This study proposed an analytical model of a fixed-rotation constrained-arc segment. Based on this, a novel two-stage constant-torque bending hinge is designed, and an optimization study is carried out. Finally, the feasibility of the design scheme is verified by theoretical analysis, finite-element analysis, and experiments. The new bending hinge provides a proficient solution for the design of fixtures, joint rehabilitation devices, and human activity assistive devices.

The fuzzy proportional–integral–derivative controller optimized by the particle swarm optimization algorithm eliminates steady-state error, improves response speed, and enhances both system adaptability and disturbance resistance. This approach effectively addresses the inherent uncertainties and nonlinear variations in bolt tightening processes. The average deviation between the tightening torque and target torque measures 0.108 N m, achieving a control accuracy of 0.9%.

In this paper, a micro-textured coated tool is proposed to improve the cutting performance of the tool by utilizing the synergistic effect of the micro-texture and coating material, and it is found that the coated tool with the micro-texture on its front and back face induces a reduction in the cutting force by 21.57 % and a reduction in the cutting temperature by 7.56 %, which effectively facilitates chip outflow and avoids the buildup of cutting heat on the tool surface.

In this paper, an entire process of laser cladding repair of a damaged polycrystalline diamond compact (PDC) bit of high value based on a dual-robot system is proposed.

To solve the flutter identification problem in the machining process of thin-walled parts, an online monitoring method based on continuous wavelet transform (CWT) and convolutional neural network–vision transformer (CNN-ViT) is proposed. First, the CNN model is utilized to extract local features from the image obtained after CWT. Then, the self-attention mechanism of the ViT model is employed to capture the global features of the feature map, and, finally, the classification results are output.

This article presents novel rehabilitation training by combining virtual reality technology and a rehabilitation robot. The goal is to provide multiple-information feedback for activities of daily living training. The rehabilitation robot receives data from virtual scenes to provide force feedback, creating a sense of presence. This approach is expected to help patients in the later stages of a stroke to improve their muscle strength and regain their upper-limb motor function.

This paper presents a novel 6-degree-of-freedom (6-DOF) compliant parallel manipulator, designed with a 6-PSS configuration and leaf spring compliant joints, together with manufacture error identification techniques. These innovations enhance motion accuracy, range and dynamic performance. This manipulator holds promise for applications like optical guidance and chip packaging.

This paper focuses on vibration suppression and trajectory planning for a two-link flexible manipulator and proposes a novel control method that integrates a modified adaptive particle swarm optimization algorithm (MAPSO) with fuzzy proportional–derivative (PD) control to achieve effective trajectory tracking.

We developed an advanced control system to enhance the comfort of vehicle seats by reducing vibrations. This innovative system combines an adaptive neuro-fuzzy inference system (ANFIS) and active disturbance rejection control (ADRC) to effectively manage the magnetorheological (MR) damper. Our research showed significant improvements in reducing seat vibrations. Moreover, the system's performance has been demonstrated to exceed that of conventional controls.

This paper develops a 4SRRR quadruped wall-climbing robot for demanding on-site work in shipyards and steel-structure manufacturing. A dynamic analytical model is established, replacing Euler–Bernoulli beam elements with Timoshenko beam elements to analyze natural frequencies. Results show that with single-element rods, the error in the first three natural frequencies is under 3.5 %. These findings validate the model's accuracy and support real-world applications. 

A trajectory prediction model based on Transfomer has been proposed to address the issue of long-term prediction accuracy in complex traffic environments. Optimizing multi-head attention based on knowledge of the scene context and vehicle position generates interactions between maps and agents, as well as between agents themselves. Its effectiveness has been evaluated on the basis of the outdoor dataset, and higher precision was achieved.