A5100366409- Machine Fault Diagnosis Techniques
- Engineering Diagnostics and Reliability
- Gear and Bearing Dynamics Analysis
- Image Processing Techniques and Applications
- Fault Detection and Control Systems
- Structural Integrity and Reliability Analysis
- Industrial Vision Systems and Defect Detection
- Advanced Decision-Making Techniques
- Financial Risk and Volatility Modeling
- Face and Expression Recognition
- Complex Systems and Time Series Analysis
- Stock Market Forecasting Methods
- Optical measurement and interference techniques
- Blind Source Separation Techniques
China University of Mining and Technology
2024-2025
Xi'an Shiyou University
2022-2023
Civil Aviation Flight University of China
2022
Shanghai University
2021
Northwestern Polytechnical University
2020
Shaoguan University
2009
Abstract The traditional empirical wavelet transform (EWT) based on the Meyer and scale-space method can decompose a signal into several modes. However, this is not effective in dealing with strong noise non-stationary signals, which may lead to modal mixing or even too many invalid components. For purpose, combination of enhanced (EEWT) correlation kurtosis (CK) proposed paper. Firstly, EEWT used segment spectrum characteristics fluctuations. It uses minimum points envelope as boundaries...
Abstract It is crucial to understand the rolling bearing fault diagnosis procedure since bearings are frequently used in rotating machinery and if a failure occurs, it will interfere with proper operation of entire piece or equipment. Deep learning increasingly being mechanical diagnosis, convolutional neural networks(CNN) most common type. In recent years, rapid growth artificial intelligence has caused methods evolve as well. A CNN diagnostic approach based on seagull optimization...
<title>Abstract</title> Rolling bearings are important components in mechanical equipment, but they also a component with high failure rate. Once malfunction occurs, it will cause equipment to and may even affect personnel safety. Therefore, studying the fault diagnosis methods for rolling is of great significance current research hotspot frontier. However, vibration signals usually exhibit nonlinear non-stationary characteristics, easily affected by industrial environmental noise, making...
Artificial intelligence technology is widely used in mechanical system fault diagnosis as an effective means, but there are few samples practice, which seriously restricts the industrial application of Al model to high-precision diagnosis. In order overcome lack samples, a method composed Gaussian cloud and domain-invariant features extraction proposed for expanding training this paper. The include three steps. Firstly, limited measured obtained by calculating time-domain feature indexes...
During the underwater vehicles (UVs) operation, thruster can malfunction due to foreign body entanglement and damaged blade. Therefore, there is need for research development on data driven methodologies condition monitoring techniques which are able achieve fast, reliable high-quality fault diagnosis. In this paper, a novel method combining Back Propagation Neural Network (BPNN) Support Vector Machine (SVM) proposed towards fast accurate diagnosis of UVs. Firstly, wavelet packet transform...
Volatility clustering is a common phenomenon in financial time series. Typically, linear models can be used to describe the temporal autocorrelation of (logarithmic) variance returns. Considering difficulty estimating this model, we construct Dynamic Bayesian Network, which utilizes conjugate prior relation normal-gamma and gamma-gamma, so that its posterior form locally remains unchanged at each node. This makes it possible find approximate solutions using variational methods quickly....