Adaptive Neural Network Control Research Articles

Neural Network Adaptive Inverse Control of Flexible Joint Space Manipulator Considering the Influence of Gravity

With the aim of correcting the problem of trajectory tracking control of a flexible joint space manipulator in environments with different gravity, a neural network adaptive inverse control algorithm based on singular perturbation theory is proposed to resist the disturbance caused by system uncertainty. Firstly, the dynamic model of a flexible joint space manipulator with the influence of gravity is established, and then the system is divided into a fast subsystem and a slow subsystem using singular perturbation theory. The velocity feedback control rate is designed for the fast subsystem to suppress the elastic vibration caused by the joint flexibility. For the slow subsystem, the uncertain term and known term are separated by the inverse control algorithm, where the uncertain term is approximated online by the RBF neural network, and the robust control rate is designed to compensate for the approximation error. The simulation results show that the control method can not only effectively reduce the high-frequency vibration caused by the flexible joint but also resist the system disturbance so that a good track control effect is achieved.

Observer-based adaptive neural network control: the convergence properties analysis under the influence of persistent excitation level

Observer-based adaptive neural network control: the convergence properties analysis under the influence of persistent excitation level

Event-triggered finite-time adaptive neural network control for quadrotor UAV with input saturation and tracking error constraints

In this article, an event-triggered finite-time adaptive neural network control tracking strategy is proposed for quadrotor unmanned aerial vehicle (UAV) with input saturation and error constraints. Firstly, the radial basis function neural networks (RBFNNs) are adopted to identify the unknown uncertainty of quadrotor UAV model from the installation errors, gyroscope errors and so on. An auxiliary equation is constructed to deal with input physical saturation from the actuator motors. Additionally, by combining the performance function and error transformation, the issue of error constraint is solved. Based on the Lyapunov stability theory and event-triggered mechanisms, a finite-time adaptive neural network scheme is developed to ensure that the closed-loop quadrotor UAV system is semi-globally practically finite-time stable, and save the computation, resources, and transmission load. Finally, the simulation results illustrate the good tracking performance of quadrotor UAV by using the proposed control strategy.

Gait coordination control of bipedal modular reconfigurable robot based on adaptive neural network

This paper proposed an adaptive neural network (NN) control method to track the desired trajectory of a bipedal modular reconfigurable robot (MRR), which can solve the gait coordination problem of bipedal MRR. The leg dynamic model and the body dynamic model of bipedal MRR are established based on the Newton–Euler iterative method, and the global dynamic model is subsequently established. Aiming at the gait coordination problem between double support phase (DSP) and single support phase (SSP), the desired trajectory is generated based on the zero-moment point (ZMP) method. The adaptive NN controller is designed to track the generated desired trajectory, which also compensates interconnected dynamic coupling (IDC) effects of the bipedal MRR. The stability of bipedal MRR system is proved by Lyapunov theory. In the end, the effectiveness of the control method is verified by comparative simulation. The simulation results show that the proposed adaptive NN method reduces the position tracking error by [Formula: see text] and the control torque by [Formula: see text] compared with the existing control methods.

Switching Event-Triggered Adaptive Neural Network Control for Switched Nonlinear Systems Under Hybrid Attacks

Switching Event-Triggered Adaptive Neural Network Control for Switched Nonlinear Systems Under Hybrid Attacks

Adaptive control of nonlinear time-varying systems with unknown parameters and model uncertainties

This paper investigates the adaptive control problem for nonlinear time-varying systems with unknown parameters and model uncertainties. A novel class of switching functions is designed, and its construction method is detailed, along with a proof of the continuity of its n−1 order derivatives. Two simple examples are provided to illustrate how the proposed congelation of variables method handles unknown high-frequency time-varying parameters in both the feedback and input paths. A new neural network control scheme is then developed, integrating an adaptive neural network controller with a robust controller. The smooth transition between these two controllers is ensured by the novel switching function, which guarantees global system stability. Furthermore, by combining the congelation of variables method with adaptive backstepping, a new adaptive tracking control scheme is proposed. This scheme effectively handles unknown high-frequency time-varying parameters while achieving asymptotic tracking of arbitrary reference signals. Simulation results show that the proposed novel adaptive control method delivers superior control accuracy while reducing energy consumption: it achieves an order of magnitude improvement over the traditional adaptive robust control method and two orders of magnitude improvement over the conventional sliding mode control method.

Research on Heave Compensation System Based on Switched Reluctance Motor

Aiming at the requirements of the marine work platform for real-time control, time-varying speed and the time-varying torque control of the motor-driven active heave compensation device, this paper introduces a composite control strategy based on the switched reluctance motor (SRM)-driven active heave compensation device. As for the compensation error caused by the time lag in the real-time system, the model prediction trajectory algorithm is used to predict the compensation displacement obtained using the dynamic model. The next time, the control parameters are then provided for the SRM control system in advance to reduce the compensation error. The SRM control strategy selects a double closed-loop compound control strategy of Back Propagation (BP) fuzzy neural network Proportion Integration Differentiation (PID) control. Its outer speed loop uses a fuzzy controller to quickly track a wide range of speed changes. The torque inner loop uses BP neural network adaptive PID control. This helps to reduce torque ripple and to ensure that the electromagnetic torque output of the SRM remains stable. Finally, the system feasibility is verified by setting different wave parameters. The simulation results show that the simulation conditions can reach 97.5% and 96.4% under the 3 and 4 wave levels, respectively. The simulation effect is satisfying, which verifies the feasibility of the proposed scheme.

Fixed-Time Fault-Tolerant Adaptive Neural Network Control for a Twin-Rotor UAV System with Sensor Faults and Disturbances

This paper presents a fixed-time fault-tolerant adaptive neural network control scheme for the Twin-Rotor Multi-Input Multi-Output System (TRMS), which is challenging due to its complex, unstable dynamics and helicopter-like behavior with two degrees of freedom (DOFs). The control objective is to stabilize the TRMS in trajectory tracking in the presence of unknown nonlinear dynamics, external disturbances, and sensor faults. The proposed approach employs the backstepping technique combined with adaptive neural network estimators to achieve fixed-time convergence. The unknown nonlinear functions and disturbances of the system are processed via an adaptive radial basis function neural network (RBFNN), while the sensor faults are actively estimated using robust terms. The developed controller is applied to the TRMS using a decentralized structure where each DOF is controlled independently to simplify the control scheme. Moreover, the parameters of the proposed controller are optimized by the gray-wolf optimization algorithm to ensure high flight performance. The system’s stability analysis is proven using a Lyapunov approach, and simulation results demonstrate the effectiveness of the proposed controller.

Neural Network-based Adaptive Finite-time Control for 2-DOF Helicopter Systems with Prescribed Performance and Input Saturation

In this study, we propose an adaptive neural network (NN) control approach for a 2-DOF helicopter system characterized by finite-time prescribed performance and input saturation. Initially, the NN is utilized to estimate the system’s uncertainty. Subsequently, a novel performance function with finite-time attributes is formulated to ensure that the system’s tracking error converges to a narrow margin within a predefined time span. Furthermore, adaptive parameters are integrated to address the inherent input saturation within the system. The boundedness of the system is then demonstrated through stability analysis employing the Lyapunov function. Finally, the effectiveness of the control strategy delineated in this investigation is validated through simulations and experiments.

Adaptive neural network control of a centrifugal chiller system

In this paper, a neuro-adaptive PI control strategy for a water-cooled centrifugal chiller system is developed, and its control performance is examined. The system model consists of a flooded evaporator, a flooded condenser, a centrifugal compressor, and an electronic expansion valve. The overall system consists of three control loops: a compressor speed control loop, an inlet guide vane (IGV) control loop, and a condenser liquid level control loop. A neuro-adaptive control strategy for compressor speed control was designed. The control performance of the chiller was tested by carrying out simulation runs using an integrated building and HVAC (IB-HVAC) system model. The major details of the IB-HVAC model are described in this paper. Results show that the neuro-adaptive controller can adapt to new system dynamics of the IB-HVAC system and give good setpoint tracking responses under a wide range of operating conditions. The results show that the neuro-adaptive controller performs better than the constant gain PI controller in terms of speed of response and setpoint tracking properties.

Observer-based self-triggered adaptive neural network control for nonlinear systems with prescribed time

This paper is concerned with the adaptive neural networks (NNs) prescribed-time control problem for a class of strict-feedback nonlinear systems subject to unmeasured states via the self-triggered control (STC). By developing a new state observer with prescribed-time function, an adaptive NNs self-triggered controller is designed to solve the problem of prescribed-time performance (PTP). Due to the initiative of the STC, it has excellent practical significance in terms of contracting computing resources and network communication resources. With the proposed new strategy, the PTP of the closed-loop system can be guaranteed, and all the signals within the closed-loop system are bounded. Finally, the practicability and effectiveness of the above prescribed-time STC algorithm are verified via some physical simulations.

Evaluation of advanced control strategies for PMSG in wind turbines: backstepping fuzzy logic control and adaptive neural network control approaches

This study presents a comparative analysis of two advanced control strategies for Permanent Magnet Synchronous Generators (PMSGs) in wind turbines: Backstepping Fuzzy Logic Control and Adaptive Neural Network Control. The aim is to evaluate their effectiveness in handling structured and unstructured uncertainties and enhancing system performance. Backstepping Fuzzy Logic Control integrates backstepping techniques with fuzzy logic regulation to improve flexibility and robustness. This method addresses the limitations of traditional PI controllers by enhancing adaptability to parameter variations and external disturbances. In contrast, Adaptive Neural Network Control employs neural networks with dynamic compensators to address high uncertainties and nonlinearities, aiming to surpass the performance of conventional PI controllers. The study involves simulations to compare these control strategies based on several criteria: robustness in managing parameter changes and external disturbances, flexibility in adapting to dynamic conditions, and overall performance including efficiency and stability. Simulation results indicate that both strategies offer significant improvements over traditional PI controllers. Backstepping Fuzzy Logic Control demonstrates strong adaptability and robustness, while Adaptive Neural Network Control shows superior efficiency and optimality, particularly in high-uncertainty environments. This comparative analysis provides insights into the strengths and limitations of each approach, offering guidance for selecting the most suitable control strategy based on specific operational requirements. The findings contribute to advancing control methodologies in wind energy systems and suggest directions for future research and practical implementation.

Advancing wind energy: adaptive neural network control for optimized permanent magnet synchronous generators

Our contribution in this paper is to design an adaptive neural network (NN) based control of a permanent magnet synchronous generator in order to overcome the effect of structured and unstructured uncertainties and external disturbances, in addition to ensuring the stability of the system, the proposed robust control strategy compensates adaptively for significant uncertainties present in uncertain nonlinear systems. First, we present the vector control of PMSG model applying two tests: with and without constrains, and then, the neural network control with PI controllers. However, conventional controllers suffer from limitations due to the presence of these high uncertainties. Therefore, we aim to improve the efficiency of artificial neural control by using dynamic compensators instead of PI controllers. The estimated states are used as inputs to the neural network (NN). Simulations of the proposed control algorithm are conducted then compared to the previous controllers: vector control and neural network control with PI controllers. Furthermore, using dynamic compensators in artificial neural control achieved both efficiency and optimality. Results have been successfully confirmed via computer simulations using MATLAB.

Event-Based Neural Networks Adaptive Control of Nonlinear Systems: A Fully Actuated System Approach

Event-Based Neural Networks Adaptive Control of Nonlinear Systems: A Fully Actuated System Approach

Neural Network Adaptive Controller Design for Air-Ground Heterogeneous Formation

Neural Network Adaptive Controller Design for Air-Ground Heterogeneous Formation

Design of a novel intelligent adaptive fractional-order proportional-integral-derivative controller for mitigation of seismic vibrations of a building equipped with an active tuned mass damper

The primary objective of this study is to introduce a novel adaptive fractional order proportional–integral–derivative (FOPID) controller. The adaptive FOPID controller’s parameters are dynamically adjusted in real-time using five distinct multilayer perceptron neural networks. The extended Kalman filter (EKF) is employed to facilitate the parameter-tuning process. A multilayer perceptron neural network, trained using the error Backpropagation algorithm, is employed to identify the structural system and estimate the plant. The real-time estimated Jacobian is applied to the controller to control the model. The stability and robustness of the adaptive interval type-2 fuzzy neural networks controller are enhanced by utilizing the EKF and the feedback error learning strategy for compensator tuning. This improvement increases resilience against estimation errors, seismic disturbances, and unknown nonlinear functions. The primary objective is to address the challenges posed by maximum displacement, acceleration, and drift, as well as the uncertainties arising from variations in stiffness and mass. In order to validate the reliability of the proposed controller, the performance investigation is carried out on an 11-story building equipped with an active tuned mass damper under far and near-field earthquakes. Numerical findings show the remarkable effectiveness of the proposed controllers compared to their predecessors. In addition, it is revealed that the inclusion of the adaptive interval type-2 fuzzy neural networks compensator has increased the performance of the proposed controller and shows significant capabilities in reducing the seismic responses of structures during severe earthquake events.

Discrete-Time Event-Triggered Type-2 fuzzy wavelet neural network control for Multi-Motor servo system

This paper investigates a discrete-time event-triggered adaptive neural network control scheme for a multi-motor servo system (MMSS) to realize a desired position tracking performance. First, a discrete-time model of the MMSS, including a dead-zone and a nonlinear friction, is established based on the Euler’s discretization. Then, a discrete-time adaptive neural network controller is designed by integrating a type-2 fuzzy wavelet neural network (T2FWNN) and the backstepping technology. The neural network is not only used to estimate uncertain nonlinearities, but also can handle the non-causal problem caused by the conventional backstepping method. Meanwhile, a fixed threshold event-triggered mechanism along with the incorporation of a dead-zone operator is superimposed into the actual controller thus saving communicational resources. Besides, stability analysis proves that all the signals in the closed MMSS are bounded, and the position tracking error converges to a small neighborhood of the origin. Finally, abundant simulation experience results demonstrate the effectiveness and robustness of the proposed scheme.

Distributed robust neural network adaptive fault-tolerant control for amorphous flattened air-ground wireless self-assembly network system

Distributed robust neural network adaptive fault-tolerant control for amorphous flattened air-ground wireless self-assembly network system

Research on gravity compensation control of BPNN upper limb rehabilitation robot based on particle swarm optimization

AbstractA four‐degree‐of‐freedom upper limb exoskeleton rehabilitation robot system with a gravity compensation device is constructed. The objective is to address the rehabilitation training needs of patients with upper limb motor dysfunction. A BP neural network adaptive control method based on particle swarm optimization is proposed. First, the degrees of freedom of the human body are analyzed, and a Lagrange method is employed to construct a dynamic model. Second, a particle swarm optimization back propagation neural network adaptive control algorithm based on particle swarm optimization is presented. Subsequently, the range of motion of the upper limbs is analyzed with reference to muscle anatomy and a three‐dimensional motion capture system. And the robot structure design is analyzed in detail. Finally, simulation experiments were conducted, and the results demonstrated that the proposed method exhibited high effectiveness and accuracy.

Output feedback adaptive neural network control for uncertain nonsmooth systems with application

The output feedback adaptive neural network control problem is addressed for uncertain nonsmooth systems with network communication constraints. First, a funnel function is provided to ensure that the tracking error restrains the pre-specified performance and improves the transient and steady-state performance simultaneously. Second, an event-triggered controller including the control input, a fixed threshold and the tracking error is designed to alleviate the communication burden. It is rigorously mathematically proved that there exists a positive lower bound to avoid the Zeno behavior. With the designed observer, the control algorithm assures that all the signals are semi-globally uniformly ultimately bounded. Finally, the validity of the proposed scheme is demonstrated through an application example.