Due to the highly nonlinear dynamics and complex behaviors in microgrids, classical controllers often cannot guarantee optimal and stable performance under all possible operating conditions and scenarios. For this reason, the use of adaptive and intelligent algorithms, especially reinforcement learning (RL)-based methods, seems essential. These algorithms have the ability to learn online and adapt to changing conditions and can effectively perform diverse and critical tasks. In this paper, the aim is to investigate the capability of the reinforcement learning-based controller in dealing with load changes, fluctuations of renewable resources, and transient disturbances, and to demonstrate its superiority over traditional control methods. The performance evaluation of the proposed controller was performed using MATLAB software, and the dynamic behavior of the microgrid was compared with two classical buck controllers and a PI controller. Also, key stability indicators, including settling time, overshoot percentage, residual error, effective value, active and reactive powers, battery flux status, and voltage and frequency variations, were analyzed.

In this paper, the problem of the motion coordination control of a moving ground robot and a quadrotor unmanned aerial vehicle with limited field-of-view (FOV) and limited communication range is addressed. By using the prescribed performance technique, a new controller is proposed to maintain a quadrotor over the moving ground robot such that the robot continuously lies inside the camera FOV, the communication link between both vehicles is preserved and no collision occurs between them. Undesirable deviations between both vehicles are effectively avoided during the turning of the ground robot by compensating for the path curvature. By employing the command-filtered backstepping control method, the first and second-order derivative terms of reference command signals are reconstructed. By an efficient combination of a radial basis function neural network (RBFNN) and an adaptive robust controller, model uncertainties, wind disturbances and neural network approximation errors are well compensated. To evaluate the performance of the proposed controller, computer simulations have been done in MATLAB software and according to the obtained results, it will be shown that the tracking errors between the quadrotor and moving robot at a certain distance have been converged to zero within a small time while a circular trajectory has been tracked despite the applied wind disturbances.

This article addresses the output-feedback reinforcement learning (RL)-based saturated proportional-integral-derivative (PID) control design for fully actuated Euler-Lagrange (EL) systems which are uncertain subject to actuator saturation with prescribed performance. It is assumed that the actuator input nonlinearity, uncertain nonlinearities and unmeasurable external disturbances have a significant impact on the system. The presence of actuator saturation and complex uncertainties may inevitably give rise to the breakdown of the EL control system. The lack of prior knowledge of the system dynamics renders the presented technique to achieve a robust prescribed tracking performance without using velocity sensors. To conquer mentioned obstacles, a novel RL saturated PID controller, which is not dependent on the system's dynamics and only requires measurable output signals is designed via actor-critic structure to deeply estimate and compensate complex unknowns. An adaptive robust controller is used to reduce external disturbances effects adaptively. The prescribed performance funnel control way is considered to guarantee predetermined output constraints. The high-gain observer (HGO) is used to estimate velocities and derivatives free of system dynamics, and generalized saturation functions are utilized to efficiently decrease actuator saturation danger. It is proved that suggested technique ensures a robust prescribed performance with input constraints in the absence of velocity sensors and the existence of considerable complicated model uncertainties. A semi-global uniform ultimate boundedness (SGUUB) stability for tracking deviation errors and state estimation deviation is ensured through a Lyapunov stability study. Finally, experimental results on a real robotic arm is carried out to further demonstrate the effectiveness of all theoretical findings.

In this paper, a high-performance intelligent tracking controller is proposed for underactuated autonomous underwater vehicles whose relative range and angle sensors are subjected to a limited sensing range and a limited field-of-view. An effective combination of feedback linearization design, multi-layer neural networks, fixed-time strategy, adaptive robust control and prescribed performance technique is simultaneously used to obtain (i) a fast fixed-time error convergence, (ii) prescribed transient and steady-state performance, (iii) the compensation of unknown parameters, unmodeled dynamics and environmental disturbances, and (iv) target tracking with limited sensing range. Relative distance and relative azimuth and elevation angles are employed as the output variables to obtain the input-output dynamic model of the system based on a nonlinear transformation. Then, an efficient fixed-time prescribed performance controller is proposed to force the main vehicle track a target vehicle with limited field-of-view sensors. The stability of the proposed controller will be guaranteed by using Lyapunov stability analysis, and simulation results will show the effectiveness of the controller.

This paper proposes a fixed-time multilayer neural network-based formation control problem for the autonomous surface vessels based on the relative distance and orientation angle constraints. The proposed approach only expends the measurements of comparative distance and orientation angle sensors with a limited field-of-view (FOV). The proposed strategy is able to obtain the perfect trajectory tracking performance when the motion ability of all the vessels is restricted into a predefined region owing to the limited FOV limitations. An asymmetric time-varying barrier Lyapunov function is efficiently utilized to cope with the limited FOV constraints. A multilayer neural network is efficiently applied to estimate the model uncertainties and unmodeled dynamics through the online updating of weight matrices. The suggested controller preserves both the comparative distance and orientation angles between consecutive vessels inside the predefined constraints, and the state errors converge to small residual sets around the zero in a fixed time. This feature accelerates the convergence speed and modifies the transient performance of the trajectory tracking control for all the vessels in the formation construction.

In this paper, an adaptive-neural constrained controller is proposed for a group of Tractor-trailer wheeled mobile robots with limited field-of-view (FOV) constraints and saturating actuators. With an effective combination of the asymmetric Barrier Lyapunov function based control design and dynamic surface control in the proposed constrained controller, the limited FOV constraints are not transgressed the predefined and limited bounds. The risk of the actuators saturation is extremely decreased through restricting amplitudes of the output states errors. It is proved that all the output states in the closed-loop system are semi-globally uniformly ultimately bounded and the relative distance and orientation angles errors are converged in the limited and preassigned boundaries. Compared with the existing results, the proposed constrained controller not only assures that these states errors between consecutive TTWMRs are bounded, but also all the output states errors converge to a small region around zero in a fixed-time that this issue accelerates the convergence speed rate and improves the transient response performance of the perfect tracking control for all TTWMRs. (c) 2023 European Control Association. Published by Elsevier Ltd. All rights reserved.

This paper addresses a new constrained control design problem to develop the trajectory-tracking specifications of the cooperative control of Euler–Lagrange systems with respect to the convergence rate and steady-state errors by constraining the limited bounds on the trajectory-tracking errors in the leader–follower formation control problem. A control design based on an asymmetric barrier Lyapunov function is proposed for the leader–follower formation control of Euler–Lagrange systems in the presence of unknown parameters and unmodeled dynamics that progresses to the infinity when its arguments attain to the predefined bounds. These constrained output states are considered in the leader–follower formation control problem to cope with the system restrictions such as limited sensing ranges. The Lyapunov stability is pursued to assure that all the signals of the closed-loop system are bounded and the leader–follower formation errors are finite-time semi-globally uniformly ultimately bounded. Finally, computer simulation results represent the impression of the newly proposed constrained leader–follower formation control for the Euler–Lagrange systems.

A new controller design is presented on the basis of the dynamic surface control (DSC) method for the constrained platoon formation control of the underactuated autonomous underwater vehicles (AUVs) in the presence of model uncertainties with limited field-of-view (FOV) constraints. An asymmetric barrier Lyapunov function (BLF) is applied to prevent both the line-of-sight (LOS) range and orientation angles from violating limited FOV constraints. Lyapunov method is adopted to reveal that all signals of the closed-loop control system are bounded and the constrained platoon formation tracking errors are semi-globally uniformly ultimately bounded (SGUUB). An adaptive neural network technique is employed to compensate uncertain parameters and unmodeled dynamics of the vehicles. Compared with existing works in the literature, the proposed control scheme not only forces both the range and orientation angles between AUVs to their desired values in the presence of FOV constraints in the fixed-time, but also decrease the safety hazard by avoiding any possible collision between the vehicles, increase the tracking error convergence rate and improve the transient performance of the tracking controller for all AUVs. The computer simulation results demonstrate the efficiency of this newly proposed constrained platoon formation controller for the AUVs.

This paper proposes a tracking controller for the formation construction of multiple autonomous surface vessels (ASVs) in the presence of model uncertainties and external disturbances with output constraints. To design a formation control system, the leader-following strategy is adopted for each ASV. A symmetric barrier Lyapunov function (BLF), which advances to infinity when its arguments reach a finite limit, is applied to prevent the state variables from violating constraints. An adaptive-neural technique is employed to compensate uncertain parameters and unmodeled dynamics. To overcome the explosion of differentiation term problem, a first-order filter is proposed to realize the derivative of virtual variables in the dynamic surface control (DSC). To estimate the leader velocity in finite time, a high-gain observer is effectively employed. This approach is adopted to reveal all signals of the closed-loop system which are bounded, and the formation tracking errors are semi-globally finite-time uniformly bounded. The computer simulation results demonstrate the efficacy of this newly proposed formation controller for the autonomous surface vessels.

Surge and constant pressure are some of the most critical issues in compressor control. In this paper, the problem of the surge and constant pressure in the presence of environmental disturbances is solved. Proposed design for control system based on proportional–integral controllers, adaptive neuro‐fuzzy inference system (FIS), and particle swarm optimized neural fuzzy and for modeling neural network strategy fuzzy nonlinear automatic regression with external input is used. Based on this, for modeling, practical and real data are extracted from the K‐250 compressor of Isfahan Steel Company. In the adaptive neuro‐fuzzy inference system–particle swarm optimization (ANFIS‐PSO) controller, the control algorithm is made of the third FIS structure based on the fuzzy center clustering method and trained based optimization on the particle swarm optimization (PSO) algorithm, which has three layers, two inputs, and a single output. The proposed control algorithm has finally been able to bring the compressor to the desired pressure, and when the compressor enters the surge area, the controller has been able to remove the compressor from this area without damaging the compressor. Finally, the proposed control system's capability and effectiveness are shown through simulation in MATLAB software and practical implementation.

This article proposes a novel prescribed performance-based neural adaptive control scheme for robot manipulators including motor dynamics under model uncertainties without velocity, acceleration, and input current measurements. The prescribed performance function approach is used to transform a constrained tracking problem of the robot model including motor dynamics into an unconstrained third-order error model in Euler-Lagrange form which inherits all properties of the robot dynamics. Then, a projection-type neural adaptive PID2 controller (a PID controller with the second-order derivative) in conjunction with a velocity-acceleration observer is proposed. Lyapunov's direct method is used to prove that the tracking and state observation errors are semiglobally uniformly ultimately bounded and converge to a small ball around the origin with a prescribed overshoot/undershoot, convergence rate, and final tracking accuracy. Finally, simulation, experimental results on a SCARA robot and comparative studies verify that the proposed controller is effective for the joint position trajectory tracking of robot manipulators in the industrial automation with minimum measurement and hardware requirements.

The estimation accuracy of the inertial navigation system integrated with the global positioning system (GPS) through multiple kinds of Kalman filters (KFs) has been widely considered. Since the classical KFs could not overcome environmental disturbances and noises, adaptive and robust structures are utilised in sensor fusion techniques. Here, different types of adaptive structures have been assumed. The fuzzy inference system benefits the adaption of the measurement covariance matrix, a scale factor employed to tune the process covariance matrix and the Chi-square algorithm to detect and bound the disturbances. The estimation accuracy and robustness of the adaptive fuzzy extended Kalman filter (AFEKF) are compared with the unscented Kalman filter (UKF) and extended Kalman filter (EKF) structure in various scenarios involving position, velocity, attitude, accelerometer and gyroscope bias estimation errors. Likewise, in order to evaluate the AFEKF approach practically, an embedded electronic board is designed involving an ARM microcontroller, an inertial measurement unit sensor, and a GPS receiver, which was installed on a land vehicle. The results demonstrated the superiority of the AFEKF over the UKF and EKF in the case of lower estimation error and higher robustness against disturbances and outliers.

This paper studies the three-dimensional platoon control of multiple underactuated autonomous underwater vehicles (AUVs) subjected to environmental disturbances and model uncertainties. The main control objective is to design a tracking controller to force a platoon of AUVs to construct a convoy-like formation along feasible trajectories while each consecutive pair preserves a desired line-of-sight distance with limited communication range and every possible collision is avoided between consecutive vehicles. To achieve this objective, the prescribed performance function (PPF) methodology is employed to constrain the relative distance and angles between successive pairs during their motion. A robust neural network (NN), hyperbolic tangent function, and dynamic surface control technique are simultaneously utilized to propose the prescribed performance-based controller which is robust against completely unknown parameters, nonlinear hydrodynamic damping, actuators saturation nonlinearity, NN approximation errors and time-varying environmental disturbances. Lyapunov?s direct method is used to prove that all signals of the closed-loop control system are bounded and the relative distance and angles converge to a neighbourhood of the origin. Finally, numerical computer simulations verify the proposed controller performance for offshore applications.

The distillation process is important process in the chemical industry and has wide application in industry. Distillation tower is used by chemical engineers as a popular tool to separate materials and is the most common method for separating materials. Keeping constant the product composition in the distillation column is very important from control perspective. Control of these complicated processes need intelligent methods to adopt the appropriate decision for control based on the behavior of the system. Between intelligent methods, fuzzy technique has superior response in complex systems control and so is used in this study. In this article at first, a type-1fuzzy controller is designed for linear model of distillation tower. In design of this Fuzzy controller, genetic algorithm (GA) is used for optimization of fuzzy rules base. It has been shown that the fuzzy controller is better than conventional PI one. Then the type-1 fuzzy controller has been replaced with type-2 fuzzy controller and has been shown that the performance of type-2 is better than type-1 in various points of view. In this study, the MATLAB/SIMULINK software has been used for modeling and implementing the proposed methods.

In this research a saturated PID controller with a fuzzy gain tuner is developed as a nonlinear control strategy, experimentally, for the precise trajectory tracking of industrial SCARA IBM 7547 robot. Designing, construction and implementation of electrical and controlling parts of this robot have been performed by the author team. Saturated PID controller gains are tuned online with the use of Fuzzy rules based on error signals and its changes. One of the advantages of the proposed controller is that it isn't based on the model parameters as well as employing a generalized saturation function in the control law formulation, which results in avoiding of actuator's saturation. Consequently, better transient and steady state responses are obtained. Experimental results demonstrate the efficiency of the proposed control system.

ABSTRACT: In this study, an observer-based tracking controller is proposed and evaluated experimentally to solve the trajectory tracking problem of robotic manipulators with the torque saturation in the presence of model uncertainties and external disturbances. In comparison with the state-of-the-art observer-based controllers in the literature, this paper introduces a saturated observer-based controller based on a radial basis function neural network. This technique helps the controller produce feasible control signals for the robot actuators. As a result, it efficiently diminishes the actuators saturation risk and consequently, a better transient performance is obtained. The stability analyses of the dynamics of the tracking errors and state estimation errors are given with the help of a Lyapunov-based stability analysis method. The theoretical analyses will systematically prove that the errors are semi-globally uniformly ultimately bounded and they converge to a small set around the origin whose size is adjustable by a suitable tuning of parameters. At last, some real experiments are performed on a laboratory robotic arm to illustrate the efficiency of the proposed control system for real industrial applications. Review History:

In this paper, an extension of the passivity-based output feedback trajectory tracking controller is addressed and implemented on a SCARA robot IBM 7547 by using generalized saturation. Compared with the output feedback controllers, a radial basis function saturated observer-based controller has been introduced. The controller will reduce the risk of actuator saturation effectively via generalized saturation functions. Implementation results are provided to illustrate the efficiency of the proposed controller in dealing with the actuator saturation.

Robust tracking control is of great importance for the surface vessels applications. This paper addresses the design of a trajectory tracking controller for fast underactuated ships in the presence of model uncertainties without velocity measurements in the yaw and surge directions. An observer-based trajectory tracking controller is proposed for the fast underactuated ship model. Then, the dynamic surface control approach is effectively exploited to propose a tracking controller considering the actuator dynamics. An adaptive robust controller is also used to compensate both the parametric and non-parametric uncertainties in the fast underactuated ship model. A Lyapunov-based stability analysis is utilised to guarantee that tracking and state estimation errors are uniformly ultimately bounded. Simulation results are presented to illustrate the feasibility and efficiency of the proposed controller.

This paper addresses the output feedback trajectory tracking control problem of Ackerman steering-drive wheeled mobile robots under nonholonomic constraints in the presence of model uncertainties without velocity measurement. A RBF neural network and a linear observer are employed to construct the controller for constrained robot with only position measurement. The proposed controllers employ saturation-type adaptive-neural control laws to effectively compensate for the uncertain parameters, unmodeled dynamics and unknown bounded disturbances. Lyapunov-based stability analyses are utilized to guarantee that tracking errors are uniformly ultimately bounded and exponentially converge to a small ball containing the origin. The simulation results are presented to illustrate the tracking effectiveness of the controller.