Trajectory tracking double two-loop adaptive neural network control for a Quadrotor

In this paper, the development and experimental validation of a novel double two-loop nonlinear controller based on adaptive neural networks for a quadrotor are presented. The proposed controller has a two-loop structure: an outer loop for position control and an inner loop for attitude control. Similarly, both position and orientation controllers also have a two-loop design with an adaptive neural network in each inner loop. The output weight matrices of the neural networks are updated online through adaptation laws obtained from a rigorous error convergence analysis. Thus, a training stage is unnecessary prior to the neural network implementation. Additionally, an integral action is included in the controller to cope with constant disturbances. The error convergence analysis guarantees the achievement of the trajectory tracking task and the boundedness of the output weight matrix estimation errors. The proposed scheme is designed such that an accurate knowledge of the quadrotor parameters is not needed. A comparison against the proposed controller and two other well-known schemes is presented. The obtained results showed the functionality of the proposed controller and demonstrated robustness to parametric uncertainty.     

Robust integral backstepping control for sensorless IPM synchronous motor controller

In this paper, a sensorless speed control for interior permanent magnet synchronous motors (IPMSM) is designed by combining a robust backstepping controller with integral actions and an adaptive interconnected observer. The IPMSM control design generally requires rotor position measurement. Then, to eliminate this sensor, an adaptive interconnected observer is designed to estimate the rotor position and the speed. Moreover, a robust nonlinear control based on the backstepping algorithm is designed where an integral action is introduced in order to improve the robust properties of the controller. The stability of the closed-loop system with the observer–controller scheme is analyzed and sufficient conditions are given to prove the practical stability. Simulation results are shown to illustrate the performance of the proposed scheme under parametric uncertainties and low speed. Furthermore, the proposed integral backstepping control is compared with the classical backstepping controller.     

Master–slave chaos synchronization using adaptive TSK-type CMAC neural control

In this paper, an adaptive TSK-type CMAC neural control (ATCNC) system via sliding-mode approach is proposed for the chaotic symmetric gyro. The proposed ATCNC system is composed of a neural controller and a supervisory compensator. The neural controller uses a TSK-type CMAC neural network (TCNN) to approximate an ideal controller and the supervisory compensator is designed to guarantee system stable in the Lyapunov stability theorem. The developed TCNN provides more powerful representation than the traditional CMAC neural network. Moreover, all the control parameters of the proposed ATCNC system are evolved in the Lyapunov sense to ensure the system stability with a proportional–integral (PI) type adaptation tuning mechanism. Some simulations are presented to confirm the validity of the proposed ATCNC scheme without the occurrence of chattering phenomena. Further, the proposed PI type adaptation laws can achieve faster convergence of the tracking error than that using integral type adaptation laws in previous published papers.     

Semi-globally/globally stable adaptive NN backstepping control for uncertain MIMO systems with tracking accuracy known a priori

This paper focuses on the problem of direct adaptive neural network (NN) tracking control for a class of uncertain nonlinear multi-input/multi-output (MIMO) systems by employing backstepping technique. Compared with the existing results, the outstanding features of the two proposed control schemes are presented as follows. Firstly, a semi-globally stable adaptive neural control scheme is developed to guarantee that the ultimate tracking errors satisfy the accuracy given a priori, which cannot be carried out by using all existing adaptive NN control schemes. Secondly, we propose a novel adaptive neural control approach such that the closed-loop system is globally stable, and in the meantime the ultimate tracking errors also achieve the tracking accuracy known a priori, which is different from all existing adaptive NN backstepping control methods where the closed-loop systems can just be ensured to be semi-globally stable and the ultimate tracking accuracy cannot be determined a priori by the designers before the controllers are implemented. Thirdly, the main technical novelty is to construct three new nth-order continuously differentiable switching functions such that multiswitching-based adaptive neural backstepping controllers are designed successfully. Fourthly, in contrast to the classic adaptive NN control schemes, this paper adopts Barbalat׳s lemma to analyze the convergence of tracking errors rather than Lyapunov stability theory. Consequently, the accuracy of ultimate tracking errors can be determined and adjusted accurately a priori according to the real-world requirements, and all signals in the closed-loop systems are also ensured to be uniformly ultimately bounded. Finally, a simulation example is provided to illustrate the effectiveness and merits of the two proposed adaptive NN control schemes.     

Control of connected vehicles with event-triggered transmission and prescribed energy budget

This paper is concerned with event-triggered cooperative control of a platoon of connected vehicles via vehicular ad hoc networks (VANETs). To reduce communications among vehicles, we introduce a hybrid event-triggered transmission mechanism based on both time elapsed and state error. The effect of time-varying transmission delay and communication energy constraint can be also taken into account in the system modeling and design procedures. The on-board sensors use different power levels to transmit information resulting in different packet loss rates. The vehicular platoon system is proved to be exponentially mean-square stable under the hybrid event-triggering scheme and a constant time headway spacing policy. A framework for co-design of the hybrid event triggering scheme and the output feedback controller is given to guarantee platoon stability and spacing-error convergence along the stream. Numerical simulations are given to demonstrate the effectiveness of proposed method.     

Robust sensor fault estimation scheme for satellite attitude control systems

The present paper proposes two new schemes of sensor fault estimation for a class of nonlinear systems and investigates their performances by applying these to satellite control systems. Both of the schemes essentially transform the original system into two subsystems (subsystems 1 and 2), where subsystem-1 includes the effects of system uncertainties, but is free from sensor faults and subsystem-2 has sensor faults but without any uncertainties. Sensor faults in subsystem-2 are treated as actuator faults by using integral observer based approach. The effects of system uncertainties in subsystem-1 can be completely eliminated by a sliding mode observer (SMO). In the first scheme, the sensor faults present in subsystem-2 are estimated with arbitrary accuracy using a SMO. In the second scheme, the sensor faults are estimated by designing an adaptive observer (AO). The sufficient condition of stability of the proposed schemes has been derived and expressed as a linear matrix inequality (LMI) optimization problem and the design parameters of the observers are determined by using LMI techniques. The effectiveness of the schemes in estimating sensor faults is illustrated by considering an example of a satellite control system. The results of the simulation demonstrate that the proposed schemes can successfully estimate sensor faults even in the presence of system uncertainties.     

A novel structure for the optimal control of bilateral teleoperation systems with variable time delay

The purpose of designing a controller for a teleoperation system is achieving stability and optimal operation in the presence of factors such as time delay, system disturbance and modeling errors. In this article three new schemes for teleoperation systems are suggested using an optimal control to reduce the error of tracking between the master and slave systems. In the first scheme optimal controller has been designed in both the master and slave subsystems and by a suitable combination of the output signals of both controllers and exerting it to the slave, it has tried to create the best performance with regard to tracking. In the second scheme, as in the first one, optimal controller is applied to both the master and slave systems and the output of each controller is then applied to its own system, and by changing the system parameters and weighting factors, it has tried to reduce the tracking error between the master and the slave subsystems. In the third structure optimal control is applied to the master. In all three structures the positions of master-slave are compared together and controlling signals are applied to the master or slave so that they can track each other in the least possible time. In all schemes the effectiveness of the system is shown through the simulations and they are compared with each other.     

A hybrid partial feedback linearization and deadbeat control scheme for a nonlinear gantry crane

This paper presents the design of a hybrid partial feedback linearization and deadbeat control scheme for a nonlinear gantry crane with friction to control its position and sway angle. The partial feedback linearization is used to linearize the nonlinear model and to stabilize its internal dynamics. In many crane applications, it's necessary to accelerate the system response. As a result, this will cause oscillation in the position as well as the sway angle. So, the deadbeat controller is added to get the desirable accelerated response without any oscillation or adverse effects on the internal dynamics stability. By using Lyapunov stability method, the proposed scheme is proved to be globally stable, with converging tracking errors to the desired performance. The simulation results are accomplished to evaluate the effectiveness of the proposed scheme and to demonstrate its reliability to control crane systems with comparative results.     

Adaptive fault-tolerant attitude control for hypersonic reentry vehicle subject to complex uncertainties

In this paper, a novel fast attitude adaptive fault-tolerant control (FTC) scheme based on adaptive neural network and command filter is presented for the hypersonic reentry vehicles (HRV) with complex uncertainties which contain parameter uncertainties, un-modeled dynamics, actuator faults, and external disturbances. To improve the performance of closed-loop FTC, command filter and neural network are introduced to reconstruct system nonlinearities that are related to complex uncertainties. Compared with the FTC scheme with only neural network, the FTC scheme with command filter and neural network has fewer controller design parameters so that the computational complexity is decreased and the control efficiency is improved, which is of great significance for HRV. Then, the adaptive backstepping fault-tolerant controller based on command filter and neural network is designed, which can solve the complexity explosion problem in the standard backstepping control and the small uncertainty problem in the backstepping control only containing command filter. Moreover, to improve the approximation accuracy of the neural network-based universal approximator, an adaptive update law of neural network weights is designed by using the convex optimization technique. It is proved that the presented FTC scheme can ensure that the closed-loop control system is stable and the tracking errors are convergent. Finally, simulation results are carried out to verify the superiority and effectiveness of the presented FTC scheme.     

Auto-structuring fuzzy neural system for intelligent control

An auto-structuring fuzzy neural network-based control system (ASFNS), which includes the auto-structuring fuzzy neural network (ASFNN) controller and the supervisory controller, is proposed in this paper. The ASFNN is used as the main controller to approximate the ideal controller and the supervisory controller is incorporated with the ASFNN for coping with the chattering phenomenon of the traditional sliding-mode control. In the ASFNS, an automatic structure learning mechanism is proposed for network structure optimization, where two criteria of node-adding and node-pruning are introduced. It enables the ASFNN to determine the nodes autonomously while ensures the control performance. In the ASFNS, all the parameters are evolved by the means of the Lyapunov theorem and back-propagation to ensure the system stability. Thus, an intelligent control approach for adaptive control is presented, where the structure and parameter can be evolved simultaneously. The proposed ASFNS features the following salient properties: (1) on-line and model-free control, (2) relax design in controller structure, (3) overall system stability. To investigate the capabilities, the ASFNS is applied to a kind of nonlinear system control. Through the simulation results the advantages of the proposed ASFNS can be validated.     

Command filtered adaptive output feedback design with novel Lyapunov-based analysis for nonlinear systems with unmodeled dynamics

This paper presents a novel Lyapunov function-based backstepping controller design to tackle the tracking problems for nonlinear systems with unmodeled dynamics and unmeasurable states. The coexistence of unmodeled dynamics and unmeasurable states is the main challenge, which calls for novel techniques to take these two factors into account simultaneously. First, the classical Luenberger observer is extended with a novel transformation function to decouple the original system state and state estimation error. In this way, the effect of unmodeled dynamics on system stability can be separately considered. On this basis, a command-filtered controller is designed to simplify the backstepping design procedures. It is worthy to pointed out that, a novel Lyapunov function is developed to simplify the stability analysis with command filter, where the filter errors, the observer error, compensated tracking errors, and parameter estimation errors can be guaranteed to be semi-globally uniformly ultimate bounded. The simulation studies are investigated to validate the effectiveness of the presented design scheme.     

State quantized sampled-data control design for complex-valued memristive neural networks

In this paper, several resultful control schemes based on data quantization are proposed for complex-valued memristive neural networks (CVMNNs). Firstly, considering the finite communication resources and the interference of failures to the system, a state quantized sampled-data controller (SQSDC) is designed for CVMNNs. Next, taking the interference of gain fluctuations into account, a non-fragile sampled-data control (SDC) law is proposed for CVMNNs in the framework of data quantification. In order to full capture more inner sampling information, a newly Lyapunov-Krasovskii function (LKF) is constructed on the basis of the proposed triple integral inequality. After that, in the framework of taking full advantage of the property of Bessel-Legendre inequality, a time-dependent discontinuous LKF (TDDLKF) is proposed for CVMNNs with SQSDC. Based on the useful LKF, several stability criteria are established. Finally, the numerical simulations are provided to substantiate the validity and less conservatism of the proposed schemes.     

Adaptive output feedback neural network control of uncertain non-affine systems with unknown control direction

This paper deals with the problem of adaptive output feedback neural network controller design for a SISO non-affine nonlinear system. Since in practice all system states are not available in output measurement, an observer is designed to estimate these states. In comparison with the existing approaches, the current method does not require any information about the sign of control gain. In order to handle the unknown sign of the control direction, the Nussbaum-type function is utilized. In order to approximate the unknown nonlinear function, neural network is firstly exploited, and then to compensate the approximation error and external disturbance a robustifying term is employed. The proposed controller is designed based on strict-positive-real (SPR) Lyapunov stability theory to ensure the asymptotic stability of the closed-loop system. Finally, two simulation studies are presented to demonstrate the effectiveness of the developed scheme.     

Real time observer and control scheme for a wind turbine system based on a high order sliding modes

The introduction of advanced control algorithms may improve considerably the efficiency of wind turbine systems. This work proposes a high order sliding mode (HOSM) control scheme based on the super twisting algorithm for regulating the wind turbine speed in order to obtain the maximum power from the wind. A robust aerodynamic torque observer, also based on the super twisting algorithm, is included in the control scheme in order to avoid the use of wind speed sensors. The presented robust control scheme ensures good performance under system uncertainties avoiding the chattering problem, which may appear in traditional sliding mode control schemes. The stability analysis of the proposed HOSM observer is provided by means of the Lyapunov stability theory. Experimental results show that the proposed control scheme, based on HOSM controller and observer, provides good performance and that this scheme is robust with respect to system uncertainties and external disturbances.     

Neural-network-based decentralized fault-tolerant control for a class of nonlinear large-scale systems with unknown time-delayed interaction faults

This paper proposes an adaptive approximation design for the decentralized fault-tolerant control for a class of nonlinear large-scale systems with unknown multiple time-delayed interaction faults. The magnitude and occurrence time of the multiple faults are unknown. The function approximation technique using neural networks is employed to adaptively compensate for the unknown time-delayed nonlinear effects and changes in model dynamics due to the faults. A decentralized memoryless adaptive fault-tolerant (AFT) control system is designed with prescribed performance bounds. Therefore, the proposed controller guarantees the transient performance of tracking errors at the moments when unexpected changes of system dynamics occur. The weights for neural networks and the bounds of residual approximation errors are estimated by using adaptive laws derived from the Lyapunov stability theorem. It is also proved that all tracking errors are preserved within the prescribed performance bounds. A simulation example is provided to illustrate the effectiveness of the proposed AFT control scheme.     

Fault-tolerant control for commercial aircraft with actuator faults and constraints

In this paper, a constrained control scheme based on model reference adaptive control is investigated for the longitudinal motion of a commercial aircraft with actuator faults and saturation nonlinearities. Actuator faults and constraints are both important factors adversely affecting the stability and performance of flight control systems. An adaptive adjustment law based on Lyapunov function is utilized to adjust the fault-tolerant control law. Both additive and multiplicative faults are considered in the designed controller to deal with the three types of actuator faults: locked in place, loss of effectiveness, and bias. Moreover, different techniques are implemented in the basic and fault-tolerant controller to anti-windup. Proofs for the stability of the two modified controllers which improve the performance of control system operating in the presence of actuator faults and saturations are proposed. Finally, a numerical example of the anti-windup fault-tolerant controller for a commercial aircraft is demonstrated. The stability and performance improvements can be accrued with the presented fault-tolerant control scheme.     

Adaptive prescribed performance control for nonlinear robotic systems

This paper investigates the problem of asymptotic tracking control of nonlinear robotic systems with prescribed performance. The control strategy is developed based on a modified prescribed performance function (PPF) to guarantee the transient behavior, while the requirements on the accurate initial tracking error in the classical PPF can be remedied. The fuzzy logic system (FLS) is used to approximate the unknown dynamics. In the existing PPF based adaptive control schemes with FLSs, the tracking error does not achieve asymptotic convergence. To address this issue, a robust integral of the sign of the error (RISE) term is incorporated into the control design to reject the FLS approximation errors and external disturbances, such that the asymptotic convergence is achieved. Finally, numerical simulation and experimental results validate the effectiveness of the proposed control scheme.     

Adaptive controller design for spacecraft formation flying using sliding mode controller and neural networks

A spacecraft formation flying controller is designed using a sliding mode control scheme with the adaptive gain and neural networks. Six-degree-of-freedom spacecraft nonlinear dynamic model is considered, and a leader–follower approach is adopted for efficient spacecraft formation flying. Uncertainties and external disturbances have effects on controlling the relative position and attitude of the spacecrafts in the formation. The main benefit of the sliding mode control is the robust stability of the closed-loop system. To improve the performance of the sliding mode control, an adaptive controller based on neural networks is used to compensate for the effects of the modeling error, external disturbance, and nonlinearities. The stability analysis of the closed-loop system is performed using the Lyapunov stability theorem. A spacecraft model with 12 thrusts as actuators is considered for controlling the relative position and attitude of the follower spacecraft. Numerical simulation results are presented to show the effectiveness of the proposed controller.     

Chaos control of the permanent magnet synchronous motor with time-varying delay by using adaptive sliding mode control based on DSC

This paper focuses on the problem of chaos control for the permanent magnet synchronous motor with chaotic oscillation, unknown dynamics and time-varying delay by using adaptive sliding mode control based on dynamic surface control. To reveal the mechanism of motor system and facilitate controller design, the dynamic behavior of the system is investigated. Nonlinear items of system model, upper bounds of time delays and their derivatives are taken as unknown in the overall process. A RBF neural network with an adaptive law, which eliminates restrictions on accurate model and parameters, is employed to cope with unknown dynamics. In order to solve issues such as chaotic oscillation, ‘explosion of complexity’ of backstepping, and chattering associated with sliding mode control, a sliding mode controller is developed within the framework of dynamic surface control by the hybrid of adaptive technology and RBF neural network. In addition, an appropriate Lyapunov function is employed to demonstrate the system stability. Finally, the feasibility of the proposed scheme is testified by simulation.     

Intelligent control for robotic manipulator with adaptive learning rate and variable prescribed performance boundaries

The purpose of this study is to enhance the transient performance and mitigate the possible boundary-crossing issue during the design of a neural network-based intelligent prescribed performance control for robotic manipulators that suffer from input saturation. Initially, an auxiliary system is created utilizing the saturation signal, which is then used to modify the prescribed performance boundaries when saturation takes place. This ensures that the tracking errors adhere to the performance constraints even if the available control effort is limited. To further enhance the transient performance of the closed-loop system, a composite learning-based online identification scheme employing a Gaussian function to adaptively adjust the learning rate is utilized instead of a fixed-learning-rate weight updating law to train the neural network. This approach facilitates the reduction of the undesired weight oscillations at the beginning of the control process when the neural network is not sufficiently trained. Lastly, the stability of the closed-loop system is demonstrated by applying the Lyapunov approach, and simulation results support the effectiveness of the identification and control schemes proposed in this study.