A5108063853- Machine Fault Diagnosis Techniques
- Structural Health Monitoring Techniques
- Fault Detection and Control Systems
- Gear and Bearing Dynamics Analysis
- stochastic dynamics and bifurcation
- Probabilistic and Robust Engineering Design
- Ultrasonics and Acoustic Wave Propagation
- Acoustic Wave Phenomena Research
- Speech and Audio Processing
- Engineering Diagnostics and Reliability
- Underwater Acoustics Research
- Blind Source Separation Techniques
- Advanced machining processes and optimization
- Spectroscopy and Chemometric Analyses
- Advanced Measurement and Detection Methods
- Industrial Vision Systems and Defect Detection
- Neural dynamics and brain function
- Image and Signal Denoising Methods
- Advanced Battery Technologies Research
- Anomaly Detection Techniques and Applications
- Ecosystem dynamics and resilience
- Non-Invasive Vital Sign Monitoring
- Advanced Algorithms and Applications
- Railway Engineering and Dynamics
- Non-Destructive Testing Techniques
Shanghai Jiao Tong University
2018-2025
University of Science and Technology of China
2011-2022
University of Huddersfield
2022
Hebei University of Technology
2022
National University of Singapore
2017
Anhui University
2016
University of Connecticut
2009
Chinese University of Hong Kong
2008
University of Massachusetts Amherst
2008
Microsoft Research Asia (China)
2006
Considering various health conditions under varying operational conditions, the mining sensitive feature from measured signals is still a great challenge for intelligent fault diagnosis of spindle bearings. This paper proposed novel energy-fluctuated multiscale approach based on wavelet packet energy (WPE) image and deep convolutional network (ConvNet) bearing diagnosis. Different vector characteristics applied in bearings, transform first combined with phase space reconstruction to rebuild...
The analysis of vibration or acoustic signals is most widely used in the health diagnosis rolling element bearings. One main challenges for bearing that weak signature incipient defects generally swamped by severe surrounding noise acquired signals. This problem can be solved stochastic resonance (SR) approach, which to enhance desired signal aid noise. paper presents an adaptive multiscale tuning SR (AMSTSR) effective and efficient fault identification A new criterion, called weighted power...
Digital signal processing algorithms are widely adopted in motor bearing fault diagnosis. However, most developed on desktop platforms, and their focus is the analysis of offline captured signals. In this paper, a simple easily implemented algorithm running an embedded system proposed for online diagnosis bearing. The core part stochastic-resonance-based adaptive filter that realizes denoising adaptation coefficient. Processed by filter, period purified obtained, then type identified. method...
Time-frequency analysis can reveal an intrinsic signature for representing nonstationary signals machine health diagnosis. This paper proposes a novel time-frequency signature, called manifold (TFM), by addressing learning on generated distributions (TFDs). The TFM is produced in three steps. First, the phase space reconstruction (PSR) employed to reconstruct inherent dynamic embedded analyzed signal. Second, TFDs are calculated represent information space. Third, conducted discover...
Multiscale noise tuning stochastic resonance (MSTSR) has been proved to be an effective method for enhanced fault diagnosis by taking advantage of detect the incipient faults bearings and gearbox. This paper addresses a sequential algorithm MSTSR train bearing in embedded system through acoustic signal analysis. Specifically, energy operator, digital filter array, fourth rank Runge-Kutta equation methods are designed realize demodulation, multiscale tuning, bistable sequence. The merit is...