In this paper, a full-regulated neural network (NN) with double hidden layer recurrent (DHLRNN) structure is designed, and an adaptive global sliding-mode controller based on the DHLRNN proposed for class of dynamic systems. Theoretical guidance adjustment mechanism are established to set up base width central vector Gaussian function in structure, where six sets parameters can be adaptively stabilized their best values according different inputs. The new improve accuracy generalization...

In this paper, an adaptive sliding mode control system using a double loop recurrent neural network (DLRNN) structure is proposed for class of nonlinear dynamic systems. A new three-layer RNN to approximate unknown dynamics with two different kinds feedback loops where the firing weights and output signal calculated in last step are stored used as signals each loop. Since has combined advantages internal NN external NN, it can acquire state information while also captured, thus designed...

In this article, an adaptive dynamic terminal sliding-mode controller using a double hidden layer recurrent neural network (DHL-RNN) structure for single-phase active power filter (APF) is proposed to improve harmonic compensation performance. First, method combining sliding mode and solve the chattering phenomenon in traditional control. Then, since nonlinear dynamics of APF difficult obtain accurately, DHL-RNN used approximate controller. Meanwhile, integral robust switching term added...

This article proposes a fractional order nonsingular terminal super-twisting sliding mode control (FONT-STSMC) method for micro gyroscope with unknown uncertainty based on the double-loop fuzzy neural network (DLFNN). First, advantages of are adopted, nonlinear function is used to design hyper plane, then tracking error in system could converge zero specified finite time. Second, can increase differential and integral, which greatly improves flexibility method. The fractional-order...

In this article, a fractional-order sliding-mode control scheme based on two-hidden-layer recurrent neural network (THLRNN) is proposed for single-phase shunt active power filter. Considering the shortcomings of traditional networks (NNs) that approximation accuracy not high and weight center vector NNs are unchangeable, new THLRNN structure which contains two hidden layers to make have more powerful fitting ability, designed approximate unknown nonlinearities. A term added controller...

This study designs a fuzzy double hidden layer recurrent neural network (FDHLRNN) controller for class of nonlinear systems using terminal sliding-mode control (TSMC). The proposed FDHLRNN is fully regulated network, which can be simply considered as combination (FNN) and radial basis function (RBF NN) to improve the accuracy approximation, so it has advantages these two networks. main advantage new that output values FNN DHLRNN are at same time, outer feedback added increase dynamic...

In this article, an approximation-based adaptive fractional sliding-mode control (SMC) scheme is proposed for a microgyroscope, where double-loop recurrent fuzzy neural network (DLRFNN) employed to approximate system uncertainties and disturbance. A fractional-order term incorporated into the sliding surface that could add extra degree of freedom combine advantages calculus SMC. new four-layer (FNN) studied, which has two feedback loops (internal loop external loop) capture weights output...

A real-time nonlinear model predictive control using a self-feedback recurrent fuzzy neural network (SFRFNN) estimator for an active power filter is developed to improve the performance of harmonic compensation. First, SFRFNN with structure and rules proposed as prediction systems. The merges advantages system structure, which can significantly dynamic performance. Second, optimization method based on gradient descent employed solve optimal problem. In addition, convergence stability RT-NMPC...

In this article, a fractional-order sliding mode control (FOSMC) scheme is proposed for mitigating harmonic distortions in the power system, whereby self-constructing recurrent fuzzy neural network (SCRFNN) used to weaken effect of compound nonlinearity caused by unknown uncertainties and environmental fluctuations. The controller (SMC) constructed maintain system be asymptotically stable calculus introduced into an SMC soften manifold design realize chattering reduction. Considering...

In this paper, a robust adaptive control strategy using fuzzy compensator for MEMS triaxial gyroscope, which has system nonlinearities, including model uncertainties and external disturbances, is proposed. A logic controller that could compensate the disturbances incorporated into scheme in Lyapunov framework. The proposed can guarantee convergence asymptotical stability of closed-loop system. does not depend on accurate mathematical models, simplifies design procedure. innovative...

In this paper, an adaptive fuzzy-neural-network (AFNN) control using nonsingular terminal sliding mode is proposed for active power filter (APF) as a current controller to attenuate the effect of unknown external disturbances and modeling uncertainties. First, dynamic model APF built in which both system parameter variations disturbance are considered. Then, based on backstepping (NTSMB) approach presented solve singularity point problem realize fast finite-time convergence. Moreover, AFNN...

In this brief, a fractional-order sliding mode control (FSMC) scheme using recurrent neural network (RNN) approximator is introduced to achieve better performance for shunt active power filter (APF). The proposed RNNFSMC combines method with structure. has more adjustable degree of freedom brings superior effect than integer order control. RNN estimator employed approximate the unknown nonlinear function APF. Experimental results are presented show effectiveness strategy, demonstrating...

In this paper, a self-regulated double hidden layer output feedback neural network (DHLFNN) is presented to control an active power filter (APF) system as current controller, which conducive the improvement of response characteristic and quality. First, global sliding mode controller introduced because it effective in achieving overall robustness during response. A new structure that has two layers proposed make parameters adaptively adjust themselves stabilize their best values. higher...

In this paper, a disturbance observer-based fuzzy sliding mode control (DOBFSMC) strategy is proposed for single-phase PV grid-connected inverter. the fact that uncertainties caused by inverter component parameter variations and changes of climatic conditions may seriously affect performance inverter, observer designed to estimate these disturbances in real time controller with output information employed voltage DC-AC system used approximate upper bound observation error between actual its...

This article focuses on the design of a terminal sliding mode control (TSMC) using fuzzy double hidden layer recurrent neural network (FDHLRNN) strategy for single-phase active power filter (APF). A TSMC is proposed to make tracking error system converge zero in finite time. An FDHLRNN and applied harmonic suppression approximate equivalent eliminate unknown disturbance, reducing role symbol switching items. The main function improve accuracy reduce current distortion rate APF. designed...

This article proposes an adaptive type-2 fuzzy neural network control system to enhance the performance of power quality improvement. First, dynamic model APF with lumped uncertainties caused by parameter perturbation ac inductor and dc capacitor is briefly introduced. Then, integral-type terminal sliding mode (TSMC) developed for finite-time reference signal tracking. Meanwhile, in terms considered chattering problem, saturation function utilized proposed TSMC. Moreover, (T2RFSFNN) derived...

To maintain the vibrations of gyroscope proof mass, a trajectory tracking control system using neural network estimator is proposed. The proposed incorporates fractional controller based on terminal sliding-mode and recurrent Chebyshev fuzzy self-evolving mechanism. fractional-order can guarantee error exponential stable, (SERCFNN) introduced to relax requirement nonlinear functional certainty. In addition, SERCFNN develops advantages (SEFNN), (RFNN), function (CFN). SEFNN adaptively update...

A self-evolving recurrent Chebyshev fuzzy neural network (SERCFNN) approximator based on a fractional order sliding mode controller (FOSMC) is developed for an active power filter to suppress harmonic distortions. The algorithm, which incorporates the structure learning with parameter learning, able dynamically adjust number of rules and shape partitions. consequent part proposed SERCFNN combines polynomials expand dimensionality input. For relaxing requirement parametric functional...

To improve the tracking performance of current controller active power filter (APF) system, an adaptive super-twisting (ASTW) acrlong SMC using a nonlinear extended state observer (NESO) based on interval type-2 fuzzy neural network (IT2FNN) strategy (ASTW- NESO) is proposed in this article. NESO IT2FNN designed to estimate system states and total disturbance, then realize compensation disturbance including unmodeled dynamics external disturbances. Then, ASTW adopts special segmented dynamic...

In this article, a complementary sliding mode (CSM) controller using self-constructing Chebyshev fuzzy recurrent neural network (SCCFRNN) is proposed for harmonic suppression control of an active power filter (APF). The SCCFRNN whose structure can be automatically learned through the designed self-learning algorithm introduced to approximate unknown nonlinear term in APF dynamic model, so as improve modeling accuracy and reduce burden CSM (CSMC). combines advantages (FNN), (RNN), (CNN), all...

An adaptive dynamic special global sliding mode controller that is based on proportional integral derivative (PID) surface using radial basis function (RBF) neural network (NN) for a three- phase active power filter (APF) was presented in this paper. To overcome the problems associated with schemes of conventional control, PID manifold introduced to realize whole process robustness and inhibition steady state error, accelerating system response meanwhile. In addition, nested can reduce...

An adaptive backstepping fuzzy sliding mode control is proposed to approximate the unknown system dynamics for a cantilever beam in this paper. The developed by combining method with strategy, where design approach used drive trajectory tracking errors converge zero rapidly global asymptotic stability and logic designed nonlinear function control. controllers can ensure proper of reference trajectory, impose desired dynamic behavior, giving robustness insensitivity parameter variations....