A5061956032- Recommender Systems and Techniques
- Fault Detection and Control Systems
- Engineering Diagnostics and Reliability
- Machine Fault Diagnosis Techniques
- Privacy-Preserving Technologies in Data
- Power Systems and Technologies
- Vibration Control and Rheological Fluids
- CO2 Sequestration and Geologic Interactions
- Smart Grid and Power Systems
- Stochastic Gradient Optimization Techniques
- Power Systems and Renewable Energy
- Privacy, Security, and Data Protection
- Microgrid Control and Optimization
- Groundwater flow and contamination studies
- Wind Turbine Control Systems
- Gear and Bearing Dynamics Analysis
- Vehicle Dynamics and Control Systems
- Geothermal Energy Systems and Applications
- Refrigeration and Air Conditioning Technologies
- Hydraulic and Pneumatic Systems
- Frequency Control in Power Systems
Yibin University
2021-2024
Shanghai Dianji University
2021
ORCID
2021
Leshan Normal University
2015
Cross-domain recommender systems are known to provide solutions the cold start and data sparsity problems in systems. This can be achieved by leveraging sufficient ratings users' profiles one domain enhance accurate recommendations another domain. However, domains with not willing share their other or due privacy legal concern. Hence this shows a need for privacy-preserving mechanism that encourages secure knowledge transfer between different domains. study proposes cross-domain system based...
An automotive suspension determines both the driving stability and comfort of vehicle occupants.This paper establishes two kinds degrees freedom for automobile vibration model uses PID controller to establish an adaptive open-loop closed-loop control system.Respectively, by step interference, white noise sinusoidal interference input, studying characteristics in vertical direction.By numerical simulation, we obtain displacement acceleration-time graphs.The simulation results show that first...
Abstract The fault diagnosis method based on ResNet50 convolutional neural network and migration learning is proposed as a way of improving the gearbox diagnosis. Firstly, exporting normal faulty data gearbox. Then converting exported into one-dimensional images to generate corresponding training test sets, train in model get accuracy set set. After fine adjustment, it used for diagnosis, compared with VGG16, ResNet101, GoogleNet model, above 86.6%. It has good prospect application, its...
Wind turbine employs pitch angle control to maintain captured power at its rated value when the wind speed is higher than value. This work adopts a perturbation observer based sliding-mode (POSMC) strategy realize robust variable-pitch of permanent magnet synchronous generator (PMSG). POSMC combines system nonlinearities, parametric uncertainties, unmodelled dynamics, and time-varying external disturbances into perturbation, which aims estimate via without an accurate model. Subsequently,...
The existing gearbox fault diagnosis models often need a lot of data and corresponding tags to complete the model training, but actual is less unevenly distributed. Aiming at situation that scarce distributed, this paper proposes method based on Deep Convolution Generative Adversarial Network (DCGAN). First, original vibration signals collected in early stage are processed through processing form sample set input into DCGAN for confrontation virtual samples with real characteristics...