A5112502938- Gear and Bearing Dynamics Analysis
- Machine Fault Diagnosis Techniques
- Advanced Measurement and Detection Methods
- Advanced Decision-Making Techniques
- Fault Detection and Control Systems
- Evaluation Methods in Various Fields
- Power Systems and Technologies
- Tribology and Lubrication Engineering
- Image and Signal Denoising Methods
- Textile materials and evaluations
- Industrial Vision Systems and Defect Detection
- Advanced Sensor and Control Systems
- Color perception and design
- Power Systems Fault Detection
- Dyeing and Modifying Textile Fibers
- Aerodynamics and Acoustics in Jet Flows
- Image Processing Techniques and Applications
- Technology and Security Systems
- Advanced Algorithms and Applications
- Non-Destructive Testing Techniques
- Evaluation and Optimization Models
- Advanced Image Processing Techniques
Guangdong Ocean University
2024-2025
Southeast University
2019-2025
Nanjing University of Information Science and Technology
2023
Bearings are crucial components of modern mechanical equipment and their failure can lead to downtime, economic losses, potential threats personal safety. Therefore, it is essential carry out fault diagnosis bearings. In this paper, Multichannel Signal Transformer (MST) model employed for diagnosing bearing faults. Initially, a single vibration signal two motor current signals collected combined into multichannel signal. This then used train test the MST model. The performance subsequently...
Rolling bearings are the core devices in industrial field, widely used machinery production and automation industry. Therefore, it is necessary to detect fault of rolling bearing. In this paper, an improved VGG model based on Channel Attention mechanism (SENet) proposed extract spatial features multi-scale after signal preprocessing. The BiGRU network Global optimization time domain pretreatment. Excellent results obtained by parallel fusion for detection.
Abstract Mechanical fault transfer diagnosis utilizes the acquired diagnostic knowledge of machinery to address issues in target machinery. This approach demonstrates promising results overcoming limitations incomplete information and scarce labeled data era big data. However, when confronted with cross-machine diagnosis, significant domain discrepancies pose challenges traditional methods, leading lower accuracy learning efficiency. To overcome these problems, this work introduces a novel...
<title>Abstract</title> Recent research has demonstrated that various network architectures combined with Transformers exhibit outstanding performance, particularly in models integrating CNNs, which have made significant strides the field of fault diagnosis. However, existing combine and CNNs fail to effectively utilise multi-scale convolutions for feature extraction suffer from channel weight information loss, weakens network's capability. Therefore, this paper proposes an MK-ACFormer...
<title>Abstract</title> Rolling bearings are pivotal components within rotating mechanical systems, and accurately predicting their remaining service life holds significant practical importance. This paper addresses issues prevalent in common deep learning methods for useful (RUL), notably inadequate feature extraction low prediction accuracy resulting from reliance solely on short-term or long-term dependent features.In this paper, we introduce a residual method bearings, named...
In this paper, a fault location method considering distribution network partition based on deep learning is proposed, in which the Tensorflow framework employed to establish and construct model of network. This firstly collects current voltage data form vectors through Feeder Terminal Unit. Combined with complex theory, each node degree calculated represent priority, topology partitioned regional model. Secondly, it builds feature extracting Deep Neural mine mapping relations between...