A5051602167- Fault Detection and Control Systems
- Anomaly Detection Techniques and Applications
- Music Technology and Sound Studies
- Advanced Sensor and Control Systems
- Time Series Analysis and Forecasting
- Music and Audio Processing
- Diverse Musicological Studies
- Artificial Immune Systems Applications
- Structural Integrity and Reliability Analysis
- Advanced Algorithms and Applications
- Machine Fault Diagnosis Techniques
- Hydraulic and Pneumatic Systems
- Advanced Data Processing Techniques
- Oil and Gas Production Techniques
- Network Security and Intrusion Detection
- Machine Learning and ELM
- Evaluation Methods in Various Fields
- Age of Information Optimization
Wuhan University of Technology
2025
Hefei University of Technology
2022-2024
Northumbria University
2024
Rapid developments of offshore wind industry offer a strong demand opportunity for turbine remote diagnosis. As turbines are often located in harsh and communication-constrained environments, the collection transmission data is severely restricted, which poses serious challenge to conventional centralized diagnostic paradigm that relies on aggregation. To address this challenge, we propose novel event-triggered federated learning framework decentralized fault diagnosis turbines....
Multivariate time-series (MTS) collected from multiple sensors on industrial pumps often exhibit concept drift and noise contamination due to variable working conditions complex environments. To detect anomalies in such MTS, we propose a novel model called spectral residual with self-attention variational autoencoder (SR-SAVAE). Specifically, the operation is used mitigate drift, while inference combined total variation regularization address issue of contamination. Experimental results...
Emerging multisource data provide a promising way to make breakthroughs in remaining useful life prediction. Due the diversity industrial sites and complexity of engineering systems, large amount degradation information machinery is hidden multitype data, which poses challenge adequately capture complex features that jointly affect life. To this end, we propose an interactive attention-based deep spatio-temporal network effectively fuse vibration waveforms time-varying operating signals....
In recent years, deep learning has significantly advanced the MIDI domain, solidifying music generation as a key application of artificial intelligence. However, existing research primarily focuses on Western and encounters challenges in generating melodies for Chinese traditional music, especially capturing modal characteristics emotional expression. To address these issues, we propose new architecture, Dual-Feature Modeling Module, which integrates long-range dependency modeling Mamba...