The automation and intelligence development of heavy-duty mobile machines and industrial equipment require the accurate control of electrical-hydraulic valve-controlled system (EHVS). This article presented a generic reinforcement learning with predictive target information control (RLPC) method for EHVS to improve the control accuracy, in which a distributional soft actor-critic (DSAC) iteration frame was established. First, a dynamic model considering nonlinearity, saturation, and uncertainty from a time-varying system perspective was established and validated through tests under typical conditions. Then the model-free RLPC method was designed for EHVS. As the baseline, the classical proportional-integral-derivative (PID) and an adaptive PID (APID) with RL-tuning were designed for comparison purposes. Finally, the corresponding iteration frame was established to improve the performance of RL-related works in the designed control methods with DSAC. The comparison results during typical operations show that the proposed RLPC method can handle dynamic response and steady errors better at different states of the system and actuator. The effects of the predictive horizon on control performance were also revealed. The stability of the method was also validated with a designed instantiating EHVS, specifically a hydraulic inverted pendulum system. The performance of the proposed methods was quantitatively analyzed with the normalizing performance indicator ρ. The mean value of the indicator was about 0.0028, which is lower than the first two methods and the existing control method for EHVS.

Articulated steering vehicles (ASVs), with brilliant maneuverability and efficiency, are being widely applied in mining, construction, agriculture, and forestry. However, their special structures result in them having complex dynamic characteristics, but there are no reliable models for further research. This study established a simulation platform with the dynamic model of ASVs, where the subsystems of the power train, steering systems, tires, and frames were also included. The dynamic model was validated with field test data of typical working cycles, in which the focus was on longitudinal and lateral motions and the characteristics of steering and power train systems. Then, the distribution of hydraulic and drive power was revealed using the simulation platform and test data. For a load–haul–dump (LHD) vehicle with a 6 m³ capacity, the maximum power of the system was about 289 kW; the power of the motor accounted for the majority of the power at the beginning stage of loading, being about 74%, and then the hydraulic power dominated in the later stage of loading. During the transport stage, the power of the motor accounted for about 79% of the total power. Finally, the influence of the dynamic parameters on lateral and longitudinal motions was analyzed based on the validated platform.

In order to recover and utilize the potential energy of mining trucks efficiently, this paper proposes a nested optimization method of a novel energy storage system. By analyzing the multi-objective optimization problem of the oil-circulating hydro-pneumatic energy storage system, a nested optimization method based on the advanced adaptive Metamodel-based global optimization algorithm is carried out. Research shows that this method only requires a short time to solve the complex nonlinear hybrid optimization problem and achieves better results. The optimized energy storage system has higher system efficiency, energy density, and volume utilization rate, thus obtaining a smaller system volume and weight. Verified by the bench experiment of its powertrain, the hydro-pneumatic hybrid mining truck with the optimized energy storage system significantly reduces its fuel consumption and CO₂ emission. Thus, it lays the foundation for the practical application of hydro-pneumatic hybrid mining trucks.

Articulated steering vehicles (ASV) are widely used in many industries for their high efficiency and excellent maneuverability. The autonomous driving and intelligent control of ASV are extremely critical owing to the operation characteristics. As a very important parameter, the tire-road friction coefficient (TRFC) determines the extreme tire force directly in the process of intelligent control. However, it cannot be obtained with the existing methods for the harsh environment and special structure of ASV. This paper proposed a two-layer model-based method of tire-road friction coefficient estimation for ASV. The dynamic models of ASV in the XY plane, including the longitudinal and lateral models of frames, tire forces, and steering system models, are established first. The dynamic models are embedded into the upper layer with a Kalman filter (KF) to estimate the tire forces in longitudinal and lateral directions. During the process, some self-contained sensors, including the state sensors of frames and steering system, are used to provide the observation data. In the lower layer, a recursive least square (RLS) method with a forgetting factor is used to obtain the TRFC and tire stiffness parameters with the aid of the tire model. The simulation and field test are carried out to validate the method under comprehensive conditions, in which different steering commands, velocities, and roads are included. The simulation and field test results show that the forgetting factor has a significant influence on the convergence and robustness of the proposed method. The forgetting factor τ = 0.95 is used in the field test, the estimation result of dry concrete road friction coefficient is around 0.83. The results indicated that the proposed method can obtain the TRFC and tire parameters dynamically for ASVs.

Hydraulic vibratory hammer is a key equipment during piling process, and mechanical, hydraulic part of the hammer and workload are coupled with each other during operation. The vibration performance depends on the design parameters and the driving system. In order to investigate the vibration performance, a coupled dynamic model is established for hydraulic vibratory hammer, in which the mechanical model of hammer, hydraulic model for driving, and the model of workload are included. The filed test was carried out to validate the dynamic model under idle and operating conditions. Pressure and flow of the hydraulic driving system and acceleration of the mechanical part were obtained during different test conditions. The results of test and simulation were analyzed in time and frequency domain to validate the coupled dynamic model. Then, effects of different eccentric block parameters on the vibration performance were investigated based on the validated model, including radius, thickness, and angle of the eccentric block. Further the design parameters of optimal vibration performance of the hammer are obtained under the constraints of hammer structure, in which the angle is 90°, thickness is 190 mm, and radius is 175 mm.Article Highlights We established a coupled dynamic model of the hydraulic vibratory hammer, including the mechanical model of hammer, hydraulic model for driving, and the simplified model of workload.; The field test is proceeded to validate the model under idle and operating condition; the dynamic response of the mechanical part and hydraulic driving part is analyzed in time and frequency domain; The performance of the hammer is analyzed with the coupled dynamic model, in which better performance of the hammer is obtained. The model-based method also provides a rapid and economical solution for the performance optimization of the hammer.

The energy storage system of electric-drive heavy mining trucks takes on a critical significance in the characteristics including excellent load capacity, economy, and high efficiency. However, the existing battery-based system does not apply to harsh cold environments, which is the common working condition for the above trucks. A type of cycle hydro-pneumatic energy storage system for the trucks was proposed in this study. The dynamic model of the system, including the dynamic and thermodynamic models of hydraulic and pneumatic parts, was built to analyze the performance of the system. Subsequently, the thermodynamic characteristics were clarified during the energy storage and released through the real test condition-based simulation. The power and energy performances of the system were studied in practice based on the above characteristics. The analysis of the results showed that the system reduced 22.03% driving power at the optimal braking energy recovery rate, the energy density was nearly 12.6 MJ/m³, the maximum input power was higher than 230 kW, and the cycle efficiency was about 40.6%. The results of this study will be conducive to the application of the hydro-pneumatic energy storage system for the electric-drive mining trucks and reducing the resulting carbon emission.