Adaptive Fuzzy Neural Network Control Research Articles

Adaptive fuzzy control for a marine vessel with time‐varying constraints

An adaptive fuzzy neural network (FNN) control scheme is proposed for a marine vessel with time-varying constraints, guaranteed transient response and unknown dynamics. A series of continuous constraint functions are introduced to shape the motion of a marine vessel. To deal with the constraint problems and transient response problems, an asymmetric time-varying barrier Lyapunov function is designed to ensure that the system states are upper bounded by the considered constraint functions. FNNs are constructed to identify the unknown dynamics. Considering existing approximation errors when FNNs approximating the unknown dynamics, an adaptive term is designed to compensate the approximation errors in order to obtain accurate control. Via Lyapunov stability theory, it has been proved that all the states in the closed-loop system are uniformly bounded ultimately without violating the corresponding prescribed constraint region. Two comparative simulations are carried out to verify the effectiveness of the proposed control.

Multiobjective design of fuzzy neural network controller for wastewater treatment process

In this paper, an improved multiobjective optimal control (MOOC) strategy is developed to improve the operational efficiency, satisfy the effluent quality (EQ) and reduce the energy consumption (EC) in wastewater treatment process (WWTP). First, the adaptive kernel function models of the process, which can describe the complex dynamics of EQ and EC, are developed for the proposed MOOC strategy. Meanwhile, a multiobjective optimization problem is constituted to account for WWTP. Second, an improved multiobjective particle swarm optimization (MOPSO) algorithm, using a self-adaptive flight parameters mechanism and a multiobjective gradient (MOG) method, is designed to minimize the established objectives. And then the optimal set-points of dissolved oxygen (SO) and nitrate (SNO) are obtained in the treatment process. Third, an adaptive fuzzy neural network controller (FNNC) is applied for realizing the tracking control of the obtained set-points in the proposed MOOC strategy. Finally, Benchmark Simulation Model No.1 (BSM1) is introduced to evaluate the effectiveness of the proposed MOOC strategy. Experimental results show the efficacy of the proposed method.

Adaptive fuzzy neural network control of wastewater treatment process with multiobjective operation

Abstract This study investigates an adaptive fuzzy neural network control system for the multiobjective operation of wastewater treatment process (WWTP) with standard effluent quality (EQ) as well as low energy consumption (EC). The control system consists of an optimization module with the adaptive multiobjective differential evolution (AMODE) algorithm and a control module with the adaptive fuzzy neural network (AFNN). First, an AMODE algorithm, using the adaptive adjustment strategies for selecting the suitable scaling factor and crossover rate, is developed to optimize all objectives simultaneously. Then, the optimal set-points of the dissolved oxygen concentration in the fifth tank ( S O5 ) and the nitrogen nitrate concentration in the second anoxic tank ( S NO2 ) of WWTP can be obtained by the AMODE algorithm. Second, an AFNN controller, based on an adaptive second order algorithm, is employed to trace the set-points of S O5 and S NO2 for achieving the process performance. Finally, the proposed control system is applied on the Benchmark Simulation Model 1 (BSM1). The performance comparison with other algorithms indicates that the proposed control system yields better effluent qualities and lower average operation consumption.

Adaptive Fuzzy Neural Network Control for a Constrained Robot Using Impedance Learning.

This paper investigates adaptive fuzzy neural network (NN) control using impedance learning for a constrained robot, subject to unknown system dynamics, the effect of state constraints, and the uncertain compliant environment with which the robot comes into contact. A fuzzy NN learning algorithm is developed to identify the uncertain plant model. The prominent feature of the fuzzy NN is that there is no need to get the prior knowledge about the uncertainty and a sufficient amount of observed data. Also, impedance learning is introduced to tackle the interaction between the robot and its environment, so that the robot follows a desired destination generated by impedance learning. A barrier Lyapunov function is used to address the effect of state constraints. With the proposed control, the stability of the closed-loop system is achieved via Lyapunov's stability theory, and the tracking performance is guaranteed under the condition of state constraints and uncertainty. Some simulation studies are carried out to illustrate the effectiveness of the proposed scheme.

Adaptive Iterative Learning Control for Freeway Traffic Flow Systems Using Improved Bacterial Foraging Optimized Desired Traffic Densities Planning

In this paper, we propose a discrete fuzzy-neural adaptive iterative learning control (AILC) for freeway traffic flow systems with random initial resetting errors, iteration-varying desired traffic densities, and random bounded off-ramp traffic volumes using traffic densities, space mean speeds, and on-ramp waiting queues design. It is assumed that the system nonlinear functions and input gains are unknown for controller design. An adaptive fuzzy-neural network controller and an adaptive robust controller are applied to compensate for the unknown system nonlinearities and input gains, respectively. Moreover, to deal with the disturbances from random bounded off-ramp traffic volumes, a dead-zone like auxiliary error with a time-varying boundary layer is introduced as a bounding parameter. This proposed auxiliary error is also utilized to construct the adaptive laws without using the bound of the input gain. The traffic density tracking error is shown to converge along the axis of learning iteration to a residual set whose level of magnitude depends on the width of boundary layer. Besides, since the nice desired traffic densities designed for the coordinated control objective of the AILC for freeway traffic flow systems are generally unknown, the improved bacterial forging optimization (IBFO) algorithm is used to optimize the fitness function, which is constructed by the coordinated control objective including (1) minimum total travel time, (2) minimum on-ramp average waiting time, and (3) minimum changes of desired traffic densities. Finally, a computer simulation example is used to verify the learning performance of the proposed fuzzy-neural AILC for freeway traffic flow systems using IBFO-based desired traffic densities planning.

Indirect Adaptive Fuzzy Supervisory Control with State Observer for Unknown Nonlinear Time Delay System

This paper proposes an indirect adaptive fuzzy neural network (FNN) controller with state observer and supervisory controller for a class of uncertain nonlinear dynamic time delay systems. First, the approximate function of unknown time delay system is inferred by the adaptive time delay FNN system. Next, a state observer is designed to estimate the unknown system states and the indirect adaptive fuzzy controller is constructed. Finally, the closed loop controller is obtained by incorporating the supervisory controller with the indirect adaptive fuzzy controller. Therefore, if the system tends to unstable, i.e., error dynamics is larger than a prescribed constraint which is determined by designer, the supervisory controller will activate to force the state to be stable. The free parameters of the indirect adaptive FNN controller can be tuned online by observer-based output feedback control law and adaptive laws by means of Lyapunov stability criterion. The resulting simulation example shows that the performance of nonlinear time delay chaotic system is fully tracking the reference trajectory. Meanwhile, simulation results show that the adaptive control effort of the proposed control scheme is much less due to the assist of the supervisory controller.

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.

Design of Adaptive Fuzzy-Neural-Network Control for a Single-Stage Boost Inverter

This study mainly focuses on the development of an adaptive fuzzy-neural-network control (AFNNC) system for a single-stage boost inverter. First, the dynamic model of a single-stage boost inverter is analyzed and is built for the later control manipulation. Then, a total sliding-mode control (TSMC) framework without the reaching phase in conventional SMC is developed for enhancing the system robustness during the transient response of the voltage tracking control. In order to alleviate the control chattering phenomena caused by the sign function in the TSMC design and relax the requirement of detailed system dynamics, an AFNNC system is further investigated to imitate the TSMC law for the boost inverter. In the AFNNC system, online learning algorithms are derived in the sense of Lyapunov stability theorem and projection algorithm to ensure the stability of the controlled system without the requirement of auxiliary compensated controllers despite the existence of uncertainties. The output of the AFNNC system can be easily supplied to the duty cycle of the power switch in the boost inverter without strict constraints on control parameters selection in conventional control strategies. In addition, the effectiveness of the proposed AFNNC scheme is verified by realistic experiments, and its advantages are indicated in comparison with a traditional double-loop proportional-integral control scheme and the TSMC framework.

Design of Adaptive Control and Fuzzy Neural Network Control for Single-Stage Boost Inverter

This study mainly focuses on the development of two newly designed control strategies including an adaptive control scheme and a fuzzy neural network (FNN) control system for a single-stage boost inverter. First, the dynamic model of a single-stage boost inverter is analyzed and built for the later control manipulation. Then, a model-based adaptive control scheme and a model-free FNN control system with varied learning rates are designed sequentially. The effectiveness of the proposed adaptive control scheme and the proposed FNN control system is verified by experimental results of a 1-kW single-stage boost inverter prototype, and their merits are indicated in comparison with a traditional double-loop proportional-integral (PI) control framework. Experimental results show that the superior FNN control system has significant improvements of 45.2% total harmonic distortion and 37.1% normalized mean square error compared to the conventional double-loop PI control framework under nonlinear loads.

Reference Model with an Adaptive Hermite Fuzzy Neural Network Controller for Tracking a Synchronous Reluctance Motor

This article presents a reference adaptive Hermite fuzzy neural network controller for a synchronous reluctance motor. Although synchronous reluctance motors are mathematically and structurally simple, they perform poorly under dynamic modes of operation because certain parameters, such as the external load and non-linear friction, are difficult to control. The proposed adaptive Hermite fuzzy neural network controller overcomes this problem, as using the Hermite function instead of the conventional Gaussian function shortens the training time. Furthermore, the proposed adaptive Hermite fuzzy neural network controller uses an online self-tuning fuzzy neural network to estimate the system's lumped uncertainty. The estimation method involves a fuzzy controller with expert knowledge of the initial weight of the neural network. Finally, the Lyapunov stability theory and adaptive update law were applied to guarantee system convergence. In this article, the responsiveness of the adaptive Hermite fuzzy neural network controller and an adaptive reference sliding-mode controller is compared. The experimental results show that the adaptive Hermite fuzzy neural network controller markedly improved the system's lumped uncertainty and external load response.

Optimal H<SUP align="right">∞</SUP> control without reaching phase for a variable speed wind turbine based on fuzzy neural network and APSO algorithm

This paper presents a novel optimal H∞ tracking-based adaptive fuzzy neural network controller (HAFNNC) for a variable speed wind turbine. The main objective of the controller is to optimise the energy captured from the wind. In the presence of large uncertainties, H∞ control approach produces oscillatory phenomenon due to the higher needed gain. In order to reduce this gain, fuzzy neural network (FNN) with online adaptation of the parameters is used to estimate the uncertain parts of the system plant and hence enable a lower gain to be used. To eliminate the trade-offs between the H∞ tracking performance and the high gain at the control input, we have introduced a new method based on the modification of the output tracking error through the use of both the exponential function and the adaptive particle swarm optimisation (APSO) algorithm. The stability and effectiveness of the proposed method are proved by Lyapunov method and the simulations are given to demonstrate the performance of the proposed approach.

Hybrid Adaptive Fuzzy Neural Network Control for Grid-Connected SOFC System

The solid oxide fuel cell (SOFC) is widely acknowledged for clean distributed power generation use, but critical process problems frequently occur when the stand-alone fuel cell is directly linked with the electricity grid. To guarantee the optimal operation of the SOFC in a power system, it is essential, that its generation ramp rate and load following is fast enough to sustain power quality. In order to address these problems, a suitable and highly efficient control system will be required to control and track power load demands for complex SOFC power systems under grid connection. Therefore, novel nonlinear hybrid adaptive Fuzzy Neural Network (AFNN) is developed for control of grid connected SOFC. During peak power demand schedules from electric utility grid and large load perturbations, maintaining optimal power quality and load-following is a big challenge. Both the rapid power load following and safe SOFC operation requirement is taken into account in the design of the closed-loop control system. Simulation results showed that the proposed hybrid AFNN enhance the optimal power quality and load-following than conventional PI controller.

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

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

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

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

The research on hybrid drive and control technique of high-speed motorized spindle based on adaptive fuzzy neural network control

A hybrid drive and control technique is proposed for high-speed motorized spindle system. The proposed control technique enjoys the advantages of vector control and direct torque control and avoids the implementation difficulties of the two control methods. In particular, the control system includes an optimized switching table based on adaptive fuzzy neural network control which can prevent the system from the high level of torque ripple and nonsinusoidal current waveforms. A simulation model of the spindle’s hybrid drive and control system is constructed in MATLAB/Simulink, and then the related experiments are carried out on a high-speed motorized spindle whose rated speed is 15,000 r/min. The simulation and experimental results reveal that the proposed model and technique are correct and the model has excellent dynamic and static performance.

Direct adaptive type-2 fuzzy neural network control for a generic hypersonic flight vehicle

A direct adaptive interval type-2 fuzzy neural network (IT2-FNN) controller is designed for the first time in hypersonic flight control. The generic hypersonic flight vehicle is a multi-input multi-output system whose longitudinal model is high-order, highly nonlinear, tight coupling and most of all includes big uncertainties. Interval type-2 fuzzy sets with Gaussian membership functions are used in antecedent and consequent parts of fuzzy rules. The IT2-FNN directly outputs elevator deflection and throttle setting which make the GHFV track the altitude command signal and meanwhile maintain its velocity. The parameter adaptive law of IT2-FNN is derived using backpropagation method. The deviation of the control signal from the nominal dynamic inversion control signal is used as the reference output signal of IT2-FNN. The tracking errors of velocity and altitude are used as inputs of IT2-FNN. Tracking differentiator is designed to form an arranged transition process (ATP) of the command signal as well as ATP's high-order derivatives. Nonlinear state observer is designed to get the approximations of velocity, altitude as well as their high-order derivatives. Simulation results validate the effectiveness and robustness of the proposed controller especially under big uncertainties.

Research on the Control Strategy of Hybrid Energy Storage for Hybrid Electric Vehicles Based on Grid Partition and Adaptive Fuzzy Neural Network

In order to take the full advantages of battery and ultracapacitor of hybrid energy storage (HES) for hybrid electric vehicles (HEV) and solve the power allocation problems of the two energy storages when the working condition was changing, we propose a grid partition (GP) and adaptive fuzzy neural network (AFNN) control strategy. Firstly, the structure of AFNN wad determined by GP; Secondly, by adopting the back-propagation algorithm and least square method respectively, the front and back parameters of the AFNN were optimized, and the study efficiency of the parameters was raised. Finally, use the fuzzy membership functions and rules which generated automatically by AFNN in the control of HES for HEV. Under the ADVISOR 2002 simulation environment, verify the control strategy on the base of Urban Dynamometer Driving Schedule (UDDS) working condition. The results show that the battery and ultracapacitor could give full play to their respective advantages when the GP and AFNN control strategy was adopted, so the efficiency of the vehicle energy storage system could be enhanced and a higher efficiency of the braking energy recovery be obtained.

Observer-based adaptive FNN controller optimized by NAPSOSA for nonlinear time-delay systems

This study presents an observer-based adaptive fuzzy-neural network controller based on novel adaptive particle swarm optimization simulated annealing (NAPSOSA) for a class of uncertain nonlinear time-delay systems. Firstly, NAPSOSA is used to adjust the weighting function. Then, adaptive laws are adopted to approximate unknown nonlinear functions with unknown uncertainties, respectively. By examining the controller design, the observer-based control law and the weighting update law of the fuzzy-neural-network (FNN) controller are proposed for a class of nonlinear systems. In addition, based on strictly-positive-real (SPR) Lyapunov theory, the stabilization conditions for the closed-loop system are propounded. Furthermore, for obtaining a better performance, an algorithm consists of the adaptive FNN with NAPSOSA is presented to adjust the membership function of the controller. Finally, one simulation example is given to illustrate the effectiveness of the proposed approach.

Adaptive Fuzzy-Neural-Network Design for Voltage Tracking Control of a DC–DC Boost Converter

In this study, an adaptive fuzzy-neural-network control (AFNNC) scheme is designed for the voltage tracking control of a conventional dc–dc boost converter. First, the description of the circuit framework of a conventional boost converter and system modeling is introduced. Then, a total sliding-mode control (TSMC) strategy without the reaching phase in the conventional SMC is developed for enhancing system robustness during the transient response of the voltage control. In order to alleviate the control chattering phenomena caused by the sign function in the TSMC design and relax the requirement of detailed system dynamics, an AFNNC scheme is further investigated to imitate the TSMC law for the boost converter. In the AFNNC scheme, online learning algorithms are derived in the sense of Lyapunov stability theorem and projection algorithm to ensure the stability of the controlled system without the requirement of auxiliary compensated controllers despite the existence of uncertainties. The output of the AFNNC scheme can be easily supplied to the duty cycle of the power switch in the boost converter without strict constraints on control parameters selection in conventional control strategies. In addition, the effectiveness of the proposed AFNNC scheme is verified by realistic experimentations, and its advantages are indicated in comparison with the TSMC strategy.

Novel adaptive fuzzy neural network controller for a class of uncertain non-linear systems

In this paper, an adaptive fuzzy neural network (AFNN) controller with a state observer approach based on novel adaptive particle swarm optimization-simulated annealing (NAPSO-SA) for a class of non-linear systems is proposed. First, NAPSO-SA is used to adjust the parameters of the FNN, while adaptive laws are used to approximate unknown non-linear functions and the unknown upper bounds of uncertainties respectively. Second, a state observer is applied for estimating all states that are not available for measurement in the system. By using the strictly-positive-real (SPR) stability theorem, the proposed controller not only guarantees the stability of a class of non-linear systems but also maintains good tracking performance. The novel intelligence algorithm generates optimal parameters for the control schemes and is developed to guarantee the asymptotically stability of the system. Finally, simulation results substantiate the fact that the proposed method stands out as offering better properties than the observer-based adaptive fuzzy control (OBAFC) for tracking performance.