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 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...

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...

Abstract The failure of rotating machinery can be prevented and eliminated by a regular diagnosis bearings. In deep learning (DL) models bearing fault driven big data, problems, such as data acquisition difficulties, distribution imbalance, high noise, often exist in the samples. This study proposes novel method using joint feature extraction Transformer residual neural network (ResNet) coupled with transfer (TL) strategy to overcome aforementioned issues. First, are transmitted encoder...

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...

This study develops an intelligent global sliding mode control using recurrent feature selection neural network for active power filter (APF). First, the dynamic model of APF is constructed. Second, a conventional (GSMC) introduced to achieve aim track quick changing reference signal current strategy. Since uncertain parameters are unavailable in advance, high performance cannot be assured practical applications. In this article, improve GSMC APF, (RFSNN) proposed learn function. Unlike...

In this article, a self-organizing global sliding mode control (GSMC) is developed for class of dynamic systems, whereby modeling uncertainties are estimated by metacognitive fuzzy-neural-network (MCFNN) framework. First, GSMC designed the tracking reference signals to eliminate reaching and chattering phenomenon. To overcome drawbacks GSMC, law based on MCFNN instead uncertain information. Distinguished from fixed structure schemes, can restructure network parameters extracting useful input...

A continuous fractional order sliding mode controller based on a developed output feedback feature selection neural network (OFFSNN) for an active power filter (APF) is studied in this article to effectively compensate grid harmonic current and improve quality. manifold introduced first. Then, adopted resolve the shortcoming of chattering phenomenon conventional one by designing control law. Furthermore, considering unknown part APF system, new structure called OFFSNN established estimate...

This article considers a robust intelligent control problem for class of power-electronic converters via neuro-fuzzy learning mechanism. First, terminal sliding-mode (TSMC) is designed to ensure finite-time error convergence and further enhance the system performance. Meanwhile, saturation function utilized in proposed TSMC. Then, by using type-2 fuzzy neural network (T2FNN) approximate developed TSMC, corresponding adaptive T2FNN controller with online parameter adjustment established. To...

In view of the fact that most devices are nonlinear systems, this article proposes a recurrent probabilistic compensation fuzzy neural network (RPCFNN) control scheme based on global fast terminal sliding mode (GFTSMC) for class systems with uncertainties. First, GFTSMC is developed to impose finite-time convergence feature considered systems. Second, novel RPCFNN framework designed further enhance ability deal uncertainty. Due added estimation and dynamic operator, controller possesses...

In this paper, an indirect adaptive fuzzy global sliding mode control methods (AFGSMC) are proposed for single-phase shunt active power filter as a current controller. First, applied to the loop is designed guarantee robustness. Then, system used approximate unknown dynamics in order eliminate dependence on prior knowledge, and another replace switching term reduce chattering phenomenon. Moreover, compensation based approximation error estimation, which ensures tracking performance of...

Summary In this article, the fixed‐time attitude tracking problem for rigid spacecraft is investigated based on adding‐a‐power‐integrator control technique. First, a controller designed to guarantee convergence of errors. Then, by considering presence random disturbance and actuator faults, an adaptive fault‐tolerant errors converge residual set zero in fixed time. The complete bounds settling time are derived independently initial conditions. simulation results illustrate highly precise...

In this article, a control system based on evolutionary emotional neural network is proposed for active power filters (APFs) to improve quality. First, the dynamic model of APF containing external disturbances and component parameter perturbations introduced. The global fast terminal sliding mode (GFTSM) method its finite-time convergence robustness are demonstrated. addition, an Hermite orthogonal polynomials as activation function constructed combined with mechanism form self-evolving...

As a promising information theory, reinforcement learning has gained much attention. This paper researches wind-storage cooperative decision-making strategy based on dueling double deep Q-network (D3QN). Firstly, new model is proposed. Besides wind farms, energy storage systems, and external power grids, demand response loads are also considered, including residential price thermostatically controlled (TCLs). Then, novel mechanism proposed, which combines the direct control of TCLs with...

In this paper, a backstepping global sliding mode fuzzy control based on neural network together with proportional integral derivative (PID) manifold is proposed for three-phase active power filter (APF). This system consists of PID controller, uncertainty approximator and estimator. The design process Lyapunov function the controller can be systematic structured through reverse by control. A introduced to obtain overall robustness, speeding up response. On issues conventional surface, item...

In this paper, an adaptive fuzzy-sliding control system is proposed to improve the dynamic performance of a three-phase active power filter (APF). Adaptive fuzzy controllers are employed approximate both equivalent term and switching in sliding mode controller. An online tuning algorithm for consequent parameters rules also designed. The becomes continuous chattering phenomena can be attenuated. Simulation demonstrated that method has excellent such as small current tracking error, reduced...

This study proposed an adaptive Radical Basis Function (RBF) neural control strategy with a complementary sliding mode approach to compensate the harmonic current in Active Power Filter (APF). A backstepping algorithm is incorporated simplify design procedure. Meanwhile, surface employed replace standard eliminate chattering. estimator designed approximate upperbound of lumped nonlinearities APF. simulation and real-time prototype using TMS320F28335 was built demonstrate validity controller.

An adaptive fuzzy control system with supervisory controller is proposed to improve dynamic performance of three‐phase active power filter (APF). The for APF does not build an accurate mathematical model but approximates the nonlinear characteristics using approximation. law based on Lyapunov analysis can adaptively adjust rules; therefore asymptotical stability be guaranteed. Simulation results demonstrate that has excellent such as small current tracking error, reduced total harmonic...

In this paper, an emotional intelligent terminal sliding mode controller is exploited. First, the dynamic model of a second-order nonlinear system considering unknown external disturbances presented. The fast control (FTSMC) scheme proposed in order to impose superior convergence feature. addition, from perspective further improving performance and solving problem prior knowledge dependence FTSMC design, framework with self-construction mechanism develop model-free (EITSMC). Moreover,...