Recurrent Wavelet Neural Network Research Articles

Voltage Control of PM Synchronous Generator System Using Recurrent Wavelet Neural Network Controller

A recurrent wavelet neural network (RWNN) controller is proposed to control output voltages for a permanent magnet synchronous motor (PMSM) direct drive three-phase permanent magnet synchronous generator (PMSG) system at stand-alone power application in this paper. First, the field-oriented mechanism is implemented for the control of the PMSG system. Then, a rectifier (AC/DC power converter) and an inverter (DC/AC power converter) are developed to convert the electric power generated by a three-phase PMSG system. Moreover, two online trained RWNNs using backpropagation learning algorithm are developed as the regulating controllers for both the DC-link voltage of the rectifier and the AC line voltage of the inverter. Finally, to show the effectiveness of the proposed controller, comparative studies with PI controller are demonstrated by experimental results.

Output recurrent wavelet neural network-based adaptive backstepping controller for a class of MIMO nonlinear non-affine uncertain systems

In this paper, an adaptive backstepping control problem is proposed for a class of multiple-input-multiple-output nonlinear non-affine uncertain systems. An output recurrent wavelet neural network (ORWNN) is used to approximate the unknown nonlinear functions to develop the proposed adaptive backstepping controller. The proposed ORWNN combines the advantages of wavelet-based neural network, fuzzy neural network, and output feedback layer to achieve higher approximation accuracy and faster convergence. According to the estimation of ORWNN, the control scheme is designed by backstepping approach such that the system outputs follow the desired trajectories. Based on the Lyapunov approach, our approach guarantees that the system outputs converge to a small neighborhood of the references signals, that is, all signals of the closed-loop system are semi-globally uniformly ultimately bounded. Finally, simulation results including double pendulums system and two inverted pendulums on carts system are shown to demonstrate the performance and effectiveness of our approach.

A Novel Hybrid Recurrent Wavelet Neural Network Control for a PMSM Driven Electric Scooter

The electric scooter with nonlinear friction force of the transmission belt made the hybrid recurrent neural network (HRNN) control system with degenerated tracking responses. In order to overcome this problem, a hybrid recurrent wavelet neural network (HRWNN) control system is proposed to control for a permanent magnet synchronous motor (PMSM) driven electric scooter. The HRWNN control system consists of a supervisor control, a RWNN and a compensated control with adaptive law. The on-line parameter training methodology of the RWNN can be derived using adaptation laws and the Lyapunov stability theorem. The RWNN has the on-line learning ability to respond to the system’s nonlinear and time-varying behaviors. To show the effectiveness of the proposed controller, comparative studies with HRNN control system is demonstrated by experimental results.

Intelligent control system design for UAV using a recurrent wavelet neural network

This paper aims to propose an efficient control algorithm for the unmanned aerial vehicle (UAV) motion control. An intelligent control system is proposed by using a recurrent wavelet neural network (RWNN). The developed RWNN is used to mimic an ideal controller. Moreover, based on sliding-mode approach, the adaptive tuning laws of RWNN can be derived. Then, the developed RWNN control system is applied to an UAV motion control for achieving desired trajectory tracking. From the simulation results, the control scheme has been shown to achieve favorable control performance for the UAV motion control even it is subjected to control effort deterioration and crosswind disturbance.

Innovative second-generation wavelets construction with recurrent neural networks for solar radiation forecasting.

Solar radiation prediction is an important challenge for the electrical engineer because it is used to estimate the power developed by commercial photovoltaic modules. This paper deals with the problem of solar radiation prediction based on observed meteorological data. A 2-day forecast is obtained by using novel wavelet recurrent neural networks (WRNNs). In fact, these WRNNS are used to exploit the correlation between solar radiation and timescale-related variations of wind speed, humidity, and temperature. The input to the selected WRNN is provided by timescale-related bands of wavelet coefficients obtained from meteorological time series. The experimental setup available at the University of Catania, Italy, provided this information. The novelty of this approach is that the proposed WRNN performs the prediction in the wavelet domain and, in addition, also performs the inverse wavelet transform, giving the predicted signal as output. The obtained simulation results show a very low root-mean-square error compared to the results of the solar radiation prediction approaches obtained by hybrid neural networks reported in the recent literature.

Dynamic Recurrent Wavelet Neural Network Observer Based Tracking Control for a Class of Uncertain Nonaffine Systems

In this paper, a dynamic recurrent wavelet neural network observer and tracking control strategy is presented for a class of uncertain, nonaffine systems. In proposed scheme a dynamic recurrent wavelet network is used to design a nonlinear observer .Adaptation laws are developed for the online tuning of wavelet parameters. Based on the estimated states, a state feedback control law is derived to achieve the desired tracking performance. The stability of closed loop system and ultimate upper boundedness all closed loop signals is proven in Lyapunov sense. Effectiveness of proposed scheme is demonstrated through numerical simulation.

Dynamic Recurrent Wavelet Neural Network Observer Based Tracking Control for a Class of Uncertain Nonaffine Systems

In this paper, a dynamic recurrent wavelet neural network observer and tracking control strategy is presented for a class of uncertain, nonaffine systems. In proposed scheme a dynamic recurrent wavelet network is used to design a nonlinear observer .Adaptation laws are developed for the online tuning of wavelet parameters. Based on the estimated states, a state feedback control law is derived to achieve the desired tracking performance. The stability of closed loop system and ultimate upper boundedness all closed loop signals is proven in Lyapunov sense. Effectiveness of proposed scheme is demonstrated through numerical simulation.

A multiple adaptive wavelet recurrent neural network model to analyze crude oil prices

International crude oil prices are an important part of the economy, and trends in changing oil prices have an effect on financial markets. Traditional hybrid analysis methods for international crude oil prices, such as wavelet transform and back propagation neural network (BPNN), seek synergy effects by sequentially filtering data through different models. However, these estimation methods cause loss of information through the introduction of biases in each filtering step, which are aggregated throughout the process when model assumptions are violated, and the traditional BPNN model does not have forecasting ability. In this study, we constructed a multiple wavelet recurrent neural network (MWRNN) simulation model, in which trend and random components of crude oil and gold prices were considered. The wavelet analysis was utilized to capture multiscale data characteristics, while a real neural network (RNN) was utilized to forecast crude oil prices at different scales. Finally, a standard BPNN was added to combine these independent forecasts from different scales into an optimal prediction of crude oil prices. The simulation results showed that the model has high prediction accuracy. The designed neural network is able to predict oil prices with an average error of 4.06% for testing and 3.88% for training data. This forecasting model would be able to predict the world crude oil prices with any commercial energy source prices instead of the gold prices.

Two Types of Haar Wavelet Neural Networks for Nonlinear System Identification

Since wavelet transform uses the multi-scale (or multi-resolution) techniques for time series, wavelet transform is suitable for modeling complex signals. Haar wavelet transform is the most commonly used and the simplest one. The Haar wavelet neural network (HWNN) applies the Harr wavelet transform as active functions. It is easy for HWNN to model a nonlinear system at multiple time scales and sudden transitions. In this paper, two types of HWNN, feedforward and recurrent wavelet neural networks, are used to model discrete-time nonlinear systems, which are in the forms of the NARMAX model and state-space model. We first propose an optimal method to determine the structure of HWNN. Then two stable learning algorithms are given for the shifting and broadening coefficients of the wavelet functions. The stability of the identification procedures is proven.

Adaptive dynamic surface control with sliding mode control and RWNN for robust positioning of a linear motion stage

Ball-screw-driven system provides high precision and long stroke range for positioning and tracking control of a linear stage. Friction and backlash nonlinearities in this system act often the main obstacles for high precision control. It is difficult to achieve effective compensation of these types of nonlinearities by traditional linear control methodology without the aid of a proper compensation schemes. Here, we present an adaptive dynamic surface control scheme combined with sliding mode control to compensate for friction and backlash nonlinearities in a linear stage motion system. The adaptive laws of the recurrent wavelet neural networks and friction estimation are derived to approximate and compensate for the backlash and friction nonlinearities. The boundedness and convergence of the closed-loop system are guaranteed from a Lyapunov stability analysis. The performance of the proposed control scheme was verified through simulations and experiments on the ball-screw-driven linear stage.

ADAPTIVE CONTROL FOR MIMO UNCERTAIN NONLINEAR SYSTEMS USING RECURRENT WAVELET NEURAL NETWORK

Recurrent wavelet neural network (RWNN) has the advantages such as fast learning property, good generalization capability and information storing ability. With these advantages, this paper proposes an RWNN-based adaptive control (RBAC) system for multi-input multi-output (MIMO) uncertain nonlinear systems. The RBAC system is composed of a neural controller and a bounding compensator. The neural controller uses an RWNN to online mimic an ideal controller, and the bounding compensator can provide smooth and chattering-free stability compensation. From the Lyapunov stability analysis, it is shown that all signals in the closed-loop RBAC system are uniformly ultimately bounded. Finally, the proposed RBAC system is applied to the MIMO uncertain nonlinear systems such as a mass-spring-damper mechanical system and a two-link robotic manipulator system. Simulation results verify that the proposed RBAC system can achieve favorable tracking performance with desired robustness without any chattering phenomenon in the control effort.

Predictive Control of the VAV System Based on Recurrent Wavelet Neural Network

An air supply control method of VAV system based on BP neural network is proposed in this paper, which combines with the recurrent wavelet neural network model, predictive control and optimization of parameters. With the proposed method, the air volume of the VAV system can be controlled accurately even if the change of the air is nonlinear and time-lapse. Compared with tradition control method, it has the advantages of rapidly converging, high control precision, strong skills of learning and wide application prospect.

Performance Improvement of GPS GDOP Approximation Using Recurrent Wavelet Neural Network

One of the most important factors affecting the precision of the performance of a GPS receiver is the relative positioning of satellites to each other. Therefore, it is essential to choose appropriate accessible satellites utilized in the calculation of GPS positions. Optimal subsets of satellites are determined using the least value of their Geometric Dilution of Precision (GDOP). The most correct method of calculating GPS GDOP uses inverse matrix for all combinations and selecting the lowest ones. However, the inverse matrix method, especially when there are so many satellites, imposes a huge calculation load on the processor of the GPS navigator. In this paper, the rapid and precise calculation of GPS GDOP based on Recurrent Wavelet Neural Network (RWNN) has been introduced for selecting an optimal subset of satellites. The method of NNs provides a realistic calculation approach to determine GPS GDOP without any need to calculate inverse matrix.

A Novel Adaptive Self-turned PID controller based on Recurrent-Wavelet-Neural-Network for PMSM Speed Servo Drive System

The conventional PID controller can not have a satisfactory performance when it has been applied in the permanent-magnet synchronous motor (PMSM) speed regulation system which has the characteristics of nonlinearity, strong coupling and multi-variable. With the purpose to solve this problem, a new hybrid control algorithm utilizing recurrent wavelet neural network (RWNN) is proposed, which can adjust parameters on line to be adaptive to the parameter variety and load disturbance. The effectiveness of the proposed controller is demonstrated by numerical simulations and experiments. It is proved that this scheme not only has good dynamics and steady-state performance but also enhances the robustness of system.

Sliding mode recurrent wavelet neural network control for robust positioning of uncertain dynamic systems

For an uncertain dynamic system, a hybrid control system composed of sliding mode and recurrent wavelet neural network control with friction estimation (SRWNF) has been proposed to achieve robust motion performance. In the present study, a model-free adaptive controller that does not require the system dynamics to be determined in advance is developed by the proposed recurrent wavelet neural network (RWNN). The adaptive laws of the SRWNF control system and friction estimator have been constructed from the approximation theory and the sense of the Lyapunov stability analysis for RWNN technology to mimic ideal control laws in a sliding-mode control. In addition, an adaptive bound estimation law is employed to estimate the upper boundary of approximation errors. The friction state and parameters are estimated using an adaptive friction estimation based on the LuGre friction model. The boundary of the constraint sets has also been studied. The performance of the proposed control scheme in the presence of uncertainty and friction has been verified by some simulation and an experiment.

Field-programmable gate array-based intelligent dynamic sliding-mode control using recurrent wavelet neural network for linear ultrasonic motor

A field-programmable gate array (FPGA)-based intelligent dynamic sliding-mode control (IDSMC) using recurrent wavelet neural network (RWNN) estimator is proposed to control the mover position of a linear ultrasonic motor (LUSM) in this study. First, the structure and operating principles of the LUSM are introduced briefly. Then, the dynamics of LUSM mechanism with the introduction of a lumped uncertainty, which include the friction force, is derived. Since the dynamic characteristics and motor parameters of the LUSM are non-linear and time-varying, an IDSMC using RWNN estimator is designed to achieve robust control performance of the LUSM drive system. The RWNN estimator is employed to estimate the non-linear functions including the system parameters and external disturbance. Moreover, the adaptive learning algorithm trained the parameters of the RWNN online is derived using the Lyapunov stability theorem. Furthermore, an FPGA chip is adopted to implement the developed control and on-line learning algorithms for possible low-cost and high-performance industrial applications. The experimental results show that excellent positioning and tracking performance are achieved. In addition, the robustness to parameter variations and friction force can be obtained as well using the proposed control system.

Recurrent wavelet neural backstepping controller design with a smooth compensator

Recurrent wavelet neural network (RWNN) has the advantages in its dynamic responses and information storing ability. This paper develops a recurrent wavelet neural backstepping control (RWNBC) scheme for multiple-input multiple-output (MIMO) mechanical systems. This proposed RWNBC comprises a neural controller and a smooth compensator. The neural controller using an RWNN is the principal tracking controller utilized to mimic an ideal backstepping control law; and the parameters of RWNN are online tuned by the derived adaptation laws from the Lyapunov stability theorem. The smooth compensator is designed to dispel the approximation error introduced by the neural controller, so that the asymptotic stability of the closed-loop system can be guaranteed. Finally, two MIMO mechanical systems, a mass-spring-damper system and a two-inverted pendulum system, are performed to verify the effectiveness of the proposed RWNBC scheme. From the simulation results, it is verified that the proposed RWNBC scheme can achieve favorable tracking performance without any chattering phenomenon.

Design and Application of Stable Predictive Controller Using Recurrent Wavelet Neural Networks

This paper presents a design methodology for stable predictive control of nonlinear discrete-time systems via recurrent wavelet neural networks (RWNNs). This type of controller has its simplicity in parallelism to conventional generalized predictive control design and efficiency to deal with complex nonlinear dynamics. A mathematical model using RWNN is constructed, and a learning algorithm adopting a recursive least squares is employed to identify the unknown parameters in the consequent part of the RWNN. The proposed control law is derived based on the minimization of a modified predictive performance criterion. Two theorems are presented for the conditions of the stability analysis and steady-state performance of the closed-loop systems. Numerical simulations reveal that the proposed control gives satisfactory tracking and disturbance rejection performances. Experimental results for position control of a positioning mechanism show the efficacy of the proposed method with setpoint changes.

Field-programmable gate array-based recurrent wavelet neural network control system for linear ultrasonic motor

A field-programmable gate array (FPGA)-based recurrent wavelet neural network (RWNN) control system is proposed to control the mover position of a linear ultrasonic motor (LUSM). First, the structure and operating principles of the LUSM are introduced. Since the dynamic characteristics and motor parameters of the LUSM are non-linear and time-varying, an RWNN controller is designed to improve the control performance for the precision tracking of various reference trajectories. The network structure and its on-line learning algorithm using delta adaptation law of the RWNN are described in detail. Moreover, the connective weights, translations and dilations of the RWNN are trained on-line. Furthermore, to guarantee the convergence of the tracking error, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the RWNN. In addition, an FPGA chip is adopted to implement the developed control algorithm for possible low-cost and high-performance industrial applications. Finally, the effectiveness of the proposed control system is verified by some experimental results.

Recurrent wavelet neural network controller with improved particle swarm optimisation for induction generator system

A recurrent wavelet neural network (RWNN) controller with improved particle swarm optimisation (IPSO) is proposed to control a three-phase induction generator (IG) system for stand-alone power application. First, the indirect field-oriented mechanism is implemented for the control of the IG. Then, an AC/DC power converter and a DC/AC power inverter are developed to convert the electric power generated by a three-phase IG from variable frequency and variable voltage to constant frequency and constant voltage. Moreover, two online trained RWNNs using backpropagation learning algorithm are introduced as the regulating controllers for both the DC-link voltage of the AC/DC power converter and the AC line voltage of the DC/AC power inverter. Furthermore, an IPSO is adopted to adjust the learning rates to further improve the online learning capability of the RWNN. Finally, some experimental results are provided to demonstrate the effectiveness of the proposed IG system.