Neural network-based energy-input shaping combined control for anti-sway and positioning of crane systems under non-zero initial conditions

Variable-Weight NMPC-Based Trajectory Tracking and Anti-Sway Control for Hydraulic Luffing Cranes

In driver-operated hydraulic luffing crane tasks, achieving precise motion control and effective load stabilization is essential for safe and efficient operation. This study develops a variable-weight nonlinear model predictive control (VW-NMPC) approach for driver-in-the-loop trajectory tracking and anti-sway regulation. A coupled nonlinear dynamic model integrating hydraulic, luffing, and payload dynamics is established. A virtual reference feedback mechanism is introduced to reduce feedback delays and suppress instability arising from strong nonlinearities and structural coupling. A state-dependent weighting mechanism dynamically adjusts control priorities according to driver commands and operating conditions, enabling balanced optimization in human–machine cooperation. Hardware-in-the-loop experiments show a velocity deviation of less than $2.53 \times 10 ^{-2}$ m/s and payload swing angles within $2.95 \times 10 ^{-2}$ rad under typical working scenarios. The proposed method significantly reduces operator dependence and enhances robustness, safety, and intelligence in crane operations across varying environments. These results provide a solid theoretical and practical foundation for next-generation intelligent crane control systems. Note to Practitioners—Operators of hydraulic luffing cranes often struggle to keep the boom moving smoothly while controlling payload sway. These challenges become more pronounced when the hydraulic system shows strong interaction between the structure, the actuators, and changing loads. This work is motivated by the need for a control approach that assists operators directly, improves motion stability, and reduces dependence on manual skill. The proposed method introduces two ideas that can be applied in practice. The first is a virtual feedback signal that helps the crane respond more quickly to operator input. It reduces the delay and instability that often appear in coupled hydraulic and mechanical systems and helps prevent oscillations that are difficult to manage by hand. The second idea is a weighting logic that adjusts control priorities based on the operator’s commands. As working conditions change, the controller automatically balances between accurate motion tracking and effective sway suppression. This improves responsiveness, limits overshoot, and helps maintain stable operation during demanding tasks. Hardware-in-the-loop tests show that the approach can keep speed variations small and reduce payload sway. This lowers operator workload and improves overall safety. The method, however, relies on both a reasonably accurate system model and real-time computation. Future work may simplify the algorithm or add online adaptation to broaden its use. The same principles may also benefit other hydraulic machines that require coordinated motion and stabilization, such as excavators, aerial platforms, or telescopic handlers.

A novel robust and fast control algorithm for wireless power transfer chargers based on the sliding-mode theory and fixed-time reaching process

Adaptive sliding mode strategy: A cross-coupled synchronization control method for improving the dynamic accuracy of dual-drive gantry systems under spatial perturbations

Dual-drive feed systems are widely applied in high-end manufacturing. However, their synchronization accuracy is severely limited by nonlinearities, including weak mechanical coupling, nonlinear friction, and time-varying inertia induced by center-of-gravity (CoG) shifts. To address these issues, this paper proposes a finite-time cross-coupled synchronization control method using a linear extended state observer (LESO) and adaptive nonsingular terminal sliding mode control (ANTSMC). A nonlinear model incorporating CoG-dependent inertia asymmetry, elastic coupling, and nonlinear friction is established, and a cross-coupled control (CCC) architecture is introduced to formulate the generalized coupling error. Next, a LESO is designed to estimate and feedforward-compensate for total disturbances—including CoG shifts and external loads—in real time. Combined with the ANTSMC scheme, the generalized coupling error, together with the tracking and synchronization errors, is driven into a prescribed neighborhood within a finite time. Furthermore, an adaptive switching gain law with a dead-zone constraint is developed. This mechanism dynamically adjusts the switching gain to handle asymmetric impacts while reducing unnecessary steady-state switching activity and control-input chattering. Finally, simulations and experiments on a dual-drive gantry system validate the proposed strategy. The results demonstrate that the LESO-ANTSMC scheme significantly suppresses complex time-varying disturbances, substantially improving dynamic synchronization and tracking precision.

Adaptive control strategy for VSG virtual inertia based on RBF neural network

This paper presents a hierarchical control scheme for virtual synchronous generators (VSGs) to mitigate power oscillations and steady-state errors induced by power command variations and grid frequency fluctuations. Unlike conventional adaptive methods that operate at the parameter level, the proposed architecture addresses the inherent structural coupling between damping and droop characteristics from a control-structure perspective. It integrates two complementary modules: a lower-level differential feedforward compensation (DFC) loop that restructures the active-power control channel to achieve structural decoupling between damping and droop, thereby eliminating steady-state deviations under frequency disturbances; and an upper-level RBF neural network that uses frequency deviation and its rate of change to dynamically regulate the virtual inertia J-the sole optimized parameter-reducing the control dimension while enhancing transient response and frequency stability. The uniform ultimate boundedness of the closed-loop system is proved via Lyapunov theory. The strategy is validated through four typical disturbance scenarios via Starsim hardware-in-the-loop experiments, along with comprehensive sensitivity analyses covering system parameters (short-circuit ratio from 1 to 5) and controller parameters (DFC coefficient and filter time constant deviations), as well as RBF initialization uncertainties. Results demonstrate that the DFC-RBF-VSG achieves zero overshoot, settling time within 0.1 s, zero steady-state error under frequency disturbances, total harmonic distortion (THD) reduced to 2.44%–2.95%, and peak inrush current limited within 300 A, consistently outperforming conventional Fixed-VSG, linear-adaptive VSG (Linear-VSG), fuzzy-based adaptive VSG (Fuzzy-VSG), and feedback-compensated VSG (FBC-VSG). The method strikes a favorable balance among dynamic responsiveness, steady-state precision, and robustness, offering an effective solution for high-penetration renewable energy systems.

Simulation and Real‐Time Implementation for Power Quality Enhancement Systems Using Adaptive Neural Network Strategy

A nested terminal sliding mode control scheme based on hippocampal neural network to overcome the performance limitations of existing APF control methods and reduces the total harmonic distortion of the grid source current to 1.29% in simulation and 3.03% in experiment.

Improved sliding mode control of direct-drive electro-hydrostatic actuator based on adaptive neural network

Aiming at the problem that various parameter uncertainties and disturbances degrade the tracking control performance in the direct-drive electro-hydrostatic actuator, an improved sliding mode control based on adaptive neural network is proposed in this paper. First, a new sliding mode reaching law is designed. On the basis of the exponential reaching law, a variable gain term based on system state variables, a piecewise function with power terms of the sliding surface and a new switching function are introduced, which improves the response speed, enhances the anti-disturbance capability and suppresses chattering. Secondly, a new adaptive radial basis function neural network observer based on the minimum learning parameter is designed. The outputs of the high-gain observer are taken as the inputs of the radial basis function neural network. An adaptive learning rate dynamically varying with the observation error is developed and incorporated into the weight updating law of the neural network, which improves the real-time nonlinear approximation accuracy for unknown disturbances. The stability was proved through the Lyapunov function. The results demonstrate that the proposed control method outperforms the other control methods in terms of both response speed and control accuracy.