A5048630560- Machine Fault Diagnosis Techniques
- Advanced machining processes and optimization
- Structural Health Monitoring Techniques
- Gear and Bearing Dynamics Analysis
- Fault Detection and Control Systems
- Engineering Diagnostics and Reliability
- Ultrasonics and Acoustic Wave Propagation
- Industrial Vision Systems and Defect Detection
- Image and Signal Denoising Methods
- Advanced Surface Polishing Techniques
- Tribology and Lubrication Engineering
- Advanced Measurement and Metrology Techniques
- ECG Monitoring and Analysis
- Advanced Machining and Optimization Techniques
- Structural Integrity and Reliability Analysis
- Blind Source Separation Techniques
- Optical measurement and interference techniques
- Surface Roughness and Optical Measurements
- Non-Destructive Testing Techniques
- EEG and Brain-Computer Interfaces
- Phonocardiography and Auscultation Techniques
- Iterative Learning Control Systems
- Bladed Disk Vibration Dynamics
- Occupational Health and Safety Research
- Advanced Optical Sensing Technologies
Xiamen University
2014-2023
Xi'an Jiaotong University
2012-2015
The authors introduce an iterative algorithm, called matching demodulation transform (MDT), to generate a time-frequency (TF) representation with satisfactory energy concentration. As opposed conventional TF analysis methods, this algorithm does not have devise ad-hoc parametric dictionary. Assuming the FM law of signal can be well characterized by determined mathematical model reasonable accuracy, MDT adopt partial and stepwise refinement strategy for investigating properties signal....
As a typical example of large and complex mechanical systems, rotating machinery is prone to diversified sorts faults. Among these faults, one the prominent causes malfunction generated in gear transmission chains. Although they can be collected via vibration signals, fault signatures are always submerged overwhelming interfering contents. Therefore, identifying critical fault’s characteristic signal far from an easy task. In order improve recognition accuracy signal, novel intelligent...
Composite materials have been widely used in many industries due to their excellent mechanical properties. It is difficult analyze the integrity and durability of composite structures because own characteristics complexity load environments. Structural health monitoring (SHM) based on built-in sensor networks has evaluated as a method improve safety reliability reduce operational cost. With rapid development machine learning, large number learning algorithms applied disciplines, also are...
Purpose This paper aims to present a novel particle swarm optimization (PSO) based on non-homogeneous Markov chain and differential evolution (DE) for path planning of intelligent robot when having obstacles in the environment. Design/methodology/approach The three-dimensional surface is decomposed into two-dimensional plane height information z axis. Then, grid method exploited environment modeling problem. After that, recently proposed switching local evolutionary PSO (SLEPSO) DE analyzed...
The noise cancellation in electrocardiogram (ECG) signal is very influential to distinguish the essential features masked by noises. power line interference (PLI) main source of most bio-electric signals. Digital notch filters can be used suppress PLI ECG However, problems transient interferences and ringing effect occur, especially when digitization does not meet condition full period sampling. In this paper, obtain a better PLI, designing approach, generating adaptive filter (ANF) sharp...
Machined surfaces are rough from a microscopic perspective no matter how finely they finished. Surface roughness is an important factor to consider during production quality control. Using modern techniques, surface measurements beneficial for improving machining quality. With optical imaging of machined as input, convolutional neural network (CNN) can be utilized effective way characterize hierarchical features without prior knowledge. In this paper, novel method based on CNN proposed...
Tool wear and breakage are inevitable due to the severe stress high temperature in cutting zone. A highly reliable tool condition monitoring system is necessary increase productivity quality, reduce costs equipment downtime. Although many studies have been conducted, most of them focused on single-step process or continuous cutting. In this paper, a robust milling methodology based 2-D convolutional neural network (CNN) derived wavelet frames (DWFs) presented. The frequency band...
Accurate identification of the type seizure is very important for treatment plan and drug prescription epileptic patients. Artificial intelligence has shown considerable potential in fields automated EEG analysis classification. However, highly personalized representation seizures led to many research results that are not satisfactory clinical applications. In order improve adaptability algorithm, this paper proposes an adversarial learning-driven domain-invariant deep feature method, which...
Intelligent fault diagnosis is of great significance to guarantee the safe operation mechanical equipment. However, widely used models rely on sufficient independent and homogeneously distributed monitoring data train model. In practice, available equipment faults are insufficient distribution varies greatly under different working conditions, which leads low accuracy trained diagnostic model restricts it, making it difficult apply other conditions. To address these problems, a novel method...
Bearing performance degradation assessment is meaningful for keeping mechanical reliability and safety. For this purpose, a novel method based on kernel locality preserving projection proposed in article. Kernel extends the traditional into non-linear form by using function it more appropriate to explore information hidden data sets. Considering point, used generate subspace from normal bearing data. The test are then projected onto obtain an index assessing degrees. that expressed of inner...