A5037433861- Machine Fault Diagnosis Techniques
- Gear and Bearing Dynamics Analysis
- Fault Detection and Control Systems
- Engineering Diagnostics and Reliability
- Structural Health Monitoring Techniques
- Hydrocarbon exploration and reservoir analysis
- Advanced Algorithms and Applications
- Vibration Control and Rheological Fluids
- Blind Source Separation Techniques
- Robotic Path Planning Algorithms
- Seismic Performance and Analysis
- Vehicle Noise and Vibration Control
- Image and Signal Denoising Methods
- Structural Engineering and Vibration Analysis
- Hydraulic Fracturing and Reservoir Analysis
- Streptococcal Infections and Treatments
- Advanced Sensor and Control Systems
- Anomaly Detection Techniques and Applications
- Vibration and Dynamic Analysis
- Neonatal and Maternal Infections
- Mechanical Failure Analysis and Simulation
- Reservoir Engineering and Simulation Methods
- Non-Destructive Testing Techniques
- Autonomous Vehicle Technology and Safety
- Speech and Audio Processing
Guangzhou Center for Disease Control and Prevention
2019-2025
Nanjing University of Aeronautics and Astronautics
2016-2025
Research Institute of Petroleum Exploration and Development
2018-2024
Shandong University of Science and Technology
2021-2023
Nantong University
2023
ORCID
2020-2022
Weatherford College
2021
Guangdong Pharmaceutical University
2016-2018
Soochow University
2017
Kaifeng University
2010
Case-based intelligent fault diagnosis methods of rotating machinery can deal with new faults effectively by adding them into the case library. However, case-based scarcely refer to automatic feature extraction, and k-nearest neighbor (KNN) commonly required is unable determine nearest neighbors for different testing samples adaptively. To solve these problems, a method proposed based on enhanced KNN (EKNN), which take advantage both parameter-based methods. First, EKNN embedded...
Effective data-driven rotating machine fault diagnosis has recently been a research topic in the and health management of machinery systems owing to benefits, including safety guarantee, labor saving, reliability improvement. However, vast real-world applications, classifier trained on one dataset will be extended datasets under variant working conditions. Meanwhile, deviation between can triggered easily by speed oscillation load variation, it highly degenerate performance learning-based...
Mechanical fault datasets are always highly imbalanced with abundant common mechanical samples but a paucity of from rare conditions. To overcome this weakness, the simulation signals is proposed in paper. Specifically, frequency spectra employed as model signals, then Wasserstein generative adversarial network (WGAN) implemented to generate simulated based on labeled dataset. Finally, real and artificial combined train stacked autoencoders (SAE) detect health validate effectiveness WGAN-SAE...
Intelligent fault diagnosis methods are promising in dealing with mechanical big data owing to their efficiency extracting representative features. However, there is always an undesirable shift variant property embedded raw vibration signals, which hinders the direct use of signals networks. A convolutional neural network (CNN) a widely used and efficient method extract features various fields for its excellent sparse connectivity, equivalent representation weight sharing properties. CNN...
Among various fault diagnosis methods, deep learning has shown state-of-the-art performance in processing mechanical big data. This paper investigates a reliable method known as autoencoder, which is most suitable for automatic feature extraction of signals. However, traditional autoencoders have two deficiencies: (1) the multi-layer structure autoencoder an internal covariate shift problem, will cause great difficulty network training. (2) The application case rotating speed fluctuation not...
Abstract Rolling bearings play a vital role in the overall operation of rotating machinery. In practice, many learning methods for variable-speed fault diagnosis ignore task-specific decision boundaries, making it very difficult to completely match feature distribution between different domains. Therefore, overcome this problem, an adversarial domain adaptation asymmetric mapping with CORAL alignment is presented. The extractor able extract more specific-domain features obvious distinction....