A hydraulic drive-based self-propelled photovoltaic panel cleaning robot was developed to tackle the challenges of harsh environmental conditions, difficult roads, and incomplete cleaning of dust particles on the photovoltaic panel surface in photovoltaic power plants. The robot has the characteristics of the crawler wheel drive, rear-wheel-independent turning and three-point-independent suspension design, which makes it adhere to the walking requirements of complex environmental terrains, more flexible in turning and automatically levelling so that the stability of the boom mechanism during walking can be ensured. The kinematics model of the upper arm structure equipped with the end cleaning device was built, and the optimized Circle chaotic map and nonlinear weight factor were introduced to enhance the search ability and convergence speed of the sparrow algorithm. Furthermore, the boom running track was optimized in combination with the seven-order non-uniform B-spline curve. Through optimization, the running time of the boom was reduced by 18.7%, and the cleaning efficiency of photovoltaic panel surface was increased. The effectiveness of self-propelled photovoltaic panel cleaning robot cleaning and the reliability of time-optimal trajectory planning were confirmed through simulation and experiment.

As a representative of multi-functional engineering machinery, the excavator is irreplaceable in the field of engineering construction. To autonomously control the excavator bucket, it is essential to control the position of the bucket hydraulic cylinder. As a consequence of the problem of position tracking control spawned from external disturbance and other factors in the self-mining servo system of excavators, a strategy of sliding mode backstepping control based on the particle swarm optimization algorithm and neural network disturbance observer (PSO-NNDO-SMBC) was recommended accordingly. Meanwhile, the complex disturbance was estimated online and compensated for by the system control input by the universal approximation property of the neural network disturbance observer (NNDO). Afterwards, the uncertainty of control parameters was optimized by the particle swarm optimization algorithm (PSO) and was fed back to the controller parameter input end. Afterwards, a co-simulation model of MATLAB/Simulink (MATLAB2023b) and AMESim (Simcenter Amesim 2304) was established for simulation analysis, and a test bench was set up for comparison and verification. As proven by the experimental results, PSO-NNDO-SMBC possessed strong anti-interference ability. In contrast to the sliding mode backstepping control based on the particle swarm optimization algorithm (PSO-SMBC), the maximum displacement tracking error was lowered by 50.5%. Furthermore, in comparison with the Proportional-Integral-Derivative (PID), the maximum displacement tracking error was decreased by 75.2%, which tremendously optimized the control accuracy of excavator bucket displacement tracking.

Three-wheeled agricultural robots possess the advantages of high flexibility, strong maneuverability, and low cost. They can adapt to various complex terrains and operational environments, making them highly valuable in the fields of crop planting, harvesting, irrigation, and more. However, the horizontal stability of the three-wheeled agricultural robot chassis is compromised when working in harsh terrain, significantly impacting the overall operational quality and safety. To address this issue, this study designed a leveling system based on active suspension and proposed a stepwise leveling method based on an adaptive dual-loop composite control strategy (ADLCCS-SLM). Firstly, in the overall control of the three-wheeled chassis, a stepwise leveling method (SLM) was introduced. This method allows for rapid leveling by incrementally adjusting one or two suspensions, effectively avoiding the complex interactions between suspension components encountered in traditional methods involving the simultaneous linkage of three suspensions. Next, in terms of suspension actuator control, an adaptive dual-loop composite control strategy (ADLCCS) was proposed. This strategy employs a dual-loop composite control both internally and externally and utilizes an improved adaptive genetic algorithm to adjust critical control parameters. This adaptation optimizes the chassis leveling performance across various road conditions. Finally, the effectiveness of the proposed ADLCCS-SLM was validated through simulation and experimental testing. The test results showed that the control effect of the proposed method was significant. Compared to the traditional multi-suspension linkage leveling method based on PID, the peak values of pitch angle and roll angle were reduced by 31.8% and 33.3%, respectively.

In this study, to address the issues of tooth tip operation discontinuity and jitter during autonomous excavator operation, a multi-segment mixed interpolation method utilizing different higher-order polynomials has been proposed. This approach is designed to optimize the tooth tip trajectory of the excavator under multiple constraints, resulting in a smoother trajectory. Specifically, the single-bucket excavator was chosen as the research object, and three different high-order mixed polynomials were utilized to interpolate the trajectory of the digging discrete points. Through a comparative analysis under multiple constraints, this study explored and analyzed the joint angle, angular velocity, and angular acceleration curves of each excavator’s joint. An experimental platform was established to investigate the hydraulic system of an excavator, and the optimal trajectory was controlled using a high-order mixed polynomial interpolation. The results of this study demonstrate that the tracking accuracy of the excavator’s actuator under the optimal interpolation strategy is high, with a maximum displacement deviation of ±3 mm. Additionally, during operation, the excavator manipulator runs smoothly and continuously with minimal flexible impact and vibration.

The independent metering system used in the combination of traditional cartridge proportional valves employs an excessive number of components, which increases the complexity of the control strategy. To address this problem, a novel independent metering system based on pilot hydraulic control was developed. Following the pressure and flow requirements, the structure and valve body size of the two spools were designed. The effect of the parameter change in the control valve on the dynamic response characteristics of the main spool was investigated by simulation. A control strategy was developed based on load force direction prediction and two-chamber pressure switching to verify the feasibility of working mode switching during load direction change. As indicated by the results, compared with the mode switching control strategy of the traditional independent metering system, the proposed control strategy could effectively reduce the number of mode switching and ensure the continuity of the actuator operation. Compared with the traditional load-sensitive valve control system, the proposed pilot-controlled independent metering system achieved an average energy-saving efficiency of 47.27%. This study provides technical reference for the low energy consumption, high efficiency, and sustainable development of hydraulic systems.

Laser vision seam tracking enhances robotic welding by enabling external information acquisition, thus improving the overall intelligence of the welding process. However, camera images captured during welding often suffer from distortion due to strong noises, including arcs, splashes, and smoke, which adversely affect the accuracy and robustness of feature point detection. To mitigate these issues, we propose a feature point extraction algorithm tailored for weld images, utilizing an improved Deeplabv3+ semantic segmentation network combined with EfficientDet. By replacing Deeplabv3+’s backbone with MobileNetV2, we enhance prediction efficiency. The DenseASPP structure and attention mechanism are implemented to focus on laser stripe edge extraction, resulting in cleaner laser stripe images and minimizing noise interference. Subsequently, EfficientDet extracts feature point positions from these cleaned images. Experimental results demonstrate that, across four typical weld types, the average feature point extraction error is maintained below 1 pixel, with over 99% of errors falling below 3 pixels, indicating both high detection accuracy and reliability.