Neural Network Control Scheme Research Articles

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.

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.

Event-Triggered Adaptive Neural Network Tracking Control for Uncertain Systems With Unknown Input Saturation Based on Command Filters.

This brief presents a modified event-triggered command filter backstepping tracking control scheme for a class of uncertain nonlinear systems with unknown input saturation based on the adaptive neural network (NN) technique. First, the virtual control functions are reconstructed to address the uncertainties in subsystems by using command filters. A piecewise continuous function is employed to deal with the unknown input saturation problem. Next, an event-triggered tracking controller is developed by utilizing the adaptive NN technique. Compared with standard NN control schemes based on multiple-function-approximators, our controller only requires a single NN. The closed-loop system stability is analyzed based on the Lyapunov stability theorem, and it is shown that the Zeno behavior is also avoided under the designed event-triggering mechanism. Simulation studies are performed to validate the effectiveness of our controller.

Active Control of Longitudinal Combustion Instability in Bluff-Body Stabilized Premixed Flames with Multiple Neural Network Controller

ABSTRACT The suppression performance of multiple neural network controller on the longitudinal combustion instability is investigated in the Volvo bluff-body stabilized premixed flame. Two controlled plant models, e.g. one-dimensional (1D) reduced order acoustic network model and three-dimensional (3D) large eddy simulation model are adopted to verify this control strategy. In order to build the reduced order Volvo acoustic network model, large eddy simulation is adopted to extract the characteristics of system heat release under wide bandwidth and construct the flame transfer functions. For the 1D acoustic network model, this controller can completely eliminate the pressure oscillation using fuel valve as actuator. For the 3D large eddy simulation model that mimics the real-time oscillating characteristics, clustered prediction method and amplitude limiting method are adopted in multiple neural network control strategy to better account for the nonlinear characteristics of the 3D Volvo flame. This control strategy enables the modulation of the phase relationship between the heat release rate oscillation and pressure oscillation by introducing small perturbations to the inlet equivalence ratio, and attenuates the amplitude of the second harmonic of the unstable mode effectively.

Adaptive Neural Network Finite-Time Prescribed Performance Consensus Control for a Class of Second-Order Multi-Agent Systems

This research investigates the semi-global practical finite-time prescribed performance consensus control issue for a class of second-order multi-agent systems with unknown nonlinear functions. Unlike the previous finite-time control set by a finite-time performance function, we give finite-time control by constraining the terminal sliding manifold in a performance function. In addition, an adaptive neural network control scheme is designed, which simplifies the controller and avoids the chattering issue existing in traditional sliding mode control. Eventually, a novel adaptive finite-time prescribed performance consensus control strategy is designed, which ensures that all system variables are semi-globally practical finite-time stable and consensus errors of the multi-agent systems converge within the prescribed region in finite time. The effectiveness and practicality of the presented control strategy are evaluated by conducting simulation cases.

Disturbance Observer-Based Adaptive Intelligent Control of Marine Vessel With Position and Heading Constraint Condition Related to Desired Output.

This article studies the adaptive control about the geodetic fixed positions and heading of three-degree-of-freedom dual-propeller vessel. During the navigation of a vessel at sea, due to the unpredictable sea, on the one hand, it is important to ensure that the vessel can smoothly follow the desired geodesic fixed position and heading; on the other hand, when the sailing environment is harsh, it is even more important that the vessel can adapt to the desired geodesic fixed position and heading that change at any time for safe driving. Therefore, this article selects the time-varying function related to the desired geodesic fixed position and heading as the constraint condition, and the constraint condition will change in real time as the expected position and heading change. The design of the control strategy is difficult, and the designed control strategy will be more suitable for complex maritime navigation conditions. First, the article constructs a log-type barrier Lyapunov function. Second, by introducing an unknown external disturbance observer, the external disturbances caused by the environment that may be encountered during the vessel's voyage can be observed. Then, combined with the backstepping algorithm, a neural network (NN) control strategy and adaptive law are designed. Among them, for the uncertain function in the process of designing the control strategy, the NN is used to approximate it. Furthermore, through the Lyapunov stability analysis, it is shown that applying the designed control strategy to the vessel system in this article can ensure that the system is closed-loop stable. The final simulation experiment shows the effectiveness of the designed control strategy.

Adaptive Neural Network Tracking Control of Robotic Manipulators Based on Disturbance Observer

This article presents an adaptive neural network (ANN) control scheme based on a disturbance observer that can achieve trajectory tracking control of robotic manipulators under external disturbances and dynamic model uncertainties. Firstly, an ANN controller based on full-state feedback is derived using the backstepping technique to achieve an online approximation of uncertainty. The integral sliding mode surface with a position error is introduced into the controller, which reduces the steady-state error of the system and enhances robustness. Then, a novel disturbance observer is designed to estimate both the approximation errors of the ANN and external disturbances, and to provide compensation for the controller, effectively suppressing the trajectory tracking errors caused by approximation errors and disturbances. Subsequently, the Lyapunov stability theory is utilized to demonstrate the stability of the developed control strategy and the boundedness of all closed-loop signals. Finally, numerical simulations are used to confirm the efficacy of the proposed control method.

A DNN-orchestrated cognitive radio-based power control scheme for D2D communication

Device-to-device (D2D) communication demonstrates its efficacy across diverse domains, including military, surveillance, public safety, disaster management, content sharing, and local advertising, through its provision of proximity-based connections. Moreover, it elevates data rates, spectrum efficiency, and network throughput with efficient resource allocation while simultaneously reducing latency. However, it encounters challenges related to unregulated high-power consumption, leading to interference in D2D communication. Hence, in this paper, we proposed a deep neural network (DNN) and cognitive radio-driven efficient power control scheme for D2D communication. The proposed scheme operates in two distinct phases: the cognitive radio and the DNN-based phase. In this context, cognitive radio aids in selecting secondary users or cellular mobile equipment (CUE) through energy detection spectrum sensing. Subsequently, the DNN model is employed to optimize the transmission power of CUE in D2D communication. The effectiveness of the proposed scheme is assessed through various metrics, including loss, optimizers, learning rates, and sum rates.

Decentralized event‐triggered output feedback adaptive neural network control for a class of MIMO uncertain strict‐feedback nonlinear systems with input saturation

SummaryFor a class of multiple‐input multiple‐output large‐scale nonlinear systems in strict‐feedback form with input saturation, external disturbances and immeasurable states, an adaptive decentralized neural network (NN) control strategy on the basis of event triggered mechanism is investigated in this article. In contrast to the literature, the proposed method is centered on the control‐error as a replacement to the tracking‐error that leads to a simplified derivation approach of adaptive laws. Furthermore, the control gains for this class of systems are considered unknown nonlinear functions and not assumed as simple unity or known gains as always done in the literature. Moreover, the challenge of losing controllability that typically arises in state transformation‐based methods, as reported in the literature, is entirely resolved in our approach. Last and not least, all restrictions imposed on unmatched interconnections are eliminated along with avoiding the complexity explosion caused by recursive back‐stepping designs. For this end, the unknown ideal control laws are approximated using NNs, while additional control terms are added to handle saturation effects, unknown interactions, and approximation errors. Additionally, fuzzy inference systems are employed to estimate unknown control errors. Due to the strictly positive real property, the tracking errors are proved to belong to a small compact set using Lyapunov theory. Simulation results demonstrate the effectiveness of the proposed approach.

Power Quality Gain of Self-Lift Luo Converter used for Hybrid Renewable Power System with Battery Grid Integration

The renewable power sources such as wind as well as photovoltaic (PV) energy are fashionable for residential and commercial applications. For the reason, that eco friendlessness plus expenditure are effective. This paper intends a Self-Lift Luo converter integrated with solar photovoltaic system to the utility grid along with its Adaptive Neuro-Fuzzy Inference System (ANFIS) and Recurrent Neural Network (RNN) control strategies are proposed. By achieve an energy management for the proposed system using Bidirectional Battery converter along with battery system. Power supervision move towards is suggested to control the DC bus voltage by way of Self-Lift Luo converter. The wind power with Doubly Fed Induction Generator (DFIG) based grid integration with a PI controller. Under this work, DSTATCOM has been used to improve the quality of power under different load conditions. The obtained results designate that the proposed approach delivers recovered performance with enhanced efficiency and nominal harmonics. The intact system is validated through a MATLAB simulation.

A Novel Zeroing Neural Network Control Scheme for Tracked Mobile Robot Based on an Extended State Observer

A novel zeroing neural network control scheme based on an extended state observer is proposed for the trajectory tracking of a tracked mobile robot which is subject to unknown external disturbances and uncertainties. To estimate unknown lumped disturbances and unmeasured velocities, a third-order fixed-time extended state observer is proposed, and the observation errors converge to zero in fixed time. Based on the estimated values, the zeroing neural network controller is designed for a tracked mobile robot to track an eight shape. The stability of the system is analyzed based on Lyapunov theory. Simulation results are illustrated to show the effectiveness of the proposed control scheme.

Global adaptive neural network control of nonlinear time-varying systems with unknown control coefficients and model uncertainties

This paper investigates the adaptive control problem for the strict-feedback nonlinear time-varying system (NTVS) with unknown control coefficients and model uncertainties. To address the problem that the neural network (NN) can only achieve local approximation of unknown nonlinear functions, a novel NN control scheme is proposed. The scheme consists of a NN controller that operates inside the approximation domain and a robust controller that operates outside the approximation domain, and a novel switching function is designed to enable the two controllers to switch smoothly in the vicinity of the approximation domain to ensure that all signals of the closed-loop system are globally uniformly ultimately bounded. To address the problem that unknown time-varying control coefficients are difficult to handle, an adaptive fault-tolerant control scheme is proposed in combination with the congelation of variables method. The scheme employs classical adaptive control to adapt to the variation of unknown control coefficients and robust control to eliminate the time-varying disturbance terms, and introduces a positive integrable time-varying function to achieve asymptotic tracking of an arbitrary reference signal. The combination of these two schemes constitutes a global adaptive neural network control (GANNC) method for the NTVS with unknown control coefficients and model uncertainties. Finally, an adaptive attitude fault-tolerant controller for launch vehicles is designed by using the GANNC method, which can realize the accurate tracking of the attitude control system to the reference command under normal status, strong disturbances and actuator failures, and comparative experiments prove the effectiveness and superiority of the controller.

Anti-lock braking control using an interval type-2 fuzzy neural network scheme for electric vehicles

Control precision and robustness can be regarded as essential challenges of slip ratio control because of the external uncertainties of road conditions and the internal delay response of braking actuators. In addition, it is difficult to obtain a trade-off between braking energy recovery efficiency and braking safety under some extreme braking conditions. To synchronously improve both slip ratio control and braking energy recovery efficiency for different road conditions, an anti-lock braking system (ABS) using a novel interval type-2 fuzzy neural network (IT2FNN) control scheme is proposed for electrohydraulic braking systems. The novel IT2FNN control scheme with five layers is designed to calculate the commanded braking torque. The membership function layer utilizes type-2 fuzzy sets to describe the slip ratio error degree, which enhances the scheme’s anti-interference ability, and the enhanced Karnik-Mendel (EKM) algorithm is used in the type-reduction layer to accelerate computation. Additionally, the network adjusts the parameters of the membership function and rules by decreasing the performance function value corresponding to the braking torque error to improve slip ratio control and enhance the self-adaptation capacity. Simulations showed that IT2FNN control can not only improve slip ratio control performance and decrease the braking torque error but also enhance the energy recovery efficiency of regenerative braking on different road surfaces.

Design of a neural network control scheme for the maximum power point tracking (MPPT)

This paper proposes a control method for the maximum power point tracking (MPPT) of a photovoltaic system and this with the aim of increasing the output power of a photovoltaic system. An electronic controller is built-in between the photovoltaic generator and the load, whose principal role is the permanent monitoring of the maximum power point of the PV generator commonly called MPPT (Maximum Power Point Tracking) and that in general by acting on a DC-DC converter device. The contribution of this paper resides at the level DC converter device. The contribution of this paper resides at the level of the electric output of the converter, which can be estimated thru three state variables, which are the solar insolation, the temperature of the junction and information on the dynamics of the charging voltage if it exists.

Adaptive and intelligent control of a dual-arm space robot for target manipulation during the post-capture phase

Dual-arm space robots provide a promising solution for efficiently and flexibly completing complex on-orbit servicing tasks. However, their effectiveness is often hindered by strong dynamic coupling between the robotic arms and the satellite base in the microgravity environment. In this paper, both robotic arms are used as task arms, and a system model that considers the closed-loop constraint formed after a dual-arm space robot captures a target is established. On this basis, two types of control strategies, namely self-tuning control strategy (STC) and radial basis function neural network control strategy (RBF) are proposed for trajectory tracking of the target transferred or detumbled by the robot arms in the presence of system uncertainty or external disturbances. The control methods are verified and compared against the traditional computed torque control strategy (CTC) in terms of control accuracy and system robustness through simulation. The results demonstrate the excellent robustness of both RBF and STC strategies. RBF outperforms the other strategies in terms of control accuracy, while STC proves to be the most energy-efficient.

Adaptive inertia and damping of grid‐connected inverter with improved VSG control

AbstractThe control technology of virtual synchronization generator (VSG) based on energy storage system is proposed to compensate for the inertia and damping loss caused by the grid connection of distributed generators. However, with the addition of virtual inertia and damping, VSG is prone to generate frequency and power oscillation, and the regulating ability is weakened. For the above problems, this paper analyzes the inertia and damping characteristics of the synchronous motor in the rotation of synchronous motors, and applies artificial neural network control to VSG. In intelligent control strategy, a multi‐input‐output radial basis function (RBF) neural network is first proposed to adaptively adjust virtual inertia and damping. Finally, an experimental platform with a rated power of 1 kW and a variable load of 1 kW was built to validate the proposed control strategy. The experimental results show that the artificial neural network control strategy has a better regulation ability.

Radial basis function neural network controller for power control of molten salt breeder reactor of nuclear power plant

The molten salt breeder reactor (MSBR) basically uses molten salt as fuel. Due to molten salt, it is difficult to control power of the MSBR core. To solve this problem, a neural network control scheme is adopted for the same system. Firstly, a nonlinear MSBR model is taken and after linearizing a single input single output (SISO) system is constructed out of it. Radial basis function neural network (RBFNN) has strong tolerance to input noise, online learning ability and good generalization. Therefore, RBFNN controller is used for controlling the core power of the MSBR. The conventional RBFNN dominates in the neural active region. Compact RBF networks has been designed by using newly developed algorithm. By using Lyapunov stability criterion, it has proved that the variation of core power is bounded and it may be comparable to any traditional neural networks or fuzzy interference system. Results of the study reflect the efficiency of RBFNN controller for controlling power of MSBR core.

Adaptive neural network control for Markov jumping systems against deception attacks

This paper proposes an innovative approach for mitigating the effects of deception attacks in Markov jumping systems by developing an adaptive neural network control strategy. To address the challenge of dual-mode monitoring mechanisms, two independent Markov chains are used to describe the state changes of the system and the intermittent actuator. By employing a mapping technique, these individual chains are amalgamated into a unified joint Markov chain. Additionally, to effectively approximate the unbounded false signals injected by deception attacks, an adaptive neural network technique is skillfully built. A mode monitoring scheme is implemented to design an asynchronous control law that links the mode information between the joint Markov chain and controller with fewer modes. The paper derives sufficient criteria for the mean-square bounded stability of the resulting system based on Lyapunov theories. Finally, a numerical experiment is conducted to demonstrate the effectiveness of the proposed method.

Deterministic Learning From Adaptive Neural Network Control for a 2-DOF Helicopter System With Unknown Backlash and Model Uncertainty

In this study, we develop a deterministic learning control approach using adaptive neural network (NN) for a two-degrees-of-freedom helicopter nonlinear system subject to unknown backlash and model uncertainty. First, by combining the backstepping and direct Lyapunov approaches, a novel adaptive NN control scheme with an inverse compensation method is proposed to address the input backlash nonlinearity, track specified trajectories, and stabilize the closed-loop system. Simultaneously, uncertain system dynamics are accurately identified and stored as learned knowledge in constant radial basis function NN weights, while satisfying partial persistent excitation. Subsequently, by extracting the learned knowledge, a learning-based controller is constructed to operate the same control tasks to achieve a superior control performance, less backlash nonlinearity, and minimal computational burden. Finally, the validity and efficacy of the proposed scheme are demonstrated through numerical examples and experiments.

Modeling and control for PEMFC hydrogen management subsystem based on neural network compensation and prescribed tracking accuracy

The hydrogen management subsystem plays an important role in fuel cell automobiles as it impacts the output performance of the polymer electrolyte membrane fuel cell (PEMFC). This paper investigates the design and implementation of the neural network-based control for anode pressure and hydrogen excess ratio (HER). Firstly, the coupled nonlinear multiple-input-multiple-output (MIMO) system is transformed into canonical form one by using input–output linearization. Secondly, the neural network control scheme is proposed to regulate the anode pressure and HER without using the exact prior knowledge of the system. Moreover, a prescribed performance function (PPF) is proposed to guarantee the overshoot and steady-state tracking errors within the quantitative boundaries. To avoid the laborious parameter selection, the restriction that the initial error is within the performance function bound is relaxed by proposing a tuning function. Finally, the Lyapunov stability theory, numerical simulations and hardware-in-loop (HIL) experiments show the effectiveness of the proposed controller. Simulation and HIL experiment results show that the proposed control strategy is effective in realizing quantitative adjustment of tracking error while showing the best performance indexes including the root mean square error (RMSE) and minimum deviation of tracking error (DTE) compared with the neural network controller (NNC) and traditional prescribed performance controller (TPPC).