DC microgrids have emerged as a highly efficient and reliable architecture for integrating renewable energy sources, energy storage systems, and modern electronic loads in applications ranging from data centres and electric vehicles to all-electric ships and more-electric aircraft. A critical challenge in these systems is the presence of Constant Power Loads (CPLs), which arise from tightly regulated power electronic converters. The inherent negative incremental impedance characteristic of CPLs degrades system damping and can lead to voltage instability and collapse. This paper provides a comprehensive review of the control strategies developed to mitigate CPL-induced instability. It systematically classifies and analyzes methods, ranging from conventional passive and linear active damping to advanced nonlinear techniques, including Sliding Mode Control (SMC), Backstepping, Passivity-Based Control (PBC), and Model Predictive Control (MPC). Furthermore, the review examines the latest adaptive and intelligent control strategies, including Reinforcement Learning and Neural Network-based controllers, which provide remarkable adaptability to uncertain and time-varying system conditions. A critical comparative analysis is presented, discussing the trade-offs in robustness, performance, computational cost, and implementation complexity. Finally, key research gaps are identified, and promising future directions—including hybrid control, large-signal stability guarantees, scalable distributed control, and Explainable AI—are discussed. This review serves as a valuable resource for researchers and engineers working towards the design of robust, efficient, and stable next-generation DC power systems.

This paper investigates the design of a robust controller for the trajectory tracking issue of an underactuated quadrotor unmanned aerial vehicle (UAV) subject to multiple disturbances. An anti-disturbance control framework is proposed by utilizing extended state observer (ESO) and neural network technology. Firstly, the dynamic model of the quadrotor UAV under wind and payload disturbance is established. To actively estimate the lumped disturbance of the UAV system, an ESO with only one parameter is introduced and the disturbances are transformed into the extended state of the UAV system for estimation. Secondly, an adaptive tracking controller that does not accurately obtain the dynamic model knowledge is constructed based on neural network method, where weights of the network can be automatically adjusted by the developed adaptive law. Then, finite-time convergency is analyzed for the ESO with only one parameter, and the Lyapunov criterion is adopted to verify the uniform ultimate boundedness of the UAV closed-loop system. Finally, various simulations under different scenarios are carried out to demonstrate the superiority and effectiveness of the proposed control strategy. For comparison, linear active disturbance rejection control (LADRC), sliding mode control (SMC), model-free based terminal SMC (MFTSMC), and adaptive fractional-order control (ADFOC) algorithms are introduced. Moreover, the physical experiment is given to validate the practicability of the proposed method.

This paper addresses the attitude tracking control problem for laterally symmetric vehicles during the boost phase under aerodynamic parameter variations and high-altitude wind disturbances. A neural disturbance observer-based nonsingular predefined-time sliding mode control scheme is proposed. First, a Lyapunov-based predefined-time stability criterion is established, which facilitates the design of an adaptive predefined-time observer using radial basis function neural networks. Without requiring prior knowledge of disturbance bounds, this observer ensures that disturbance estimation errors converge to a neighborhood of the origin within a predefined time parameter. Second, a novel nonsingular predefined-time sliding surface is constructed using hyperbolic tangent functions, leading to an integrated predefined-time sliding mode controller. The proposed scheme guarantees that the upper bound of the convergence time for initial attitude tracking errors is independent of the initial boost-phase states and can be arbitrarily predefined. Unlike conventional predefined-time control methods, the proposed approach eliminates controller singularity issues while avoiding the introduction of piecewise continuous functions or double-integral terms in either the sliding surface or the control law, thereby reducing structural complexity. Theoretical analysis confirms the boundedness of all closed-loop signals during attitude tracking. Numerical simulations demonstrate the effectiveness of the proposed control strategy under complex flight conditions.

Modulating inhibitory control in test-anxious individuals via tDCS: An ERP study.

Adaptive neural network control of manipulators with input deadband and field-of-view constraints

Fixed-Time Prescribed Performance Neural Fault-Tolerant Control of Euler–Lagrange Systems Under Unknown Bounded Initial Conditions

Dynamic self-triggered adaptive neural PI control for underactuated MASS with predefined performance

Prescribed performance synchronization of memristor-based chaotic systems with uncertainties via neural adaptive learning control strategy

Empowering phase change material thermodynamics via physics-consistent neural network-enabled advanced building control

Deep neural network-based adaptive supervisory control for strict-feedback nonlinear systems with sensor and actuator faults

Neural network control for mitigating actuator delay in ATR engines using predictive compensation and stability reward

Observer-based prescribed-time optimal neural consensus control for six-rotor UAVs: A novel actor-critic reinforcement learning strategy.

Adaptive neural network fault-tolerant control for stochastic nonlinear systems based on reinforcement learning

Evaluating cortical activity and balance performance in Alpine skiers: An fNIRS study.

To meet the requirements of precise speed profile tracking of urban rail transit system in complex environments and to reduce energy consumption, a back propagation (BP) neural network control strategy with partially updatable weights is proposed, it not only achieves better control performance but is also easy to deploy in large-scale industrial applications. Firstly, a train dynamic model is established, and the additional resistance encountered during train operation is considered to simulate complex operating conditions. Then, the BP neural network architecture is determined, the rules of each structural layer and the definition of weight parameters are included, and the algorithm’s adaptability to changes in model parameters and external disturbances is ensured. Finally, a simulation model is established for comparative studies, and the motor speed control experiment is conducted as an initial exploration of real train operation control. Results indicate that the BP neural network controller with partially adjustable weights exhibits high speed tracking accuracy and robustness.

The triceps surae, composed of the soleus (SOL) and medial (MG) and lateral (LG) gastrocnemii, are anatomically-derived synergists which act as a functional unit to plantarflex the ankle. However, anatomical differences suggest that each muscle is capable of generating distinct torques at the ankle, raising the possibility that each can be independently controlled to suit the needs of a given task. This possibility was explored by investigating the activation patterns of the triceps surae during two balance tasks that use different neuromechanical control strategies to maintain equilibrium. High-density surface EMG was recorded from the triceps surae of 14 healthy young adults during multiple trials of dual- and single-legged standing. Newly developed analyses examined how each muscle tuned its activity with center of pressure (COP) movement throughout 2-D space. During dual-legged standing, only the SOL and MG were active and both tuned their activity uniformly with anteroposterior COP movement. By contrast, during single-legged standing, each muscle showed robust activation and significantly different directional tuning, with the LG most active before medial COP movement, while SOL and MG were most active before lateral COP movement. Further analyses demonstrated the LG could be activated entirely independent of the SOL and MG, and vice versa, with independent activation of each muscle causing different angular deflections of the COP during single-, but not dual-legged standing. These observations reveal a sophisticated level of neural control, whereby the nervous system exploits subtle differences between highly similar muscles to tune stabilizing torques in a task-dependent manner.

Many aquatic animals, including larval zebrafish, exhibit intermittent locomotion, moving via discrete swimming bouts followed by passive glides rather than continuous movement. However, fundamental questions remain unresolved: What neural mechanisms drive this behavior, and what functional benefits does this behavior offer? Specifically, is intermittent swimming more energy efficient than continuous swimming, and, if so, by what mechanism? Live-animal experiments pose technical challenges, because observing or manipulating internal physiological states in freely swimming animals is difficult. Hence, we developed ZBot, a bioinspired robot that replicates the morphological features of larval zebrafish. Embedding a network model inspired by neural circuits and kinematic recordings of larval zebrafish, ZBot reproduces diverse swimming gaits of larval zebrafish bout-and-glide locomotion. By testing ZBot swimming in both turbulent and viscous flow regimes, we confirm that viscous flow markedly reduces traveled distance but minimally affects turning angles. We further tested ZBot in these regimes to analyze how key parameters (tail-beating frequency and amplitude) influence velocity and power use. Our results show that intermittent swimming lowers the energetic cost of transport across most achievable velocities in both flow regimes. Although prior work linked this efficiency to fluid dynamics, like reduced glide drag, we identify an extra mechanism: better actuator efficiency. Mechanistically, this benefit arises because intermittent locomotion shifts the robot's actuators to higher inherent efficiency. This work introduces a fishlike robot capable of biomimetic intermittent swimming-with demonstrated energy advantages at relevant speeds-and provides general insights into the factors shaping locomotor behavior and efficiency in aquatic animals.

With the development of aerospace technology, hypersonic flight vehicles are evolving towards larger size, lighter weight, and higher performance. Their cross-domain maneuverability and extreme flight environment led to the rigid–flexible coupling effect and became the core bottleneck restricting performance improvement, seriously affecting flight stability and control accuracy. This paper systematically reviews the research status in the field of control for high-speed rigid–flexible coupling aircraft and conducts a review focusing on two core aspects: dynamic modeling and control strategies. In terms of modeling, the modeling framework based on the average shafting, the nondeformed aircraft fixed-coordinate system, and the transient coordinate system is summarized. In addition, the dedicated modeling methods for key issues, such as elastic mode coupling and liquid sloshing in the fuel tank, are also presented. The research progress and challenges of multi-physical field (thermal–structure–control, fluid–structure–control) coupling modeling are analyzed. In terms of control strategies, the development and application of linear control, nonlinear control (robust control, sliding mode variable structure control), and intelligent control (model predictive control, neural network control, prescribed performance control) are elaborated. Meanwhile, it is pointed out that the current research has limitations, such as insufficient characterization of multi-physical field coupling, neglect of the closed-loop coupling characteristics of elastic vibration, and lack of adaptability to special working conditions. Finally, the relevant research directions are prospected according to the priority of “near-term engineering requirements–long-term frontier exploration”, providing Refs. for the breakthrough of the rigid–flexible coupling control technology of the new-generation high-speed aircraft.

Neural Observer-Based Iterative Learning Leader-Following Control for Multi-Agent Systems Subject to Unknown Dynamics and Multiple Faults

An adaptive control strategy is developed and analyzed for trajectory tracking of mechanical systems subject to simultaneous model uncertainties and full-state constraints. To overcome the significant hurdle of guaranteeing both transient and steady-state performance within a user-defined time, a novel predefined-time adaptive neural network (NN) control scheme is proposed. By integrating predefined-time stability theory with a nonlinear mapping framework, a control scheme is developed to rigorously enforce full-state constraints while achieving predefined-time convergence. Radial basis function neural networks (RBFNNs) are employed to approximate the unknown system dynamics, with adaptive laws designed for online learning. The nonlinear mapping is strategically incorporated to ensure that the full-state constraints are never violated throughout the entire operation. Furthermore, through Lyapunov stability theory, it is proved that all signals of the resulting closed-loop system are uniformly ultimately bounded, and most importantly, the trajectory tracking error converges to a small neighborhood of zero within a predefined time, which can be explicitly set regardless of initial conditions. Comparative simulation results on a representative mechanical system are provided to demonstrate the superiority of the proposed controller, showcasing its faster convergence, higher tracking accuracy, and guaranteed constraint satisfaction compared to conventional finite-time and adaptive NN control methods.