This paper deals with adaptive tracking for discrete-time multiple-input-multiple-output (MIMO) nonlinear systems in presence of bounded disturbances. In this paper, a high-order neural network (HONN) structure is used to approximate control law designed by the backstepping technique, applied block strict feedback form (BSFF). also includes respective stability analysis, on basis Lyapunov approach, whole controlled system, including extended Kalman filter (EKF)-based NN learning algorithm....

This paper presents the results of use training algorithms for recurrent neural networks based on extended Kalman filter and its in electric energy price prediction, both cases: one-step ahead n-step ahead. In addition, it is included stability proof using well-known Lyapunov methodology, proposed artificial network trained with an algorithm filter. Finally, applicability prediction scheme shown by mean data from European power system.

This paper deals with real-time adaptive tracking for discrete-time induction motors in the presence of bounded disturbances. A high-order neural-network structure is used to identify plant model, and based on this a control law derived, which combines block-control sliding-mode techniques. also includes respective stability analysis whole system strategy avoid weight zero-crossing. The scheme implemented real time using three-phase motor.

The solution of the inverse kinematics mobile manipulators is a fundamental capability to solve problems such as path planning, visual-guided motion, object grasping, and so on. In this article, we present metaheuristic approach kinematic problem manipulators. approach, represent robot using Denavit–Hartenberg model. algorithm able taking into account platform. proposed avoid singularities configurations, since it does not require inversion Jacobian matrix. Those are two main drawbacks...

This paper presents a nonlinear control of quadrotor unmanned aerial vehicle(UAV) for trajectory tracking. The dynamical model is obtained by the Euler- Lagrange methodology. In this paper, proposed strategy based on integral backstepping technique with sliding mode (SMC) altitude and lateral motion. addition, an inner loop used to stabilize vehicle orientation. implementation applied Qball-X4 prototype Quanser Inc. which has OptiTrackTM cameras provide position sonar sensor gives...

Influenza A virus infections are causes of severe illness resulting in high levels mortality. Neuraminidase inhibitors such as zanamivir and oseltamivir used to treat influenza; however, treatment recommendations remain debatable. In this paper, a discrete-time inverse optimal impulsive control scheme based on passivation is proposed address the antiviral scheduling problem. We adapt results regarding stability, passivity, optimality for action. The study founded mathematical models whose...

This brief focuses on real-time implementation, as applied to a three-phase induction motor, of results already published in 2007. The proposed controller is based high-order neural network, trained online using Kalman filter learning, approximate control law designed by the backstepping technique.

In this paper, a consensus-based formation control strategy is presented, subject to area constraints and collision avoidance. To achieve desired pattern, law proposed that incorporates vertex-tension function along with signed constraints. The provides the capabilities of avoidance among agents. Moreover, avoid local minimum stagnation mitigate ambiguities within shape. Additionally, approach can be implemented considering group differential-drive mobile robots in both centralized...

This work introduces a novel and practical metaheuristic algorithm, the Gaslike Social Motility (GSM) designed for optimization image thresholding segmentation. Inspired by deterministic model that replicates social behaviors using gaslike particles, GSM is characterized its simplicity, minimal parameter requirements, emergent dynamics. These dynamics include: (1) attraction between similar (2) formation of stable particle clusters, (3) division groups upon reaching critical size, (4)...

A nonlinear discrete-time neural observer for unknown systems in presence of external disturbances and parameter uncertainties is presented. It based on a recurrent high-order network trained with an extended Kalman-filter algorithm. This brief includes the stability proof Lyapunov approach. The applicability proposed scheme illustrated by real-time implementation three phase induction motor.

In this paper, an adaptive single neuron Proportional–Integral–Derivative (PID) controller based on the extended Kalman filter (EKF) training algorithm is proposed. The use of EKF allows online with faster learning and convergence speeds than backpropagation method. Moreover, propose PID approach includes a back-calculation anti-windup scheme to deal windup effects, which common problem in controllers. performance proposed shown by presenting both simulation experimental tests, giving...

In recent years, unmanned aerial vehicles (UAVs) have gained significant attention. However, we face two major drawbacks when working with UAVs: high nonlinearities and unknown position in 3D space since it is not provided on-board sensors that can measure its respect to a global coordinate system. this paper, present real-time implementation of servo control, integrating vision sensors, neural proportional integral derivative (PID), order develop an hexarotor image based visual control...

In this paper, a Higher Order Wavelet Neural Network (HOWNN) trained with an Extended Kalman Filter (EKF) is implemented to solve the wind forecasting problem. The based scheme composed of high order terms in input layer, two hidden layers, one incorporating radial wavelets as activation functions and other using classical logistic sigmoid, output layer linear function. A filter algorithm employed update synaptic weights wavelet network. size regression vector determined by means Lipschitz...

An approach to plan smooth paths for mobile robots using a Radial Basis Function (RBF) neural network trained with Particle Swarm Optimization (PSO) was presented in [1]. Taking the previous as an starting point, this paper it is shown that possible construct simple global path and then modify locally PSO-RBF, Ferguson splines or Bézier curves PSO, order describe more complex partially known environments. Experimental results show our fast effective deal

This paper discusses a novel training algorithm for neural network architecture applied to time series prediction with smart grids applications. The proposed is based on an extended Kalman filter (EKF) improved using particle swarm optimization (PSO) compute the design parameters. EKF-PSO-based employed update synaptic weights of network. size regression vector determined by means Cao methodology. structure captures more efficiently complex nature wind speed, energy generation, and...