Bobo Helian

Electrohydraulic actuators (EHAs) are critical in applications demanding compact designs, high power density, and precise motion control. However, their nonlinear dynamics and inherent uncertainties pose considerable control challenges. This study develops a reinforcement learning (RL)-based control framework, integrating an actor–critic algorithm [deep deterministic policy gradient (DDPG)] and a novel reward-shaping method to address these challenges without requiring prior expert knowledge. The proposed approach is validated on a heavy-duty EHA-driven inverted pendulum testbench, as a benchmark system for nonlinear and unstable dynamics. Experimental results demonstrate the RL controller’s effectiveness in achieving the dual-control goal: swing-up and balancing of the EHA-driven pendulum. Furthermore, a comparative analysis with the classical linear quadratic regulator (LQR) highlights the strengths and limitations between RL-based control and model-based control. This study serves as fundamental research, offering practical and theoretical contributions to the application of RL in advanced motion control for EHAs and other complex systems.

Electro-hydraulic systems have been widely applied in industrial applications due to their excellent robustness and high power to weight ratio. In scenarios requiring large driving forces and high-power output, traditional single-actuator methods are inadequate, making multiactuator systems, such as dual-cylinder setups, essential for effective load handling. Achieving high-precision synchronized motion in such systems is critical but challenging due to internal force coupling caused by inertial eccentric loads and deflection torques, as well as dynamic discrepancies among actuators. To address these challenges, this study proposes a dual-cylinder synchronization control strategy based on hydraulic thrust allocation. By analyzing and modeling the system's rotational dynamics, a thrust allocation strategy is developed to reduce rotational effects, mitigate internal force coupling, and enhance synchronization accuracy. In addition, an adaptive robust control adaptive robust control (ARC) strategy compensates for variations in actuator dynamics, ensuring precise synchronization under nonlinear and uncertain conditions. To validate the superiority of the proposed algorithm, experiments were conducted under two challenging operating conditions. The results demonstrate that the algorithm effectively handles internal force coupling and different actuator dynamics, significantly improving synchronization accuracy.

Independent metering systems (IMSs) have shown superior performance in hydraulic industrial applications because of the high power density, large force output, and high control freedom. However, the presence of mechanical safety structures, such as relief valves and replenishing valves, introduces complex constraints that significantly limit performance improvements of the IMS. If the constraints are violated, then some undesirable phenomena, such as cavitation, overflow, and pressure surge, will occur to make the system lose accuracy and stability. In this article, a double-loop control strategy, which combines theouter loop constrained trajectory planner and the inner loop adaptive robust motion controller (ARC), is developed to realize the constrained motion control of the IMS. In the outer loop, both kinematic and dynamic constraints are transformed into time-varying constraints on the replanned trajectory, which are calculated based on the state feedback online to optimize the planner's performance. A time-optimal motion trajectory is planned using a third-order nonlinear filter, ensuring convergence to the original reference while meeting the assigned constraints. In the inner loop, the high-performance ARC controller is designed to make the IMS track the replanned trajectory despite uncertainties and nonlinearities. To demonstrate the constrained performance of the proposed double-loop control framework, experiments with different control strategies are conducted on an IMS test bench.

Independent metering systems (IMSs) have been applied and researched in mobile machinery due to their advantages of reduced throttling energy losses and remarkable advances under negative load through decoupling actuator throttling control. Although IMSs have the control flexibility to deal with negative workloads, the control performance of the IMSs is challenged by uncertain loads in mobile operations, limiting the control accuracy. In addition, if the motion reference is improperly specified and exceeds the constraints, the pressure of the actuator may oscillate significantly and potentially result in control instability. In this study, a constrained adaptive robust control strategy is proposed for an IMS. An adaptive robust control strategy is designed for the meter-in and meter-out throttling to achieve precision motion control despite the nonlinearities and uncertainties of the electro-hydraulic IMS. The value of the uncertain workload is estimated in real-time and utilized in the model-based controller to improve control accuracy. In addition, a constrained trajectory planning approach is presented to handle out-of-constraint references and ensure motion tracking performance. This effectively prevents pressure fluctuations caused by the inappropriate reference.

The motion control technology of electro-hydraulic actuators has great significance in industrial applications. Constraints significantly limit the motion control performance of actuator motion control, in addition to the inherent nonlinearities and uncertainties of the electro-hydraulic systems. The constraints comprise kinematic and dynamic constraints, and they can be time-varying owing to variations in the system. If the constraints are not fulfilled, the control accuracy may be adversely affected, for instance by actuator vibration, cavitation, or even instability. This article proposes a constrained motion control strategy for a variable-speed pump-driven hydraulic actuator. To robustly track a desired trajectory under constraints, the control strategy combines a nonlinear filter-type trajectory planning strategy and an adaptive robust motion controller. The trajectory planning strategy is designed by considering dynamic and kinematic constraints of the electro-hydraulic system, and it synthesizes a trajectory that reaches the given reference in minimum time while fulfilling these multiple constraints. Meanwhile, the adaptive robust motion controller tracks the synthesized trajectory with guaranteed control accuracy in the presence of inherent nonlinearities of the electro-hydraulic actuator. In addition, the assignments of the multiple constraints are adjusted in real time, which further optimize the constrained motion control performance. Comparative experiments with various given references were conducted to verify the advantages of the proposed constrained control strategy.

This article proposes an integrated two-loop motion control strategy of an electro-hydraulic actuator, in which the cylinder actuator is driven by a variable speed pump to track a desired trajectory. The control strategy combines constrained trajectory planning (outer loop) with nonlinear motion control (inner loop) to achieve accurate trajectory tracking of electro-hydraulic actuators under constraints. A nonlinear filter-type trajectory planner is utilized as the outer loop to synthesize the optimal trajectory, reaching the desired reference with the minimum time while fulfilling the constraints. A full-state constraints assignment approach is proposed, including motion and pressure state constraints. Furthermore, to accurately track the synthesized trajectory of the outer loop, a model-based adaptive robust backstepping motion controller is designed as the inner loop, which can realize guaranteed robustness and high accuracy of the trajectory tracking in the presence of dynamic nonlinearities and parametric uncertainties of the electro-hydraulic actuator. Experiments with contrast control strategies and practical trajectories are conducted, which comprehensively verify the advantages of the proposed integrated two-loop control strategy.