Self-recurrent Wavelet Neural Network Research Articles

Event-Triggered Neural Sliding Mode Guaranteed Performance Control

To solve the trajectory tracking control problem for a class of nonlinear systems with time-varying parameter uncertainties and unknown control directions, this paper proposed a neural sliding mode control strategy with prescribed performance against event-triggered disturbance. First, an enhanced finite-time prescribed performance function and a compensation term containing the Hyperbolic Tangent function are introduced to design a non-singular fast terminal sliding mode (NFTSM) surface to eliminate the singularity in the terminal sliding mode control and speed up the convergence in the balanced unit-loop neighborhood. This sliding surface guarantees arbitrarily small overshoot and fast convergence speed even when triggering mistakes. Meanwhile, we utilize the Nussbaum gain function to solve the problem of unknown control directions and unknown time-varying parameters and design a self-recurrent wavelet neural network (SRWNN) to handle the uncertainty terms in the system. In addition, we use a non-periodic relative threshold event-triggered mechanism to design a new trajectory tracking control law so that the conventional time-triggered mechanism has overcome a significant resource consumption problem. Finally, we proved that all the closed-loop signals are eventually uniformly bounded according to the stability analysis theory, and the Zeno phenomenon can be eliminated. The method in this paper has a better tracking effect and faster response and can obtain better control performance with lower control energy than the traditional NFTSM method, which is verified in inverted pendulum and ball and plate system.

Motion control of linear induction motor using self-recurrent wavelet neural network trained by model predictive controller

Due to end effects phenomena that cause a decrease of air-gap flux and thrust force, obtaining a precise velocity for a linear induction motor (LIM) has become a significant challenge. This study suggests implementing a novel controller based on a self-recurrent wavelet neural network (SRWNN) and model predictive controller (MPC) to regulate the velocity and thrust force of LIM. The MPC was used to train the SRWNN in this study. The ultimate goal of employing such a control approach in neural network training is to reduce the degree of uncertainty caused by changes in motor parameters and load disturbance. The indirect field-oriented control (IFOC) approach was used to investigate velocity and flux control under varied loading circumstances. Furthermore, to supply the required LIM stator voltage, a SVPWM dependent voltage source inverter was used in this work. To ensure reliable performance, the suggested system combines the benefits of neural networks with the MPC method, resulting in a versatile controller with a basic construction that is easy to accomplish. The MATLAB package is utilized to simulates and outputs LIM responses. The results confirm that the proposed method, which efficiently controls the velocity and thrust force of the LIM, can cope with changes in load force disruption and motor parameters.

Maximum Power Tracking and Power Sharing in Grid Connected WECS Using Modified PFC Rectifier and PR Controlled Inverter

This article presents an improved maximum power tracking and power sharing technique by using a self-recurrent wavelet neural network (SRWNN) controller. A power factor correction (PFC) rectifier as machine-side converter and proportional resonant (PR) controlled three-phase inverter as grid-side converter for wind energy conversion system (WECS) is presented. The modified PFC rectifier ensures the machine to work at maximum power coefficient, by using a sensor less SRWNN controller. Hence, it extracts maximum power at various wind speeds and provides unity power factor operation at generator side so as to increase the efficiency. The PR controlled inverter ensures proper real and reactive power sharing with the grid, which also acts as a distribution static compensator (DSTATCOM), by casting off harmonics at the grid side for nonlinear loads. The wind turbine, generator, converter and controller are modeled in MATLAB/Simulink platform and performance is analyzed for maximum power tracking and power sharing for a 40kVA, 400 V WECS. An extensive analysis of the proposed system is carried out in a developed experimental setup and the results validate the theoretical claims.

State and disturbance estimation for test masses of drag-free satellites based on self-recurrent wavelet neural network

In recent years, the drag-free satellites have been widely used for some fundamental physical experiments, such as checking short-range effects of general relativity, geopotential determination and the exploration of static ocean current. And the space-borne detector of gravitational waves is one of the important applications for drag-free satellites in the future. In this study, the estimation of relative motion state and disturbance for test masses of drag-free satellite after release are researched. Firstly, the relative motion model between the test masses is established based on corresponding reference frames. Secondly, a self-recurrent wavelet neural network estimator is designed to estimate the pure gravitational relative motion state and disturbance for the test masses, and the sliding mode controller is used to transfer the relative motion state to the ideal state. Finally, the proposed estimation methods are verified by the simulation results.

Data-driven thermal error compensation of linear x-axis of worm gear machines with error mechanism modeling

To increase the machining accuracy of worm gear machines, the thermal error compensation was carried out from the view of X-axis's error mechanism of worm gear machines. The spatial motion error of the worm hob caused by X-axis's positioning error is derived, and then the necessity for the reduction of the positioning error is proved. The memory behaviors of the thermal error are revealed, and finally, the applicability of self-recurrent wavelet (SRW) neural networks to the error modeling is demonstrated. Then the genetic algorithm (GA) is used to optimize the number of neurons in the wavelet and product layers and weights of SRW neural networks, and the error models are established with the GA-SRW, SRW, and back propagation (BP) neural networks. The results show that the predictive performance of the error models based on GA-SRW, SRW, and BP neural networks decreases in turn. Moreover, the precision improvement ratios for the average normal error of tooth surfaces of the GA-SRW neural network error model are more than 21.8% and 43.7% compared to the SRW and BP neural networks error models, respectively. Besides, the predictive performance of the GA-SRW neural network model is better than that of the regression models.

Frame-Angle Controlled Wavelet Modulated Inverter and Self-Recurrent Wavelet Neural Network-Based Maximum Power Point Tracking for Wind Energy Conversion System

In this work, a new control methodology is proposed for Type -IV wind energy conversion system (WECS) using a self-recurrent wavelet neural network (SRWNN) control with a Vienna rectifier as the machine side converter (MSC). A SRWNN combines excellent dynamic properties of recurrent neural networks and the fast convergence speed of wavelet neural network. Hidden neurons of SRWNN contains local self-feedback loops, which provide the memory feature and the necessary information of past values of the signals, allowing it to track maximum power from WECS under varying wind speeds. The Vienna rectifier allows unity power factor operation to increase electrical efficiency. Frame angle-controlled wavelet modulation is proposed for the grid side converter (GSC). Wavelet modulated inverter produces output voltage fundamental components with higher magnitudes than those obtained from the pulse width modulated inverters. The non-linear load compensation and power quality enhancement are achieved by executing frame angle control for WM inverter. The overall system is modeled, and performance is verified in MATLAB Simulink. The hardware prototype is developed, and the switching pulses for the rectifier and inverter are generated using dSPACE1104 controller. The results prove that the system provides low harmonic content and high magnitude of the fundamental current component at the machine and grid sides and ensures maximum power operation at various wind speeds.

Adaptive self-recurrent wavelet neural network and sliding mode controller/observer for a slider crank mechanism

In this paper, a novel control strategy based on an adaptive Self-Recurrent Wavelet Neural Network (SRWNN) and a sliding mode controller/observer for a slider crank mechanism is proposed. The aim is to reduce the tracking error of the linear displacement of this mechanism while following a specified trajectory. The controller design consists of two parts. The first one is a sliding mode control strategy and the second part is an SRWNN controller. This controller is trained offline first, and then the SRWNN weights are updated online by the adaptive control law. Apart from the hybrid control strategy proposed in this paper, a velocity observer is implemented to replace the use of velocity sensors. The outcomes obtained in the numerical experiment section prove that the smallest tracking error is obtained for the linear and angular displacements in comparison with other strategies found in literature due to the uncertainty and disturbance rejection properties of the sliding mode and the self-recurrent wavelet neural network controllers.

Adaptive self-recurrent wavelet neural network and sliding mode controller/observer for a slider crank mechanism

Adaptive self-recurrent wavelet neural network and sliding mode controller/observer for a slider crank mechanism

Adaptive impedance control of uncertain robot manipulators with saturation effect based on dynamic surface technique and self-recurrent wavelet neural networks

SUMMARYSaturation nonlinearities, among the known challenges in control engineering, are ubiquitous in robotic systems and can lead to stability and performance degradation. In this paper, an adaptive dynamic surface impedance (ADSI) control approach is developed for an n-link robotic manipulator by employing self-recurrent wavelet neural networks (SRWNNs) in order to overcome the saturation effect. The proposed control approach is inspired by the theory of dynamic surface control (DSC) and SRWNNs. As a novel application of the dynamic surface method to obtain a simple structure, the target impedance is formulated in the state–space, and effective dynamic surfaces are defined to track the desired impedance behavior. In fact, DSC is used to force the robot manipulator to track the desired impedance, while the robot interacts with an environment. In addition, SRWNNs are applied to approximate the parametric uncertainties and external disturbances in the robot dynamical model. Self-feedback neurons are embedded as memory units in SRWNNs to model the sudden dynamic jumps of the environment. Using Lyapunov's method, an ADSI controller is designed, and adaptation laws are induced to guarantee the stability of the closed-loop system. Finally, simulations are conducted to verify the proper performance of the proposed approach for removing the saturation effect and tracking the target impedance. It is worth noting that the simulation results indicate the robustness of the controller against uncertainties and external disturbances.

Controller Design Based On Wavelet Neural Adaptive Proportional Plus Conventional Integral-Derivative For Bilateral Teleoperation Systems With Time-Varying Parameters

In this study, a new controller method based on wavelet neural adaptive proportional plus conventional integral-derivative (WNAP+ID) controller through adaptive learning rates (ALRs) for the Internet-based bilateral teleoperation system is developed. The PID controller design suffers from dealing with a plant with an intricate dynamic model. To make an adaptive essence for PID controller, this study uses a trained offline self-recurrent wavelet neural network as a processing unit (SRWNN-PU) in parallel with conventional PID controller. The SRWNN-PU parameters are updated online using an SRWNN-identifier (SRWNNI) in order to reduce the controller error in realtime function. Using feedback linearization method and a PID controller, the presented control method reduced the tracking error in the subsystems of the teleoperation system, i.e., master and slave which are stabilized, respectively. Additionally, time-varying delay in teleoperation systems is considered as noise making the master signals be modulated because wavelt neural networks have a high susceptibility to remove the noise, thus the WNAP+ID controller is able to eliminate the noise effect. In this paper, we concentrated on the efficiency and stability of the teleoperation system with time-varying parameters through simulation outcomes. Moreover, the results of the WNNs are compared with those of multi-layer perceptron neural networks (MLPNNs).

Self‐recurrent wavelet neural network–based identification and adaptive predictive control of nonlinear dynamical systems

SummaryIn this paper, the problem of simultaneous identification and predictive control of nonlinear dynamical systems using self‐recurrent wavelet neural network (SRWNN) is addressed. The structure of the SRWNN is a modification of the wavelet neural network (WNN). Unlike WNN, the neurons present in the hidden layer of SRWNN contain the weighted self‐feedback loops. Dynamic back‐propagation algorithm is employed to derive the necessary parameter update equations. To further improve the convergence speed of the parameters, a time‐varying (adaptive) learning rate is used. Four simulation examples are considered for testing the effectiveness of the proposed method. Furthermore, some disturbance rejection tests are also performed on the proposed method. The results obtained through the simulation study confirm the effectiveness of the proposed method.

Internal Model Control Using a Self-Recurrent Wavelet Neural Network Trained by an Artificial Immune Technique for Nonlinear Systems

Internal Model Control Using a Self-Recurrent Wavelet Neural Network Trained by an Artificial Immune Technique for Nonlinear Systems

Model Reference Adaptive Control based on a Self-Recurrent Wavelet Neural Network Utilizing Micro Artificial Immune Systems

Abstract 
 This paper presents an intelligent model reference adaptive control (MRAC) utilizing a self-recurrent wavelet neural network (SRWNN) to control nonlinear systems. The proposed SRWNN is an improved version of a previously reported wavelet neural network (WNN). In particular, this improvement was achieved by adopting two modifications to the original WNN structure. These modifications include, firstly, the utilization of a specific initialization phase to improve the convergence to the optimal weight values, and secondly, the inclusion of self-feedback weights to the wavelons of the wavelet layer. Furthermore, an on-line training procedure was proposed to enhance the control performance of the SRWNN-based MRAC. As the training method, the recently developed modified micro artificial immune system (MMAIS) was used to optimize the parameters of the SRWNN. The effectiveness of this control approach was demonstrated by controlling several nonlinear dynamical systems. For each of these systems, several evaluation tests were conducted, including control performance tests, robustness tests, and generalization tests. From these tests, the SRWNN-based MRAC has exhibited its effectiveness regarding accurate control, disturbance rejection, and generalization ability. In addition, a comparative study was made with other related controllers, namely the original WNN, the artificial neural network (ANN), and the modified recurrent network (MRN). The results of these comparison tests indicated the superiority of the SRWNN controller over the other related controllers.
 Keywords: Artificial neural network, micro artificial immune system, model reference adaptive control, self-recurrent wavelet neural network , Wavelet neural network.

Indirect adaptive fuzzy wavelet neural network with self- recurrent consequent part for AC servo system

This paper proposes a novel indirect adaptive fuzzy wavelet neural network (IAFWNN) to control the nonlinearity, wide variations in loads, time-variation and uncertain disturbance of the ac servo system. In the proposed approach, the self-recurrent wavelet neural network (SRWNN) is employed to construct an adaptive self-recurrent consequent part for each fuzzy rule of TSK fuzzy model. For the IAFWNN controller, the online learning algorithm is based on back propagation (BP) algorithm. Moreover, an improved particle swarm optimization (IPSO) is used to adapt the learning rate. The aid of an adaptive SRWNN identifier offers the real-time gradient information to the adaptive fuzzy wavelet neural controller to overcome the impact of parameter variations, load disturbances and other uncertainties effectively, and has a good dynamic. The asymptotical stability of the system is guaranteed by using the Lyapunov method. The result of the simulation and the prototype test prove that the proposed are effective and suitable.

Adaptive complementary fuzzy self-recurrent wavelet neural network controller for the electric load simulator system

Due to the complexities existing in the electric load simulator, this article develops a high-performance nonlinear adaptive controller to improve the torque tracking performance of the electric load simulator, which mainly consists of an adaptive fuzzy self-recurrent wavelet neural network controller with variable structure (VSFSWC) and a complementary controller. The VSFSWC is clearly and easily used for real-time systems and greatly improves the convergence rate and control precision. The complementary controller is designed to eliminate the effect of the approximation error between the proposed neural network controller and the ideal feedback controller without chattering phenomena. Moreover, adaptive learning laws are derived to guarantee the system stability in the sense of the Lyapunov theory. Finally, the hardware-in-the-loop simulations are carried out to verify the feasibility and effectiveness of the proposed algorithms in different working styles.

Adaptive PID controller design for wing rock suppression using self-recurrent wavelet neural network identifier

This paper presents a novel control scheme based on auto-tuning PID controller to suppress wing rock phenomena. Due to having a complex dynamic, wing rock motion identification is not a simple task, and this complexity can adversely affect the performance of PID controller. Employing a wavelet neural network based identifier, this paper develops an auto tuning adaptive PID controller to tackle the problem. Since having an acceptable control performance inevitably involves having a meticulously trained identifier, the training performance is of utmost importance. Aiming at boosting the training efficacy, a two-phase algorithm encompassing Bees algorithm and Back-Propagation (BP) is proposed by this paper to train the proposed identifier respectively in off-line and on-line modes. Due to its inherent capability in sifting the global minima, Bees algorithm is employed to find initial values of weights around which it is then possible to conduct a local search by means of BP based online training. Therefore, the identifier can precisely furnish the proposed PID controller with the system sensitivity in on-line mode. The adaption of PID controller can thus be performed in each time step. The performance of this method has been presented in simulation results and the comparison section confirms the effectiveness of proposed scheme.

An SRWNN-based approach on developing a self-learning and self-evolving adaptive control system for motion platforms

ABSTRACTIn this paper, a self-recurrent wavelet neural network (SRWNN)-based indirect adaptive control architecture is modified for performing speed control of a motion platform. The transient behaviour of the original learning algorithm has been improved by modifying the learning rate updates. The contribution of the proposed modification has been verified via both simulations and experiments. Moreover, the performance of the proposed architecture is compared with robust RST designs performed on a similar benchmark system, to show that via adaptive nonlinear control, it is possible to obtain a fast step response without degrading the robustness of a multi-body mechanical system. Finally, the architecture is further improved so as to possess structural learning for populating the SRWNNs automatically, rather than employing static network structures, and simulation results are provided to show the performance of the proposed structural learning algorithm.

Short-term electricity load forecasting of buildings in microgrids

Electricity load forecasting plays a key role in operation of power systems. Since the penetration of distributed and renewable generation is increasingly growing in many countries, Short-Term Load Forecast (STLF) of micro-grids is also becoming an important task. A precise STLF of the micro-grid can enhance the management of its renewable and conventional resources and improve the economics of energy trade with electricity markets. As a consequence of the highly non-smooth and volatile behavior of the load time series in a micro-grid, its STLF is even a more complex process than that of a power system. For this purpose, a new prediction method is proposed in this paper, in which a Self-Recurrent Wavelet Neural Network (SRWNN) is applied as the forecast engine. Moreover, the Levenberg–Marquardt (LM) learning algorithm is implemented and adapted to train the SRWNN. In order to demonstrate the efficiency of the proposed method, it is examined on real-world hourly data of an educational building within a micro-grid. Comparisons with other load prediction methods are provided.

Self-adaptive vibration control of simply supported beam under a moving mass using self-recurrent wavelet neural networks via adaptive learning rates

A self-recurrent wavelet neural network (SRWNN) is used to control suppression of vibration of an Euler–Bernoulli beam under excitation of a moving mass traveling along a vibrating path. The proposed control structure uses one SRWNN as an identifier and one as a controller. The SRWNN identifier is trained to model the dynamic behavior of the process and provide the SRWNN controller with information about system sensitivity. The SRWNN controller uses the sensitivity information provided by the SRWNN identifier to update weights and produce a signal that controls beam vibration. The gradient descent method and adaptive learning rates (ALRs) are used to update all SRWNN weights. The ALRs are obtained using the discrete Lyapunov stability theorem which guarantees the convergence of the proposed control structure. The performance and robustness of the proposed controller are evaluated at different mass ratios of moving mass to beam and for dimensionless velocity of a moving mass. The simulations verify the effectiveness and robustness of the controller.

Direct adaptive power system stabilizer design using fuzzy wavelet neural network with self-recurrent consequent part

This paper aims to propose a stable fuzzy wavelet neural-based adaptive power system stabilizer (SFWNAPSS) for stabilizing the inter-area oscillations in multi-machine power systems. In the proposed approach, a self-recurrent Wavelet Neural Network (SRWNN) is applied with the aim of constructing a self-recurrent consequent part for each fuzzy rule of a Takagi-Sugeno-Kang (TSK) fuzzy model. All parameters of the consequent parts are updated online based on Direct Adaptive Control Theory (DACT) and employing a back-propagation-based approach. The stabilizer initialization is performed using an approach based on genetic algorithm (GA). A Lyapunov-based adaptive learning rates (LALRs) algorithm is also proposed in order to speed up the stabilization rate, as well as to guarantee the convergence of the proposed stabilizer. Therefore, due to having a stable powerful adaptation law, there is no requirement to use any identification process. Kundur's four-machine two-area benchmark power system and six-machine three-area power system are used with the aim of assessing the effectiveness of the proposed stabilizer. The results are promising and show that the inter-area oscillations are successfully damped by the SFWNAPSS. Furthermore, the superiority of the proposed stabilizer is demonstrated over the IEEE standard multi-band power system stabilizer (MB-PSS), and the conventional PSS.