A5101989721- Manufacturing Process and Optimization
- Plant Disease Resistance and Genetics
- Advanced Manufacturing and Logistics Optimization
- Plant and Fungal Interactions Research
- Assembly Line Balancing Optimization
- Agricultural Engineering and Mechanization
- Gear and Bearing Dynamics Analysis
- Machine Fault Diagnosis Techniques
- Welding Techniques and Residual Stresses
- Soil Mechanics and Vehicle Dynamics
- Plant Disease Management Techniques
- HVDC Systems and Fault Protection
- Wireless Power Transfer Systems
- Food Quality and Safety Studies
- Industrial Vision Systems and Defect Detection
- Advanced Battery Technologies Research
- Image and Object Detection Techniques
- Nutrition, Health and Food Behavior
- Advanced Chemical Sensor Technologies
- Silicon Carbide Semiconductor Technologies
- Multilevel Inverters and Converters
- Advanced Measurement and Detection Methods
- Robotics and Sensor-Based Localization
- Energy Harvesting in Wireless Networks
Beijing Information Science & Technology University
2025
University of Auckland
2009-2023
Henan University of Science and Technology
2023
Yunnan Agricultural University
2018
To address the challenge of low diagnostic accuracy in rolling bearing fault diagnosis under varying operating conditions, this paper proposes a novel method integrating synchronized wavelet transform (SWT) with an enhanced Vision Transformer architecture, referred to as ResCAA-ViT. The SWT is first applied process raw vibration signals, generating high-resolution time-frequency maps input for network model. By compressing and reordering coefficients frequency domain, enhances resolution,...
Aiming at the potato cropping pattern in hilly area of southwest China, a small digging device for harvester was designed. First, overall structure determined according to soil physical characteristic and test site. Then, shovel, key components were designed analyzed relationship between inclination shovel power loss under conditions different speed, depth bulk density by MATLAB software, mathematical models established. Finally, three-dimensional model whole machine established SolidWorks,...
Branched deformable linear objects, like wire harnesses, are vastly used in the electrical industry to interconnect multiple electronic components while allowing small relative motions. Their nature gives them an infinite-dimensional configuration space, which is challenging for robotic manipulation and requires sensor feedback about actual configuration. Cameras have been before automation attempts as of branched objects. However, image processing sensible occlusions unstructured...
This paper presents a new type of Inductive Power Transfer (IPT) pickup which directly regulates power in AC form, hence producing controllable high-frequency source. The has significant advantages terms increased system efficiency, reduced size and low production cost compared to traditional pickups that also produce controlled output using complex AC-DC-AC conversion circuits. processing employs switches operating under soft switching conditions clamp parts the resonant voltage across...
Three-level NPC inverters have been widely used in grid-connected systems due to their superior performance compared with two-level inverters, but more switches lead high fault probability. Meanwhile, the neutral point potential (NPP) fluctuation of DC link is an inherent problem three-level inverters. To keep inverter running stably after single-arm failure, a fault-tolerant control strategy based on optimised space vector pulse width modulation (SVPWM) proposed this paper. Firstly,...
The evaluation and prediction of food state during chewing are important for understanding imitating the process, which has implications industry. This study aims to develop a system deep learning vision analyze changes in Particle Size Distribution (PSD) features solid mastication. A stereoscopic with multiple cameras will be designed capture all samples from different angles. robot used under supervision this collect images samples, creating database. database train module capable PSD...
Advanced robotic systems are increasingly vital in remanufacturing, bringing about revolutionary changes end-of-life (EOL) product recovery, disassembly, and remanufacturing. However, a key characteristic of EOL products is the uncertainty condition their components, resulting stochastic disassembly times. Hence, this research addresses robot line balancing Problem (SRDLBP), which arises from inherent stochasticity operation times during practical operations. To address challenge, study...
Abstract The real-time assessment and prognostication of food texture during mastication are paramount for comprehending emulating the chewing process, bearing significant ramifications industry. This study unveils a deep learning-oriented recognition framework utilizing Mask R-CNN to analyze throughout process. We create an extensive bolus image compendium train learning model proficient in discrimination processing parameter estimation. A vision system, incorporating Intel RealSense D435i...