algorithm-based energy-saving control strategy to control a highly nonlinear and time-varying active magnetic bearing (AMB) positioning system that considers energy efficiency and control performance simultaneously. Most AMB control schemes use a bias current with a superimposed control current to improve the linearity and dynamic performance of the system. However, the bias current causes power losses even if no electromagnetic force is required. As such, a recurrent wavelet fuzzy neural network with adaptive differential evolution (RWFNN-ADE)-based dynamic bias current control strategy is proposed in this paper so as to minimize the energy consumed by an AMB without altering its positioning performance and robustness. To begin with, this paper analyzes the operation principle of the AMB positioning system with a differential driving mode. Subsequently, the proposed RWFNN-ADE control scheme, in which the control current and bias current are controlled by the RWFNN and ADE, respectively, is introduced in detail. Finally, the experimental results demonstrate the high-accuracy control and significant energy-saving performances of the proposed RWFNN-ADE-controlled AMB positioning system. In the tests corresponding to operation periods of 10 and 50 s, the energy improvements compared to the baseline values were 20.24% and 17.65%, respectively, in nominal cases, and 18.89% and 18.68%, respectively, in parameter variation cases, for the proposed control strategy.

Self-Organizing Recurrent Wavelet Fuzzy Neural Network-Based Control System Design for MIMO Uncertain Nonlinear Systems Using TOPSIS Method

The major objective of this study is to design an effective control algorithm for dealing with multiple-input–multiple-output uncertain nonlinear systems. Novelty advantages of the proposed method include: (1) The network has the maximum initial rules; it helps to increase the responsiveness of the system; (2) the network has two dynamic thresholds: One dynamic threshold is utilized to consider whether to retain or to delete the existing rules and the other is used for generating a new rule; (3) the fuzzy neural network-based system can automatically construct the network structure and adjust the parameters of the system; (4) the network uses multiple combination techniques, such as sliding mode control, adaptive control, recurrent unit, wavelet function, fuzzy logic, neural network, and technique for order of preference by similarity to ideal solution multi-criteria decision analysis method. Based on the advantages of the above techniques, a self-organizing recurrent wavelet fuzzy neural network control system is designed comprising a main controller and a robust compensator. The gradient descent method is used to online tune the parameters for the main controller, and a Lyapunov stability theorem is applied to guarantee the system’s stability. Finally, the proposed control system is applied to a nonlinear chaotic system, an inverted double-pendulum system, and an unmanned aerial vehicle motion control to verify the effectiveness of the proposed control scheme. The simulation results show that the proposed control scheme can achieve favorable control performance.

Recurrent fuzzy wavelet neural networks based on robust adaptive sliding mode control for industrial robot manipulators

A robust adaptive control method is proposed in this paper based on recurrent fuzzy wavelet neural networks (RFWNNs) system for industrial robot manipulators (IRMs) to improve high accuracy of the tracking control. The RFWNNs consist of four layers, and second layer has the feedback connections. Wavelet basis function is used as fuzzy membership function. In general, it is not easy to adopt a model-based method to achieve this control object due to the uncertainties of the IRM, such as unknown dynamic, disturbances and parameter variations. To solve this problem, all the parameters of the RFWNNs system are tuned online by an adaptive learning algorithm, and online adaptive control laws are determined by Lyapunov stability theorem. In addition, the robust controller is designed to deal with the approximation error, optimal parameter vectors and higher-order terms in Taylor series. Therefore, with the proposed control, the desired tracking performance, stability and robustness of the closed-loop manipulators system are guaranteed. The simulations and experimental performed on a three-link IRMs are provided in comparison with fuzzy wavelet neural network and robust neural fuzzy network to demonstrate the effectiveness and robustness of the proposed RFWNNs methodology.

Quaternion-Based Adaptive Backstepping RFWNN Control of Quadrotors Subject to Model Uncertainties and Disturbances

This paper presents a quaternion-based adaptive backstepping control method using recurrent fuzzy wavelet neural network (RFWNN) for regulation and trajectory tracking of quadrotors subject to model uncertainties and disturbances. For the controller synthesis, a more complete model of an uncertain quadrotor is first obtained by incorporating with mass variations and wind disturbances, which are online learned by using the RFWNN. Afterward, a quaternion-based adaptive backstepping RFWNN controller is synthesized by integrating backstepping, quaternion control, and the RFWNN online learner. The closed-loop stability of the overall quadrotor control system is shown semi-globally uniformly ultimately bounded via Lyapunov stability theory. The effectiveness and performance of the proposed control method are well exemplified by conducting four simulations on hovering and three-dimensional sinusoidal trajectory tracking control of a quadrotor. Through the simulation results, the proposed control method is shown superior by comparing to two existing methods.

ADAPTIVE-BACKSTEPPING POSITION CONTROL BASED ON RECURRENT-FWNNS FOR MOBILE MANIPULATOR ROBOT

In this paper, we proposed an adaptive-backstepping position control system for mobile manipulator robot (MMR). By applying recurrent fuzzy wavelet neural networks (RFWNNs) in the position-backstepping controller, the unknown-dynamics problems of the MMR control system are relaxed. In addition, an adaptive-robust compensator is proposed to eliminate uncertainties that consist of approximation errors and uncertain disturbances. The design of adaptive-online learning algorithms is obtained by using the Lyapunov stability theorem. The effectiveness of the proposed method is verified by comparative simulation results.

Intelligent Sliding-Mode Position Control Using Recurrent Wavelet Fuzzy Neural Network for Electrical Power Steering System

A digital signal processor (DSP)-based intelligent sliding-mode control (SMC) is proposed for the position control of a six-phase permanent magnet synchronous motor (PMSM) drive system installed in an electric power steering (EPS) system in this study. First, the dynamic mathematical model of the EPS system is derived by the Lagrangian dynamics. Since the EPS system is a nonlinear and time-varying system, the control accuracy is very sensitive to the parameter variations and external disturbances. Therefore, a SMC is developed for the position control of the EPS system. However, the upper bound of the uncertainties is difficult to obtain in advance and the choice of switching control gain in SMC is vital but time-consuming and may cause undesired chattering phenomenon. Hence, an intelligent SMC with a novel recurrent wavelet fuzzy neural network (ISMC-RWFNN) is proposed, in which a recurrent wavelet fuzzy neural network (RWFNN) is adopted as an uncertainty estimator to overcome the aforementioned disadvantage of SMC. Moreover, a robust compensator is employed to reduce the estimation error. In addition, the adaptive learning algorithms for the online training of the RWFNN are derived using the Lyapunov theorem and Taylor series. Finally, the proposed ISMC-RWFNN to control the position of a six-phase PMSM drive system for the EPS system is implemented in a 32-bit floating-point DSP, and some experimental results are provided to verify its effectiveness.

Robust Adaptive Backstepping Sliding Mode Control for Six-Phase Permanent Magnet Synchronous Motor Using Recurrent Wavelet Fuzzy Neural Network

A robust adaptive backstepping sliding mode control (ABSMC) with recurrent wavelet fuzzy neural network (RWFNN) is proposed for the speed regulation of a six-phase permanent magnet synchronous motor (PMSM) demonstrating parameter perturbations and load disturbances. First, a motor drive system model with lumped uncertainty is developed. Then, a nonlinear robust speed controller using ABSMC and $H_{\infty }$ theory is presented. In this technique, ABSMC is employed to guarantee the speed tracking and parameter perturbation suppression; meanwhile, nonlinear $H_{\infty }$ is utilized to minimize the influence of dynamic load disturbances on its tracking output. In addition, an uncertainty observer based on the RWFNN is designed to estimate the unknown and improve the robustness of motor drive system further. Ultimately, simulations and AppSIM simulator-based experimental results both indicate that the proposed control scheme can perfectly compensate the parameter perturbations and load disturbances while maintaining speed tracking precision.

Application of a recurrent wavelet fuzzy-neural network in the positioning control of a magnetic-bearing mechanism

A new recurrent wavelet fuzzy neural network (RWFNN) with adaptive learning rates is proposed to control the rotor position on the axial direction of a thrust magnetic bearing (TMB) mechanism in this study. First, the dynamic analysis of the TMB with differential driving mode (DDM) is derived. Because the dynamic characteristics and system parameters of the TMB mechanism are high nonlinear and time-varying, the RWFNN, which integrates wavelet transforms with fuzzy rules, is proposed to achieve precise positioning control of the TMB. For the designed RWFNN controller, the online learning algorithm is derived using back-propagation method. Moreover, since the improper selection of learning rates for the RWFNN will deteriorate the control performance, an improved particle swarm optimization (IPSO) is adopted to adapt the learning rates of the RWFNN on-line. Numerical simulations show the validity of TMB system using the proposed RWFNN controller with IPSO under the occurrence of uncertainties.

Recurrent Fuzzy Wavelet Neural Network to Control a PCV

Pneumatic Control Valves (PCV) are used in the process industries. In this paper, a Recurrent Fuzzy Wavelet Neural Network (RFWNN) is constructed by using Recurrent Wavelet Neural Network (RWNN). In RWNN, temporal relations are embedded in the network by adding feedback connections on the first layer of the network, and wavelet basis n is used as fuzzy membership function. The proposed method is applied on a PCV. P, PI and PID controllers are also employed For comparison. Bondgraph method has been utilized to model the control valve, so as to compare the response characteristics of valve. Simulation results have been made for four controllers.