Neural Control Approach Research Articles

Direct adaptive neural control for precision piezoelectric actuator without hysteresis compensation

This paper introduces a novel Direct Adaptive Neural Control (DANC) approach to enhance the precision of piezoelectric actuator motion control significantly. By effectively addressing the complexities of hysteresis, DANC simplifies system design while delivering superior performance. A Radial Basis Function Neural Network (RBFNN) is employed to handle system uncertainties robustly, and a switching control mechanism guarantees stability, rigorously verified through Lyapunov analysis. Experimental results using a Thorlabs PZS001 actuator convincingly demonstrate substantial performance improvements over conventional PID control, the feedforward-based neural network and feedback control (FF-FB control).

An Improved Predefined-Time Adaptive Neural Control Approach for Nonlinear Multiagent Systems

An Improved Predefined-Time Adaptive Neural Control Approach for Nonlinear Multiagent Systems

Neural network-based distributed consensus tracking control for uncertain Euler–Lagrange systems over directed topologies

This paper proposes a neural network-based robust control approach for driving disturbed Euler–Lagrange systems (e.g., robot manipulator) in a directed network to perform consensus tracking of a heterogeneous leader’s output signal. The parameter matrices and external disturbances in each follower’s Euler–Lagrange dynamics are unmeasurable, thus we unify them into one lumped uncertainty term. Neural networks are then employed to online estimate these uncertainties, with adaptive update laws ensuring the boundedness of the estimation errors. Subsequently, a set of distributed observers are developed to adaptively estimate the leader’s states as well as the unidentified parameter vector and output matrix in the leader’s model. With their help, the robust cooperative controller is designed. Its efficacy on directed networks is theoretically justified by designing a Lyapunov function with a special structure. This function produces symmetric positive definite matrices when its first derivative terms interact with the specified parameters in the observer and Laplacian matrices for directed graphs. Finally, numerical simulations based on two-link robot manipulators are carried out to verify that the tracking errors converge to zero when applying the neural network-based robust controller.

Disturbance observer-based finite-time adaptive neural control scheme of DFIG-wind turbine

This paper introduces a novel disturbance observer-based finite-time adaptive neural control approach to optimize wind power conversion in a doubly fed induction generator-based wind turbines (DFIG-WT). This control strategy offers appealing features including rapid finite-time convergence, both transient and steady-state performance enhancements, and robustness against external disturbances and inherent model uncertainties. The control strategy integrates the neural networks estimation capability with the interesting proprieties of the finite-time control method to achieve efficient wind power conversion. Closed-loop finite-time stability is conducted using the finite-time Lyapunov stability concept of nonlinear systems. The developed control strategy’s effectiveness is confirmed through numerical simulation.

Full-state constraints and input backlash–based neural network control of a 2-DOF helicopter system

This paper introduces an adaptive neural network compensatory control approach designed for a 2-degree-of-freedom (2-DOF) helicopter system facing challenges such as input backlash and state constraints. The proposed methodology leverages a radial basis function (RBF) neural network to effectively approximate system uncertainties, mitigating the impact of nonlinear dynamics on control performance. To address the presence of nonlinear input backlash, a compensation technique is introduced to enhance the smoothness of input signals. In addition, for enhanced system safety, a barrier Lyapunov function is integrated to impose restrictions on position and velocity states, resulting in constrained control. Through a rigorous analysis using the Lyapunov direct method, this paper demonstrates the effectiveness of the proposed approach in achieving bounded stability of the system. The validation of the approach is further established through the presentation of simulation and experimental results, showcasing its effectiveness and feasibility in real-world applications.

Integrated Modular Neural Control for Versatile Locomotion and Object Transportation of a Dung Beetle-Like Robot.

Dung beetles can effectively transport dung pallets of various sizes in any direction across uneven terrain. While this impressive ability can inspire new locomotion and object transportation solutions in multilegged (insect-like) robots, to date, most existing robots use their legs primarily to perform locomotion. Only a few robots can use their legs to achieve both locomotion and object transportation, although they are limited to specific object types/sizes (10%-65% of leg length) on flat terrain. Accordingly, we proposed a novel integrated neural control approach that, like dung beetles, pushes state-of-the-art insect-like robots beyond their current limits toward versatile locomotion and object transportation with different object types/sizes and terrains (flat and uneven). The control method is synthesized based on modular neural mechanisms, integrating central pattern generator (CPG)-based control, adaptive local leg control, descending modulation control, and object manipulation control. We also introduced an object transportation strategy combining walking and periodic hind leg lifting for soft object transportation. We validated our method on a dung beetle-like robot. Our results show that the robot can perform versatile locomotion and use its legs to transport hard and soft objects of various sizes (60%-70% of leg length) and weights (approximately 3%-115% of robot weight) on flat and uneven terrains. The study also suggests possible neural control mechanisms underlying the dung beetle Scarabaeus galenus' versatile locomotion and small dung pallet transportation.

Observer-Based Neural Control of N-Link Flexible-Joint Robots.

This article concentrates on the adaptive neural control approach of n -link flexible-joint electrically driven robots. The presented control method only needs to know the position and armature current information of the flexible-joint manipulator. An adaptive observer is designed to estimate the velocities of links and motors, and radial basis function neural networks are applied to approximate the unknown nonlinearities. Based on the backstepping technique and the Lyapunov stability theory, the observer-based neural control issue is addressed by relying on uplink-event-triggered states only. It is demonstrated that all signals are semi-globally ultimately uniformly bounded and the tracking errors can converge to a small neighborhood of zero. Finally, simulation results are shown to validate the designed event-triggered control strategy.

Decentralised adaptive neural finite-time prescribed performance control for nonlinear large-scale systems based on command filtering

In this research, the issue of decentralised adaptive neural finite-time prescribed performance control is discussed for nonstrict-feedback large-scale nonlinear interconnected systems subject to dead zones input and unknown control direction. The obstacle of ‘explosion of complex’ occurred in conventional backstepping design can be surmounted by adopting the command filter technique and nonlinearities are approximated by introducing an adaptive neural control approach. To handle the obstacles due to unknown directions and unknown interconnections, Nussbaum-type functions and two smooth functions are used and designed. Meanwhile, error compensation signals are introduced to deal with the problem associated with the dynamic surface method. To constraint the output tracking error within a predefined boundary in finite time, an improved performance function, i.e. finite-time performance function is introduced. Different from existing control results, the developed control methodology does not require any information on the boundedness of dead-zone parameters. It is further proved that the constructed controller not only assures the semi-global boundedness of all the controlled system signals, but also makes the output tracking errors reach within a predefined small set. Finally, both numerical and practical examples are supplied to further validate the effectiveness of the presented theoretic result.

Topology-Based Stabilization of Islanded Microgrids With Multiple Tie Switches Under Operational Variations: A Neural Control Approach

Topology-Based Stabilization of Islanded Microgrids With Multiple Tie Switches Under Operational Variations: A Neural Control Approach

Optimizing Automatic Voltage Regulation: A Deep Reinforcement Learning Approach

This paper presents a novel approach to enhance the performance of Automatic Voltage Regulator (AVR) systems in power systems using Deep Reinforcement Learning (DRL). The AVR plays a critical role in maintaining voltage stability and ensuring reliable power delivery. However, conventional control strategies, such as PID controllers, have limitations in handling complex and nonlinear power system dynamics. In this study, the application of DRL techniques is explored, particularly the Twin-Delayed Deep Deterministic Policy Gradient (TD3) algorithm, to AVR control. This algorithm offers the advantage of handling continuous action spaces and enable the controller to learn optimal control policies directly from the system's state information. The results show that the DRL approach outperforms the traditional PID and Neural Network-based control approaches, with the shortest time response and the best voltage regulation performance. The use of DRL in AVR system control shows promising potential for improving the efficiency and accuracy of power system control. This research provides insights into the advantages of DRL for process control and highlights its potential for future applications in power system control.

Stable cargo transportation for underactuated partial space elevator with model uncertainties and disturbances

An adaptive neural network energy-based control approach is proposed in this paper to address the issue of stabilizing a partial space elevator during cargo transportation. The method handles the challenges presented by external disturbances and model uncertainties. The dynamic model of the partial space elevator, with a typical multi-input and multi-output underactuated system, is presented. A control scheme using energy-based techniques is proposed to guarantee the stable configuration of the system, and auxiliary kinematic vector variables are designed to incorporate the uncontrollable variables to constitute controllable state subsets. Under these frameworks, adaptive control schemes are formulated using multi-layer neural networks to mitigate model uncertainty. Robust compensators are designed to effectively counteract the unknown boundaries of external disturbances and approximation errors. The stability of the closed control system is rigorously demonstrated through the application of the Lyapunov function and LaSalle's invariance principle. Numerical simulations demonstrate that the proposed control method is highly effective in suppressing oscillations during the transfer period of a partial space elevator.

Disturbance observer-based neural adaptive stochastic control for a class of kinetic kill vehicle subject to unmeasured states and full state constraints

This paper proposes a disturbance observer-based neural adaptive stochastic control approach for the attitude control system of a class of Kinetic Kill Vehicles (KKVs) with unmeasured states and full state constraints. First, a one-one mapping is applied to transform the attitude control system with state constraints into a nonlinear novel system without any constraint. As a result, the control objective is changed into the boundness of the novel system states. Furthermore, the disturbances existing in the system are effectively estimated and eliminated by the nonlinear disturbance observer as well as the radial basis function neural networks (RBFNNs). Moreover, due to the dynamic signal, the dynamic uncertainty induced by the unmeasured states with an unknown dynamic is compensated appropriately. Utilizing the stochastic Lyapunov process, the boundness of all the signals in the system can be proven and the state constraints are satisfied. Finally, two groups of simulations are conducted, which demonstrate the remarkable performance of the proposed algorithm under different working conditions and highlight the advantages compared with existing studies.

Adaptive Neural Self-Triggered Bipartite Fault-Tolerant Control for Nonlinear MASs With Dead-Zone Constraints

An adaptive neural bipartite tracking control approach is proposed for nonlinear multi-agent systems in this article. In contrast to previous results, it is worth noting that this paper considers a cooperative-competitive relationship in multi-agent systems, which stands for a more common situation. In this paper, a distributed self-triggered communication strategy is designed to improve the transmission efficiency of the whole system. In addition, the designed controller can compensate the actuator failure and dead-zone nonlinearity, and increases the system fault-tolerance. The proposed method ensures the boundedness of all signals of the closed-loop system and the bipartite tracking performance. The effectiveness of the proposed method is verified by two simulation examples. <i>Note to Practitioners</i>&#x2014;Since complex modern engineering systems are difficult to be controlled by a single component, the cooperative control mode of multi-agent systems has become the mainstream trend. For multi-agent systems with cooperative-competitive relationships, the unique bipartite consensus will allow each agent to better complete the control objectives according to their respective advantages. In addition, for engineering systems such as automated manufacturing systems and transportation systems, fault problems are becoming more commonplace. These faults may make the system difficult to operate normally, and then affect the project progress. Therefore, how to guarantee the normal work of the control system when subject to faults has become a key topic. On the other hand, the channel bandwidth of the actual communication system is limited, and frequent updating of control signals will produce huge communication pressure in the traditional control scheme. Hence, it is challenging to design a control strategy that can achieve system stability and reduce communication resources simultaneously. This paper discusses the bipartite fault-tolerant control problem for nonlinear multi-agent systems. Meanwhile, a distributed adaptive self-triggered mechanism is designed to save communication resources.

Adaptive neural dissipative control for markovian jump cyber-Physical systems against sensor and actuator attacks

This work addresses the issue of adaptive neural dissipative control for Markovian Jump Cyber-Physical Systems subject to output-dependent sensor and state-dependent actuator attacks. Attackers can inject false information into feedforward and feedback signals to degrade system performance or even destabilize the system. To identify and approximate attack signals, neural network technique is employed. Attacks are successfully withstood by constructing the estimated signals of these approximate functions. New adaptive state and output feedback controllers are being developed in the meantime. Then, by adapting Lyapunov function technique, sufficient conditions are provided to achieve the stochastic stability of the considered system with extended dissipation. Last, two practical examples are applied to elucidate the effectiveness of the devised adaptive neural control approaches.

Adaptive neural control with fast approximation for uncertain nonlinear systems: A novel composite learning approach

AbstractIn existing adaptive neural control approaches, only when the regressor satisfies the persistent excitation (PE) or interval excitation (IE) conditions, the constant optimal weights of neural network (NN) can be identified, which can be used to establish uncertainties in nonlinear systems. This paper proposes a novel composite learning approach based on adaptive neural control. The focus of this approach is to make the NN approximate uncertainties in nonlinear systems quickly and accurately without identifying the constant optimal weights of the NN. Hence, the regressor does not need to satisfy the PE or IE conditions. In this paper, regressor filtering scheme is adopted to generate prediction error, and then the prediction error and tracking error simultaneously drive the update of NN weights. Under the framework of Lyapulov theory, the proposed composite learning approach can ensure that approximation error of the uncertainty and tracking error of the system states converge to an arbitrarily small neighborhood of zero exponentially. The simulation results verify the effectiveness and advantages of the proposed approach in terms of fast approximation.

Bipartite-tracking quasi-consensus of nonlinear uncertain multi-agent systems: neural network-based adaptive state-constraint impulsive control approach

For the application of multi-agent systems (MASs), the uncertain dynamics and the actuator saturation are inevitable. Considering these factors, the bipartite-tracking quasi-consensus of nonlinear uncertain MASs over signed graph is discussed in this paper. Two kinds of neural network-based adaptive state-constraint impulsive control protocols are proposed, where the communication among the leader and followers only takes place at some discrete instants. Based on the superior approximation ability of radial basis function neural networks (RBFNNs), we design an adaptive weight updating strategy to compensate the uncertain nonlinear dynamics of the system. By means of linear matrix inequality (LMI), convex analysis, impulsive system theory and Lyapunov stability theory, we derive some simple sufficient conditions for the bipartite-tracking quasi-consensus under the assumption that the communication topology is structurally balanced. Furthermore, we estimate the region of attraction of the error system. Three simulation examples are also provided to show the effectiveness of the proposed protocols.

Adaptive Control for Uncertain Nonlinear Systems With Dynamic Full State Constraints: The SMDO Approach

This article focuses on the adaptive control issue for uncertain nonlinear systems with time-varying full-state constraints. First, a novel integral barrier Lyapunov functions (IBLFs)-based neural backstepping control approach is designed, which circumvents the trouble of conversion in the traditional used BLFs. And then, the sliding-mode disturbance observers (SMDOs) are established to deal with the immeasurable disturbances in each order of the state-constrained uncertain nonlinear systems. Besides, the dynamic threshold-based event-sampling mechanism is constructed to deal with the sparsity of resources and system controlling burden. Finally, according to the given design approach, an event-triggered adaptive controller is developed and ensures disturbance observation errors uniformly converge to the origin in finite time, and all the signals in the closed-loop system are semiglobally uniformly ultimately bounded. A developed numerical simulation case verifies the validity of the proposed approach.

Regional Load Frequency Control of BP-PI Wind Power Generation Based on Particle Swarm Optimization

The large-scale integration of wind turbines (WTs) in renewable power generation induces power oscillations, leading to frequency aberration due to power unbalance. Hence, in this paper, a secondary frequency control strategy called load frequency control (LFC) for power systems with wind turbine participation is proposed. Specifically, a backpropagation (BP)-trained neural network-based PI control approach is adopted to optimize the conventional PI controller to achieve better adaptiveness. The proposed controller was developed to realize the timely adjustment of PI parameters during unforeseen changes in system operation, to ensure the mutual coordination among wind turbine control circuits. In the meantime, the improved particle swarm optimization (IPSO) algorithm is utilized to adjust the initial neuron weights of the neural network, which can effectively improve the convergence of optimization. The simulation results demonstrate that the proposed IPSO-BP-PI controller performed evidently better than the conventional PI controller in the case of random load disturbance, with a significant reduction to near 10 s in regulation time and a final stable error of less than 10−3 for load frequency. Additionally, compared with the conventional PI controller counterpart, the frequency adjustment rate of the IPSO-BP-PI controller is significantly improved. Furthermore, it achieves higher control accuracy and robustness, demonstrating better integration of wind energy into traditional power systems.

PSO-based optimized neural network PID control approach for a four wheeled omnidirectional mobile robot

AbstractThe demand for automation using mobile robots has been increased dramatically in the last decade. Nowadays, mobile robots are used for various applications that are not attainable to humans. Omnidirectional mobile robots are one particular type of these mobile robots, which has been the center of attention for their maneuverability and ability to track complex trajectories with ease, unlike their differential type counterparts. However, one of the disadvantages of these robots is their complex dynamical model, which poses several challenges to their control approach. In this work, the modeling of a four-wheeled omnidirectional mobile robot is developed. Moreover, an intelligent Proportional Integral Derivative (PID) neural network control methodology is developed for trajectory tracking tasks, and Particle Swarm Optimization (PSO) algorithm is utilized to find optimized controller's weights. The simulation study is conducted using Simulink and Matlab package, and the results confirmed the accuracy of the proposed intelligent control method to perform trajectory tracking tasks.

NEURAL LEARNING CONTROL METHODOLOGY FOR PREDEFINED-TIME SYNCHRONIZATION OF UNKNOWN CHAOTIC SYSTEMS

This paper presents a method for achieving synchronization of chaotic systems with unknown dynamics, using a predefined-time neural learning control approach. The proposed method includes a control law for synchronization and a parameter updating law that are designed to ensure stability according to the predefined-time Lyapunov theory. The analysis of stability indicates that the synchronization errors using this approach converge to a small region around zero within the predefined time. The effectiveness of the proposed method is demonstrated through simulation examples.