A5009212353- Machine Fault Diagnosis Techniques
- Fault Detection and Control Systems
- Non-Destructive Testing Techniques
- Engineering Diagnostics and Reliability
- Gear and Bearing Dynamics Analysis
- Infrastructure Maintenance and Monitoring
- Hydrogen embrittlement and corrosion behaviors in metals
- Mechanical Failure Analysis and Simulation
- Oil and Gas Production Techniques
Chongqing University of Posts and Telecommunications
2023-2024
In recent years, domain adaption (DA) in fault diagnosis of rotary machinery has been attracting considerable attention. Recent advancements closed-set, partial, and open-set DA diagnosis, have well addressed the label inconsistent problem where relationship spaces between source target domains are assumed to be certain; however, previous information on types is unavailable applications, denoted as universal cross-domain above three kinds methods rendered ineffective. To address this issue,...
Deep learning (DL) is widely used in the field of fault diagnosis. The training DL-based diagnosis methods commonly requires collection comprehensive datasets that include all classes; however, new classes will continue to emerge during diverse phases service time rotating machinery. Traditional models suffer from reduced diagnostic accuracy due their inability adaptively identify therefore, a distribution character-guided projection replay network (DCGPR) proposed for such incremental...
Domain generalization-based fault diagnosis methods have been extensively explored in cross-domain under various operating conditions recent times. Nevertheless, these adhere to a common premise that the modes across each available source domain remain consistent. The label inconsistent problem arises when model extracts domain-invariant features from multiple domains. That is say, between domains are inconsistent, resulting overfitting scarce during training. Aiming at this problem, study...
Unsupervised domain adaption (DA) is a well-established technique for fault diagnosis of rotating machinery, which has attracted considerable attention in recent years. However, existing DA methods assume that the label spaces source and target are consistent, this assumption not always satisfied industrial settings as new types would inevitably occur during operation. Aiming at issue, an open-set (OSFD) network proposed denoted slanted adversarial (TDSAN). Specifically, two significant...
Multi-source open-set fault diagnosis (MS-OSFD) with category shift is a crucial issue in industrial scenarios, where potential unknown faults are included the target domain and label spaces of multiple source domains diverse from each other. The existing OSFD methods ignore knowledge issues, leading to incomplete transfer poor performance. Aiming at abovementioned problems, multi-adversarial deep network (MADTN) for MS-OSFD rotating machinery proposed. First, multi-source classes matching...