A5054410050- Machine Fault Diagnosis Techniques
- IoT and Edge/Fog Computing
- Fault Detection and Control Systems
- Gear and Bearing Dynamics Analysis
- Mineral Processing and Grinding
- Structural Health Monitoring Techniques
- Gait Recognition and Analysis
- Industrial Vision Systems and Defect Detection
- Anomaly Detection Techniques and Applications
- Blockchain Technology Applications and Security
- Advanced Neural Network Applications
- Advanced Computing and Algorithms
- Image and Object Detection Techniques
- Software-Defined Networks and 5G
- Image Processing and 3D Reconstruction
- Image Processing Techniques and Applications
- Risk and Safety Analysis
- Privacy-Preserving Technologies in Data
- Robot Manipulation and Learning
Fujian Special Equipment Inspection Institute
2024
South China University of Technology
2022-2024
In the wind turbine remote fault diagnosis, sensor data is susceptible to low-quality phenomena such as missing and damaged due communication delays, environmental noise, faults. These issues decrease accuracy of diagnostic models, necessitating a solution enhance model robustness under non-ideal conditions. Hence, robust scheme based on adaptive noise filtering useful feature-domain enhancement (UFDE) proposed in this paper improve stability performance. An interference identification...
The routing algorithm based on a single metric parameter is difficult to meet the Quality of Services (QoS) requirements multi-source data flows in software-defined factory heterogeneous network, resulting link congestion and waste network resources. To solve problem, this paper proposes QoS optimization method for networks double deep Q (DDQN). First, architecture proposed networks, function latency load balancing established. Then, DDQN used obtain optimal paths flows, path uniformly...
Presently, resource-constrained devices in manufacturing Internet of Things (MIoT), such as sensors and radio frequency identification (RFID) devices, collect a large amount privacy-sensitive data. However, weak passwords vulnerable encryption capabilities MIoT have often become loopholes security risks. To this end, paper proposes novel secure data-sharing scheme based on the integration blockchain fusion both real fake data to address requirements devices. First, computing resource...
With the development of artificial intelligence, machine vision technology based on deep learning is an effective way to improve production efficiency. Because rapid update automobile manufacturing industry and large variety products, time number samples model are limited, which brings great difficulties recognition components. Therefore, considering economic benefits enterprises, this paper proposes intelligent component method appropriate for small datasets, aiming explore automatic system...
Abstract Under high noise conditions and random impacts, which constitute strong interference, models often exhibit limited capability in capturing long-term dependencies, leading to lower accuracy predicting the remaining useful life (RUL) of bearings. To address this issue, a spatiotemporal fusion network capable ultra-long-term feature analysis is proposed enhance bearing RUL prediction under substantial interference. This utilizes dilated convolution-based lightweight vision transformer...
The aim of this study is to improve the cross-condition domain adaptability bearing fault diagnosis models and their diagnostic performance under previously unknown conditions. Thus, paper proposes a multi-condition adaptive method based on multi-granularity data annotation. A tree-structured labeling scheme introduced allow for hierarchical network designed automatically learn multi-level information from condition using feature extractors varying granularity, allowing extraction shared...