Recurrent Fuzzy Neural Network Research Articles

Robust Optimal Navigation Using Nonlinear Model Predictive Control Method Combined with Recurrent Fuzzy Neural Network

This paper presents a novel navigation strategy of robot to achieve reaching target and obstacle avoidance in unknown dynamic environment. Considering possible generation of uncertainty, disturbances brought to system are separated into two parts, i.e., bounded part and unbounded part. A dual-layer closed-loop control system is then designed to deal with two kinds of disturbances, respectively. In order to realize global optimization of navigation, recurrent fuzzy neural network is used to predict optimal motion of robot for its ability of processing nonlinearity and learning. Extended Kalman filter method is used to train RFNN online. Moving horizon technique is used for RFNN motion planner to guarantee optimization in dynamic environment. Then, model predictive control is designed against bounded disturbances to drive robot to track predicted trajectories and limit robot’s position in a tube with good robustness. A novel iterative online learning method is also proposed to estimate intrinsic error of system using online data that makes system adaptive. Feasibility and stability of proposed method are analyzed. By examining our navigation method on mobile robot, effectiveness is proved in both simulation and hardware experiments. Robustness and optimization of proposed navigation method can be guaranteed in dynamic environment.

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.

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.

Recurrent Neuro-Fuzzy Control of Grid-Interfaced Solid Oxide Fuel Cell (SOFC) System

The paper presents controller design, modelling, and simulations of the solid oxide fuel cell (SOFC) system. The SOFC model is used for the development of the fuzzy control scheme to improve the system performance. The SOFC is widely acknowledged for the clean distributed power generation. However, dire process problems occur frequently when the stand-alone fuel cell is directly interfaced with the electricity grid. Moreover, sustaining the optimal power quality and load following is the huge challenge, during the peak power demand schedule from the utility grid and large load perturbations. Consequently, a suitable and highly efficient control system is required for controlling and following the power load demands for the complex grid interfaced SOFC power systems. Therefore, a novel nonlinear hybrid adaptive recurrent fuzzy neural network (ARFNN) is developed for the control of the grid interfaced SOFC. The rapid power load following and safe SOFC operation requirement is also considered in the design of the closed loop control system. Simulation results proved that the proposed hybrid ARFNN enhances the optimal power quality and load-following than the conventional PI control scheme.

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.

Fault Accommodation Control for a Biped Robot Using a Recurrent Wavelet Elman Neural Network

A model-based fault accommodation control scheme that uses a recurrent wavelet Elman neural network (RWENN) is proposed to achieve satisfactory control without performance degradation for biped robot locomotion with unknown uncertainties and faults. In the fault accommodation scheme, a computed torque control is the main control that is used to track the desired trajectory when there is no fault; and a compensation control is used to eliminate the unknown model uncertainties. The proposed RWENN has an input from a context layer with self-feedback and an output recurrent layer to the hidden layer, which increases the precision and convergence time of the network compared with a recurrent neural network, a recurrent fuzzy neural network, and a recurrent wavelet neural network, so that any dynamic change, such as a fault on the system, can be estimated properly. Thus, it enhances the capability of fault accommodation. The adaptive laws of the RWENN-based fault accommodation control are derived from the Lyapunov theorem; hence, the stability of the system can be guaranteed. Finally, a case study of biped robot control with multiple faults and uncertainties is analyzed, and the effectiveness of the proposed fault accommodation scheme is demonstrated by simulation results. Its superiority is also assessed by a numerical comparison with other neural-network-based control schemes.

An intelligent detecting system for permeability prediction of MBR.

The membrane bioreactor (MBR) has been widely used to purify wastewater in wastewater treatment plants. However, a critical difficulty of the MBR is membrane fouling. To reduce membrane fouling, in this work, an intelligent detecting system is developed to evaluate the performance of MBR by predicting the membrane permeability. This intelligent detecting system consists of two main parts. First, a soft computing method, based on the partial least squares method and the recurrent fuzzy neural network, is designed to find the nonlinear relations between the membrane permeability and the other variables. Second, a complete new platform connecting the sensors and the software is built, in order to enable the intelligent detecting system to handle complex algorithms. Finally, the simulation and experimental results demonstrate the reliability and effectiveness of the proposed intelligent detecting system, underlying the potential of this system for the online membrane permeability for detecting membrane fouling of MBR.

An Incremental Learning of Concept Drifts Using Evolving Type-2 Recurrent Fuzzy Neural Networks

The age of online data stream and dynamic environments results in the increasing demand of advanced machine learning techniques to deal with concept drifts in large data streams. Evolving fuzzy systems (EFS) are one of recent initiatives from the fuzzy system community to resolve the issue. Existing EFSs are not robust against data uncertainty, temporal system dynamics, and the absence of system order, because a vast majority of EFSs are designed in the type-1 feedforward network architecture. This paper aims to solve the issue of data uncertainty, temporal behavior, and the absence of system order by developing a novel evolving recurrent fuzzy neural network, called evolving type-2 recurrent fuzzy neural network (eT2RFNN). eT2RFNN is constructed in a new recurrent network architecture, featuring double recurrent layers. The new recurrent network architecture evolves a generalized interval type-2 fuzzy rule, where the rule premise is built upon the interval type-2 multivariate Gaussian function, whereas the rule consequent is crafted by the nonlinear wavelet function. The eT2RFNN adopts a holistic concept of evolving systems, where the fuzzy rule can be automatically generated, pruned, merged, and recalled in the single-pass learning mode. eT2RFNN is capable of coping with the problem of high dimensionality because it is equipped with online feature selection technology. The efficacy of eT2RFNN was experimentally validated using artificial and real-world data streams and compared with prominent learning algorithms. eT2RFNN produced more reliable predictive accuracy, while retaining lower complexity than its counterparts.

Bayesian network based extreme learning machine for subjectivity detection

Subjectivity detection is a task of natural language processing that aims to remove ‘factual’ or ‘neutral’ content, i.e., objective text that does not contain any opinion, from online product reviews. Such a pre-processing step is crucial to increase the accuracy of sentiment analysis systems, as these are usually optimized for the binary classification task of distinguishing between positive and negative content. In this paper, we extend the extreme learning machine (ELM) paradigm to a novel framework that exploits the features of both Bayesian networks and fuzzy recurrent neural networks to perform subjectivity detection. In particular, Bayesian networks are used to build a network of connections among the hidden neurons of the conventional ELM configuration in order to capture dependencies in high-dimensional data. Next, a fuzzy recurrent neural network inherits the overall structure generated by the Bayesian networks to model temporal features in the predictor. Experimental results confirmed the ability of the proposed framework to deal with standard subjectivity detection problems and also proved its capacity to address portability across languages in translation tasks.

Wastewater treatment control method based on a rule adaptive recurrent fuzzy neural network

PurposeThe purpose of this paper is to present an on-line modeling and controlling scheme based on the dynamic recurrent neural network for wastewater treatment system.Design/methodology/approachA control strategy based on rule adaptive recurrent neural network (RARFNN) is proposed in this paper to control the dissolved oxygen (DO) concentration and nitrate nitrogen (SNo) concentration. The structure of the RARFNN is self-organized by a rule adaptive algorithm, and the rule adaptive algorithm considers the overall information processing ability of neural network. Furthermore, a stability analysis method is given to prove the convergence of the proposed RARFNN.FindingsBy application in the control problem of wastewater treatment process (WWTP), results show that the proposed control method achieves better performance compared to other methods.Originality/valueThe proposed on-line modeling and controlling method uses the RARFNN to model and control the dynamic WWTP. The RARFNN can adjust its structure and parameters according to the changes of biochemical reactions and pollutant concentrations. And, the rule adaptive mechanism considers the overall information processing ability judgment of the neural network, which can ensure that the neural network contains the information of the biochemical reactions.

Improvement of Transient Stability in a Hybrid Power Multi-System Using a Designed NIDC (Novel Intelligent Damping Controller)

This paper endeavors to apply a novel intelligent damping controller (NIDC) for the static synchronous compensator (STATCOM) to reduce the power fluctuations, voltage support and damping in a hybrid power multi-system. In this paper, we discuss the integration of an offshore wind farm (OWF) and a seashore wave power farm (SWPF) via a high-voltage, alternating current (HVAC) electric power transmission line that connects the STATCOM and the 12-bus hybrid power multi-system. The hybrid multi-system consists of a battery energy storage system (BESS) and a micro-turbine generation (MTG). The proposed NIDC consists of a designed proportional–integral–derivative (PID) linear controller, an adaptive critic network and a proposed functional link-based novel recurrent fuzzy neural network (FLNRFNN). Test results show that the proposed controller can achieve better damping characteristics and effectively stabilize the network under unstable conditions.

Design of an adaptive intelligent control scheme for switched reluctance wind generator

PurposeThis paper aims to present the analysis, design and implementation of functional link-based recurrent fuzzy neural network (FLRFNN) for the control of variable-speed switched reluctance generator (SRG).Design/methodology/approachThe node connecting weights of the FLRFNN are trained online by back-propagation (BP) algorithms. The proposed estimator requires less processing time than traditional methods and can be fully implemented using a low-cost digital signal processor (DSP) with MATLAB toolboxes. The DSP-based hybrid sensor presented in this paper can be applied to a wind energy-conversion system where the SRG is used as a variable-speed generator. The current transducer is used to monitor the energized current and proximity sensors for rotor salient.FindingsThe authors have found that optimal based on FLRFNN with Grey controller can resolve the regulation of the system with uncertainty model and unknown disturbances. This technique can maintain the system stability and reach the desired performance even with parameter uncertainties.Originality/valueThis design will improve the performance of SRG to operate more smoothly. This application is currently being studied because the SRG has well-known advantages such as robustness, low manufacturing cost and good size-to-power ratio. Performance of the proposed controller can offer better stability characteristics. Finally, the SRG has a very good efficiency in the whole operating range.

Recurrent Fuzzy Cerebellar Model Articulation Neural Network Based Power Control of a Single-Stage Three-Phase Grid-Connected Photovoltaic System During Grid Faults

A recurrent fuzzy cerebellar model articulation neural network (RFCMANN)-based controller to regulate the active and reactive power of a single-stage three-phase grid-connected photovoltaic (PV) system during grid faults is proposed in this study. Since the rapid growth of the amount of the PV systems in recent year has greatly affected the stability of the power system, the grid codes demand the grid-connected PV systems to have the low-voltage ride through (LVRT) capability to help sustaining the stability of power system especially during the grid faults. To satisfy the LVRT requirements and ensure the injected current within the safety value, the active and reactive power commands are calculated by using the current profile of the LVRT grid requirements and the current limit of the inverter. Moreover, the proposed RFCMANN controller uses the signed distance and input space repartition mechanisms to convert the dual-input variables to sole-input variable and repartition the input space to an appropriate quantity. Therefore, the structure and computation complexities of the proposed RFCMANN controller are effectively reduced and make it more practical. Furthermore, varied learning-rate coefficients are designed to guarantee the convergence of the tracking error for the proposed RFCMANN controller.

Intelligent wind power smoothing control with BESS

An intelligent wind power smoothing control using recurrent fuzzy neural network (RFNN) is proposed in this study. First, the modeling of wind power generator and the designed battery energy storage system (BESS) are introduced. The BESS is consisted of a bidirectional interleaved DC/DC converter and a 3-arm 3-level inverter. Then, the network structure of the RFNN and its online learning algorithms are described in detail. Moreover, actual wind data is adopted as the input to the designed wind power generator model. Furthermore, the three-phase output currents of the wind power generator are converted to dq-axis current components. The resulted q-axis current is the input of the RFNN power smoothing control and the output is a gentle wind power curve to achieve the effect of wind power smoothing. The difference of the actual wind power and smoothed power is supplied by the BESS. The minimum energy capacity of the BESS with a small fluctuation of the grid power can be achieved by the RFNN power smoothing control. A digital signal processor (DSP) based BESS is built using two TMS320F28335. From the experimental results of various wind variation sceneries, the effectiveness of the proposed intelligent wind power smoothing control is verified.

Diagnosis of heart disease using genetic algorithm based trained recurrent fuzzy neural networks

The World Health Organization (WHO) estimated one third of all global deaths reason as cardiovascular diseases in 2015. Some computational techniques were proposed for investigation of heart diseases. This study proposes a genetic algorithm (GA) based trained recurrent fuzzy neural networks (RFNN) to diagnosis of heart diseases. The University of California Irvine (UCI) Cleveland heart disease dataset is used in this study. Out of total 297 instances of patient data, 252 are used for training and 45 of them are chosen to be the testing. The results showed that 97.78% accuracy was obtained from testing set. In addition to the accuracy, root mean square error, the probability of the misclassification error, specificity, sensitivity, precision and F-score are calculated. The results were found to be satisfying based on comparison.

Image Backlight Compensation Using Recurrent Functional Neural Fuzzy Networks Based on Modified Differential Evolution

In this study, an image backlight compensation method using adaptive luminance modification is proposed for efficiently obtaining clear images.The proposed method combines the fuzzy C-means clustering method, a recurrent functional neural fuzzy network (RFNFN), and a modified differential evolution.The proposed RFNFN is based on the two backlight factors that can accurately detect the compensation degree. According to the backlight level, the compensation curve function of a backlight image can be adaptively adjusted. In our experiments, six backlight images are used to verify the performance of proposed method.Experimental results demonstrate that the proposed method performs well in backlight problems.

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.

Neuro-fuzzy models for hand movements induced by functional electrical stimulation in able-bodied and hemiplegic subjects

Functional Electrical Stimulation (FES) may be effective as a therapeutic treatment for improving functional reaching and grasping. Upper-limb FES models for predicting joint torques/angles from stimulation parameters can be useful to support the iterative design and development of neuroprostheses. Most such models focused on shoulder or elbow joints and were defined for fixed electrode configurations. This work proposes the use of a Recurrent Fuzzy Neural Network (RFNN) for modeling FES induced wrist, thumb, and finger movements based on surface multi-field electrodes and kinematic data from able-bodied and neurologically impaired subjects. Different combinations of structure parameters comprising fuzzy term numbers and feedback approaches were tested and analyzed in order to see their effect on the model performance for six subjects. The results showed mean success rates in the range from 60% to 99% and best success rates in the range from 78% to 100% on test data for all subjects. No common trend was found across subjects regarding structure parameters. The model showed the ability to successfully reproduce the response to FES for both able-bodied and hemiplegic subjects at least with one of the tested combinations.