- Gear and Bearing Dynamics Analysis
- Additive Manufacturing Materials and Processes
- Simulation and Modeling Applications
- High Entropy Alloys Studies
- Manufacturing Process and Optimization
- Machine Fault Diagnosis Techniques
- Industrial Technology and Control Systems
- Engineering Diagnostics and Reliability
- Tribology and Lubrication Engineering
- Welding Techniques and Residual Stresses
- Additive Manufacturing and 3D Printing Technologies
- Vibration and Dynamic Analysis
- Wind Energy Research and Development
- Industrial Vision Systems and Defect Detection
- Advanced Algorithms and Applications
- High-Temperature Coating Behaviors
- Mechanical Engineering and Vibrations Research
- Fault Detection and Control Systems
- Advanced Sensor and Control Systems
- Hydraulic and Pneumatic Systems
- Magnetic Bearings and Levitation Dynamics
- Geological Modeling and Analysis
- Advanced Computational Techniques and Applications
- 3D Shape Modeling and Analysis
- Blockchain Technology Applications and Security
Xinjiang University
2016-2025
State Grid Corporation of China (China)
2025
Smile Train
2023
Robotic Technology (United States)
2018
Robotic Research (United States)
2018
Liuyang City Maternal and Child Health Hospital
2018
Azur Space Solar Power
2018
Center for Special Minimally Invasive and Robotic Surgery
2018
Brunel University of London
2015
National University of Defense Technology
2012
Laser cladding faces several challenges, including cracking, fracture, deformation, and interlayer delamination, which hinder its widespread application in part repair. Residual stress within the workpiece is a key factor contributing to these issues. To enhance quality of laser gear tooth repairs, study integrates numerical modeling experimental approaches examine how varying annealing temperatures influence residual microstructural changes Ni60A layers. A theoretical model was established...
In order to improve the reliability and life of wind turbine, this paper takes rolling bearing in experimental platform turbine as research object. obtain intrinsic mode function (IMF) each fault type, original signals different states on are decomposed by using overall average empirical decomposition method (EEMD) wavelet packet (WPD), respectively. Then energy ratio IMF component types faults total value is calculated eigenvectors constructed. The extreme learning machine (ELM)...
Abstract To achieve real-time monitoring and intelligent maintenance of transformers, a framework based on deep vision digital twin has been developed. An enhanced visual detection model, DETR + X, is proposed, implementing multidimensional sample data augmentation through Swin2SR GAN networks. This model converts one-dimensional DGA into three-dimensional feature images Gram angle fields, facilitating the transformation fusion heterogeneous modal information. The Pyramid Vision Transformer...
Based on variational mode and XGBoost solved by particle swarm optimization algorithm, a data-driven early fault diagnosis method for wind turbine gearbox was proposed. Through the VMD decomposition of original signal, feature best is taken as vector, model used intelligent classification vector. test experiment signal collected in practice, results show that can realize warning quickly.
Abstract In order to meet the needs of intelligent manufacturing in transformer production workshop, process workshop was analyzed, and architecture a traceability system discussed. AHP used design weight functional modules, fusion mechanism all-factor identification information quality proposed. Based on RFID technology, unique code is assigned each product, which effectively improves efficiency accuracy product realizes digital management operation workshop. Finally, developed using Java...
Abstract This paper proposes a provincial-scale system integrating neural networks with electricity rate data analysis to enhance prediction accuracy and anomaly detection efficiency while ensuring user privacy. At its core is the electric network (EANN), which combines LSTM GCN effectively capture temporal dynamics of billing relational structure among users. The also introduces privacy protection scheme based on personalized federated learning for secure cross-regional analysis....
Laser-arc hybrid welding was applied to Q355 medium-thick steel plates improve weld tensile properties, with experimental verification comparing welds the base material. Numerical simulations identified optimal process parameters, analyzing effects of heat source distance, speed, laser power, and arc power on temperature field distribution molten pool morphology. Heat distance had greatest influence, followed by power. Maintaining a peak 900–1000 K refined grain structure, enhancing...
To address the limitations of traditional predictive maintenance for large wind turbines, a fault prediction method that combines gated recurrent unit (GRU) network with an improved ant lion optimization (IALO) algorithm is proposed. Traditional monitoring primarily relies on supervisory control and data acquisition (SCADA) system to monitor parameters such as oil temperature using threshold-based alarm methods. However, this approach suffers from low accuracy in judgment delayed detection....
Wind turbine is a clean, renewable and sustainable energy technology that makes it extremely important to promote global transformation achieve low-carbon development. Cracks in wind blades reduce their stability lifespan may lead significant safety hazards. Therefore, blade for the 5MW was modeled with method of layering by zones sections, dynamic characteristics cracks at different positions are analyzed. It can be found maximum stress highest when crack located root blade, from will...
We propose a novel fault-diagnosis approach for rolling bearings by integrating variational mode decomposition (VMD), refined composite multiscale dispersion entropy (RCMDE), and support vector machine (SVM) optimized sparrow search algorithm (SSA). Firstly, VMD was selected from various signal methods to decompose the original signal. Then, features were extracted RCMDE as input of diagnosis model. Compared with sample (MSE) (MDE), proved be superior. Afterwards, SSA used optimal parameters...
The working environment of wind turbine gearboxes is complex, complicating the effective monitoring their running state. In this paper, a new gearbox fault diagnosis method based on improved variational mode decomposition (IVMD), combined with time-shift multi-scale sample entropy (TSMSE) and sparrow search algorithm-based support vector machine (SSA-SVM), proposed. Firstly, novel algorithm, IVMD, presented for solving problem where VMD parameters (K α) need to be selected in advance, which...
Aiming at the influence of fundamental frequency and its harmonics in transformer vibration signals on fault signals, which cause a low identification rate degradation classification model performance, new strategy is proposed for diagnosis using periodic map spectrum feature maps as input features. In this study, optimal decomposition parameters were first found adaptively VMD improved by positive cosine optimisation algorithm; then, signal was modally decomposed, features plotted according...
As a critical raw material for the textile industry, cotton lint provides various types of yarns, fabrics and finished products. However, due to complexity supply chain its many links, information records are often missing, inaccurate or lagging, resulting in low transparency traceability. In traditional chain, data each link stored isolation; lack an effective sharing mechanism formation “information silos”, complete traceability is challenging achieve. addition, completeness authenticity...
The application of blockchain technology in industrial product quality traceability is analyzed to construct a new model that mainly based on and supplemented by an identity system. blockchain-enabled overall technical architecture system explored, blockchain-based full life cycle information constructed. First, the weights indicators different links equipment were calculated using EAHP hierarchical analysis method. manufacturing link had largest weight, with value 18.8%. Second, system’s...
To satisfy the requirements of end-to-end fault diagnosis rolling bearings, a hybrid model, based on optimal SWD and 1D-CNN, with layer multi-sensor data fusion, is proposed in this paper. Firstly, BAS algorithm adopted to obtain parameters SWD. After that, raw signals from different channels sensors are segmented preprocessed by SWD, whose name BAS-SWD. By which, sensitive OCs higher values spectrum kurtosis extracted signals. Subsequently, improved 1D-CNN model VGG-16 constructed,...
The extraction of the optimal mode bearing signal in drive system a corn harvester is challenging task. In addition, accuracy and robustness fault diagnosis model are low. Therefore, this paper proposes method that uses component as input feature. vibration first decomposed by variational decomposition (VMD) based on parameters searched artificial bee colony (ABC). Moreover, key components screened using an evaluation function fusion arrangement entropy, signal-to-noise ratio, power spectral...
This paper presents a comprehensive procedure to calculate steady dynamic response and noise radiation generated by gear reducer. In this process, the bearing force is obtained solving transmission system model, which taken as excitation of gearbox, gearbox vibration researched using FEM/BEM, so characteristics structure are demonstrated. Then time history node spectrum obtained, effect frequency doubling mesh on illustrated. The changes in radiated reducers with load calculated respectively...
Gear system is characterized by high efficiency, compact structure, and transmission ratio stability, it has been extensively applied in various industrial equipment. This paper presents a novel preliminary estimate method for gear reducer noise radiation vibration characteristics, systematic researches on characteristics of are made. In the analysis process, influence time-varying mesh stiffness, error excitation, tooth flank contact feature comprehensively considered, linear model...