This study introduces an AI model to reconstruct oil well pump performance charts. By analyzing pump data, it predicts load patterns, helping engineers detect issues early and improve efficiency. Using advanced learning with automated parameter optimization, it outperforms traditional methods and supports safer, more efficient well operations.

Current methods for analyzing three-dimensional points often fail to capture complex shapes because they scan in fixed directions. We introduce Group-wise Affine-Perturbed Serialization to solve this. Our method scans data along diverse, angled paths simultaneously to better capture geometry. This approach outperforms existing technologies in terms of accuracy without adding computational delay. It enables computers to understand real-world environments more precisely and efficiently. 

This study develops a digital-twin framework for real-time structural stress monitoring of crane structures. Integrating finite-element analysis with a radial basis function surrogate model, it enables dynamic stress prediction and visualization. Experimental results show an average prediction error of 8.29% compared to simulations and 9.98% against measured data, providing a reliable technical tool for structural health monitoring and safety.

Wearable haptic feedback remains challenging in virtual training. This paper presents a direct current servo-motor-driven force-feedback device for limb interaction. A cam angle–force model is established, and a dual closed-loop control scheme is applied to improve force accuracy under varying loads. Experiments and virtual maintenance training show rapid collision response, with force and angle errors within 4.6 %, enhancing realism  and immersion. 

In this study, a model of gear transmission considering friction and tooth-side clearance was established, and the time-varying meshing stiffness considering friction was used. The actual discontinuous stiffness was evaluated using Fourier transform, and the dynamic response of the system caused by the discontinuity was compared.  Through phase and Poincaré diagrams, the bifurcation characteristics and dynamic meshing force were discussed.

Very small cracks are hard to detect because their signals are easily obscured by noise and practical measurement limits. This work introduces a physics-based strategy that links wave behaviour with instrument performance to guide excitation selection. Experiments demonstrate earlier and more consistent crack detection, offering a practical solution for more reliable structural health monitoring.

Traditional electro-hydraulic servo valves are driven by electromagnets, which are susceptible to interference and have poor dynamic performance, severely limiting flow control accuracy. To address this issue, a hollow ultrasonic motor was designed to drive the servo valve via a ball screw. The results show that the system has good robustness and anti-interference capabilities, enabling precise control of the valve spool displacement.

Rolling guides are essential parts of precision machines, yet their design often depends on slow and costly simulations. This study presents a computer model that learns from a small number of examples to predict and improve guide performance. Combined with an automated design platform, it enables faster, more accurate, and efficient optimisation of mechanical components.

This study analyzes O-ring sealing failure under low-temperature and high-pressure conditions using a finite element model. Results show that retaining rings improve sealing pressure and prevent extrusion. Low temperatures reduce contact pressure, increasing leakage risk. Larger O-ring diameters enhance sealing.

In this paper, an improved mesh excitation calculation method with random cumulative pitch errors is constructed, and a lumped-parameter model for the herringbone planetary gear system is established. Subsequently, the action of random cumulative pitch errors on mesh excitations under different loads is studied. Furthermore, the dynamic mesh forces for all mesh pairs of the herringbone planetary gear system are investigated in detail, considering the effects of random cumulative pitch errors.  

This research addresses a critical gap in marine transport safety by developing a realistic computer model to simulate how large underwater cable pallets behave when accidentally dropped during handling. 

This article introduces a new type of magnetic coupler which overcomes traditional limitations such as poor scalability and limited torque control. Its stackable disks and unique flux adjustment mechanism enable precise and wide-range torque adjustment without moving the disks. Through modeling verification, this design achieves high torque and excellent controllability, providing a practical solution for high-performance magnetic transmission in compact industrial applications.

This paper analyses the effects of several typical polygon amplitudes and orders on wheel sound radiation in metro lines. Concurrently, research has found that there is no linear relationship between wheel–rail forces and polygon amplitudes. Furthermore, the noise reduction mechanism of resilient wheels is thoroughly explained in terms of damping, energy dissipation, vibration isolation, decoupling, and acoustic impedance characteristics. 

In this study, based on a three-dimensional transient temperature field simulation model considering the equivalent thermophysical properties of Al matrix and SiC particles, a cutting force decomposition model for pulsed laser-assisted cutting of SiCp/Al composites is established. At the same time, the difference between experimental value and theoretical value is less than 20 %, which proves the reliability of the cutting force model.

The performance of servo actuators is significantly affected by factors such as friction and backlash. Simplified analytical models have difficulty meeting the increasing demands of control systems. Therefore, this study proposes a new data-driven method for modeling nonlinear factors. Through experimental verification, the newly proposed modeling method significantly improves the accuracy of nonlinear models. This achievement provides strong support for the precise control of servo actuators.

We developed a new tool to solve the challenge of installing high-strength bolts within the extremely compact spaces of aircraft engines. Our design employs a unique ratchet–pawl mechanism driven by a hydraulic cylinder to generate high torque. Testing confirmed that the tool can safely deliver an average torque of 136 N m within a mere 4 mm gap. This successful innovation enhances assembly safety and efficiency in confined areas and establishes a foundation for the intelligent tools.

We created a robot called DTransleg that can walk on legs or roll on wheels using a simple, transformable design. Its upper leg doubles as a wheel rim, allowing smooth switching between walking and rolling. Tests with simulations and a real prototype show stable motion and easy transitions, paving the way for robots that adapt to different environments.

Rigid-flexible coupling is the development trend of lightweight parallel mechanisms. To solve the kinematic problems of such mechanisms, this paper takes the rigid-flexible coupling parallel mechanism driven by elastic thin rods as the research object, proposes an inverse geometrico-static problem (IGP) solution, and conducts relevant motion tests to verify that the solution has high accuracy. This paper can effectively solve the IGP and provide theoretical support for practical application.

The experimental results show that the oil mist is the better cutting fluid compared with dry cutting and jet cold air, producing not only the smallest specific cutting force but also the smallest surface roughness and dimensional error. Therefore, oil mist is beneficial to micromilling of thin walls made of the Ti-6Al-4V titanium alloy by polycrystalline diamond end mills.