Co-guest edit a special issue in the journal MST on condition monitoring - 个人主页 - 李响 Xiang Li
Continuous learning based condition monitoring for crucial components
Guest Editors
Changqing Shen Soochow University, China
Xiang Li Xi'an Jiaotong University, China
Min Xia Lancaster University, UK
Darren Williams The Welding Institute, UK
Miguel Martínez García Loughborough University, UK
Scope
Crucial components fault diagnosis has become an indispensable technology in modern industrial complex systems due to the rapid development of high-speed heavy load and complex mechanical equipment. Usually, the condition monitoring tasks are submitted in a sequence during addressing a series of fault diagnosis tasks with increments of working conditions, fault types or machines that often occur in real-world scenarios. Compared with transfer learning- and meta-learning-based fault diagnosis models that focus only on the performance of the model on the target task and perform poorly on previous tasks due to catastrophic forgetting, continual learning-based fault diagnosis model requires good performance on all learned tasks and does not need all historical fault data to retrain the model. Continual learning-based fault diagnosis models can constantly learn knowledge of new fault diagnosis tasks to reduce training costs and accumulate this diagnosis knowledge to improve the reliability and generalization capabilities of the diagnosis model.
To promote effective intelligent condition monitoring, a focused session in this area will be organized as a platform to present high-quality original research on the latest developments of continual learning based condition monitoring methods. Potential topics include but are not limited to the following:
- Continual learning of deep models for crucial components fault diagnosis and prognosis
- Degradation analysis for crucial components
- Cross-domain learning for robust condition monitoring
- Continual domain adaptation or domain-incremental learning for condition monitoring
- Condition monitoring with fault types increments
- Condition monitoring with machine increments
- Few-shot continual learning for condition monitoring
- Domain generalization to unseen working conditions of machines
- Adaptive fault diagnosis model for varying conditions
- Life-long learning of machine fault diagnosis model
How to submit
Before submission, authors should carefully read the journal's author guidelines.
Prospective authors should submit an electronic copy of their complete manuscript through the journal online system by doing the following:
- Visit http://mc04.manuscriptcentral.com/mst-iop
- Select 'Continuous learning based condition monitoring for crucial components' from the drop-down list.
Submission deadline
The journal will consider submissions until 31 October 2022. Accepted papers will be published as soon as possible.
-
2024
01-29
-
2023
12-31
-
2023
11-15
-
2023
10-01
-
2023
07-03
-
2023
04-16