A5035740532- Machine Fault Diagnosis Techniques
- Machine Learning in Bioinformatics
- Gear and Bearing Dynamics Analysis
- Spectroscopy and Chemometric Analyses
- Fault Detection and Control Systems
- Fractal and DNA sequence analysis
- Protein Structure and Dynamics
- Fatigue and fracture mechanics
- Advanced Algorithms and Applications
- Advanced Sensor and Control Systems
- Real-Time Systems Scheduling
- Power Transformer Diagnostics and Insulation
- Pericarditis and Cardiac Tamponade
- Advanced Wireless Communication Techniques
- Engineering Diagnostics and Reliability
- Sparse and Compressive Sensing Techniques
- Wireless Communication Networks Research
- Structural Health Monitoring Techniques
- Mechanical Failure Analysis and Simulation
- Face and Expression Recognition
- Network Time Synchronization Technologies
- Reliability and Maintenance Optimization
- Engineering and Test Systems
- Advanced Wireless Network Optimization
- Geotechnical Engineering and Underground Structures
Chengdu Third People's Hospital
2025
Anhui University of Technology
2023-2024
National University of Defense Technology
2020-2024
Harbin Institute of Technology
2024
Changsha University
2023
Hunan University
2017-2023
PLA Army Engineering University
2014-2023
Peng Cheng Laboratory
2020-2022
Wuhu Institute of Technology
2019
Air Force Engineering University
2012
Vibration signals and infrared images have different advantages characteristics. Although a few recent researches explored their information fusion in rotating machinery fault diagnosis, they show limited performance when facing strong interference imbalanced cases. Therefore, framework based on confidence weight support matrix machine (CWSMM) is proposed. In this framework, CWSMM can not only fully leverage the structure of thermography vibration time–frequency images, but also has...
Although traditional signal processing methods have good decomposition performance in multimodal signals, they lack theoretical research on periodic pulse resulting insufficient decomposition. Based this, a reduced mode (RMD) method is proposed this paper, which can decompose components (RCs) iteratively through the designed finite impulse response (FIR) filter bank. On one hand, an adaptive index called reweighted kurtosis (RK) defined as objective function of banks, so to fully consider...
As an important part of rotating machinery, gear is easy to appear some unexpected fault states, and its diagnosis very important. Fourier decomposition method (FDM) a common for diagnosis, but the noise robustness, period recognition, extraction capabilities FDM are unsatisfactory. Based on this, in this article, Ramanujan mode (RFMD) proposed. The RFMD not only has complete mathematical theory foundation also excellent ability identify extract periodic components. Emulational experimental...
As a classical demodulation method, envelope spectrum (ES) has been used in rotating machinery fault diagnosis. However, for strong noise or multiple faults, the feature extraction ability of ES is not outstanding, even if it unable to extract obvious features. Fourier transform (FT) analysis also suitable analyzing non-stationary signals. Considering shortcomings FT, this paper defines Ramanujan mixture (RFMT). The RFMT outstanding period and can accurately periodic features signal. Based...
Abstract Support matrix machine, as an effective classification method, is widely used in single task fault diagnosis. However, for the entire mechanical equipment system, state information between different components coupled with each other, and it difficult to fully express completion of a by only constructing diagnostic model that task. In view this, this paper proposes Multi-task Collaborative Enhancement Matrix Machine (MTCEMM) method. First, dimension enhancement term defined, which...
Abstract When diagnosing rolling bearing faults, the samples obtained are usually limited and imbalanced, resulting in insufficient accuracy of constructed classification model. To address problem, a new multi-sensor information fusion method based on Graph Embedding Fuzzy Broad Learning (GEFBL) is proposed this paper. In GEFBL, graph embedding broad learning framework able to represent data as nodes learning, then transform structural into low-dimensional vectors, which makes task more...
Symplectic geometry mode decomposition (SGMD) method takes the Hankel matrix as trajectory matrix, and eigenvalue of can be obtained by symplectic similarity transformation (SGST). However, with increase noise intensity, SGMD based on cannot distinguish fault signal excited defects background at same order magnitude. Based this, a periodic segment (SGT-PS) is proposed. In SGT-PS, neighboring peak designed to estimate period determine variable parameters, which overcomes defect that difficult...