Health Condition Monitoring Based on Deep Learning
1Nanjing Forestry University, Nanjing, China
2University of Macau, Macau, Macau
3Southeast University, Nanjing, China
4Nanjing University of Information Science & Technology, Nanjing, China
5University of Alberta, Edmonton, Canada
Health Condition Monitoring Based on Deep Learning
Description
Structural health condition monitoring technology has recently garnered attention more frequently in early warning equipment failures and reducing enterprise economic loss, which have been demonstrated by the progress of machinery, vibration, information and computer subjects.
However, when large-scale equipment shows abnormalities, it will directly affect the economic losses of enterprises and could even cause large-scale accidents. Hence, advanced structural health condition monitoring technology is a hot topic at the moment, while deep learning theory (e.g., belief networks, autoencoders, convolutional networks, residual networks, adversarial networks) provides an efficient path for this topic. Due to the fact that deep learning can automatically learn potentially useful features directly from the original signal, thus emerging from the dependence of priori knowledge, this provides deep learning with extensive application prospects in the field of structural health condition monitoring.
The aim of this Special Issue is to collect the recent results on recent developments, ideas and applications of deep learning in the field of health condition monitoring. We also accept achievements about novel perspectives, currently ongoing research, and discussions regarding existing methods. We welcome original research and review articles.
Potential topics include but are not limited to the following:
- Machine learning
- Deep learning
- Transfer learning
- Meta-Learning
- Condition monitoring
- Health management
- Fault diagnosis
- Life prediction
- Feature extraction