Traditional mathematical methods for calculating machining errors before production are often time-consuming. To solve this problem, we developed a data-driven intelligent method that learns from existing data to realize real-time error prediction. Our method achieves over 99 % prediction accuracy and runs significantly faster than conventional approaches, helping factories manufacture high-precision, high-quality parts more efficiently.

Speed skating training demands precise movement, but traditional coaching relies on subjective experience and existing tools are bulky or inflexible. We created a flexible cable-driven robot with enhanced control, cutting tracking errors significantly to enable precise training and inform smart sports equipment development.

Self-balancing wheelchairs can help people move in tight spaces, but they must stay upright when starting from a large tilt, carrying different users, or facing sudden pushes. We developed and tested a two-stage control approach that first brings the chair back safely from larger tilts and then keeps it steady near upright. Simulations and prototype tests showed faster recovery, better stability under disturbances, and stronger tolerance to user-weight changes, supporting safer designs.

This study uses a relatively novel optimization system to optimize the structure of a self-excited oscillating nozzle. The study identifies inlet radius, lower-nozzle diameter, and cavity length as key variables (combined impact >87 %); achieves a 77.39 % improvement in overall cleaning efficiency through global optimization; and explains the flow field evolution mechanism.

Aiming to address the problems of the large time delay and low compliance of the system caused by the slow speed of motion intention recognition based on the force signal, this paper integrates the force signal and the surface electromyography (sEMG) signal as the input of the elbow–wrist rehabilitation robot, thereby achieving a good balance between fast response and force compliance in the control system.

Modern supply chains must coordinate customer orders, factory choices, and delivery routes while conditions change quickly. This study developed a learning-based scheduling method that breaks the whole task into connected decisions and trains them step by step. Tests in simulated networks showed faster learning, shorter completion times, and better performance in unfamiliar settings. The results suggest a practical way to improve coordination in production and delivery systems.

This study proposes a novel dual-robot system controlled by a primary–secondary strategy for accurately aligning large, flexible aircraft parts in tight spaces. The primary robot ensures precise positioning, while the secondary robot actively senses and cancels out harmful internal forces, preventing part deformation. Our simulated results show that this method achieves high alignment accuracy and reduces internal forces by over 90.03 %, offering a safe and efficient automated solution for aircraft assembly.

We developed an origami-inspired robotic gripper to solve the challenge of capturing irregular space debris. The design combines compact foldability for launch with controlled, flexible bending to adapt to different shapes. We built and tested a prototype, showing it can accurately position itself, securely wrap around various objects, and hold payloads reliably. These results confirm the gripper’s effectiveness, offering a promising new solution for safe space debris capture.

Switch rails are essential to railway turnouts, but machining burrs can cause cracks, shorten service life, and affect safety. This study developed a robot-assisted milling method that adjusts tool motion and cutting force in real time along long, complex rail edges. Simulations and experiments showed reduced force fluctuations, improved force tracking, and good surface quality. The results support safer, more consistent, and automated switch rail deburring.

Although the optimal design of various marine equipment pieces has been widely studied, the optimization of an important device – the submarine cable tray – has long been neglected. To address this issue, this study specifically focused on the structural optimization design of large-scale (400 t class) submarine cable trays.

Surface roughness has the greatest impact on the erosion wear of the rotor blade, followed by the stator blade, with the least on the guide blade. As surface roughness increases, the maximum wear rate rises and the concentrated erosion wear area expands, while its location does not shift significantly. The results can provide a basis for the erosion wear assessment of compressor blades at different service stages.  

The error model of the 5-degree-of-freedom hybrid perfusion manipulator established by the product of exponentials formula is more comprehensive and effective. Compared with the traditional inverse kinematic method, the mean pose errors of the moving platform after kinematic calibration based on the product of the exponentials method are reduced by 89.04 % and 63.79 %, respectively. The proposed modeling method is applicable to error modeling and analysis of most parallel mechanisms. 

We studied how to locate damage in metal plates when only a few sensor measurements are available. Our method first combines the limited signals in a more reliable way and then sharpens the damage image with a guided learning step. Tests using laboratory measurements and supporting simulated data showed clearer images and more accurate locations. This could make structural inspection more reliable when data are scarce.

Helicopter engines often generate rapidly changing torque under different flight conditions, which can increase vibration in the transmission system and affect reliability. This study examines how these variations influence system behavior in typical scenarios. The results show that the rate of torque change, rather than its magnitude, plays a key role. Faster changes significantly amplify vibration in critical components, providing guidance for improving system safety and durability.

This study examines deep-sea gear lubrication challenges under extreme conditions, including high pressure, with a focus on EHL (elasto-hydrodynamic lubrication) theory and interface texturing advances. Critical gaps remain in multi-physics coupling and synergistic texture-coating interactions. The paper proposes a research roadmap integrating multi-scale modelling, surface engineering optimization, experimental validation, and industrial implementation to enable robust deep-sea transmission systems.

The rod-type stirred mill is the core equipment used in the grinding of potassium feldspar. However, the grinding process involves numerous parameters that influence performance, along with various evaluation metrics and prolonged single-cycle durations – collectively making it difficult to identify optimal operating conditions. This study investigates the effects of rotational speed, grinding media size, and bar spacing on milling performance. 

This paper proposes a novel 4-degree-of-freedom parallel mechanism. Its degrees of freedom are verified by screw theory. Inverse position, velocity, and acceleration models are established. The position workspace is obtained, and singular configurations are identified. The stiffness index distribution in the workspace is visualized. The inverse dynamic model is derived using the Lagrangian method. Kinematic and dynamic simulations in Adams verify the correctness of the theoretical model.

This work presents a robotic chain that can smoothly shift from flexible to rigid using air pressure. We developed a new method that applies pressure to compact internal fibers, allowing the chain to become significantly stiffer than previous designs. Through theoretical modeling and physical testing, we demonstrated reliable and wide-ranging stiffness control. This advancement enables the creation of machines that are both safe for interaction and capable of performing demanding tasks.