Rotary machine composed of Bearings, gears and shafts plays an important role in the machine tools. These components are often subjected to high loading during operation. Defects are then initiated, propagated, developed and finally cause machine breakdown. The quality and the estimated time of delivery will then be affected, causing a higher repair and labor cost. For these reasons, development of a prognostics system which has the ability to detect anomaly in early stage is important for both the academic and the industry field. In this study, we use the Spectral Granger Causality to detect the anomaly of a rotary machine, and the bearing data provided by the Center of Intelligent Maintenance Systems (IMS) and self-construction multi-bearing experiments is used to demonstrate this proposed algorithm. We hope the results of this study will be a significant improvement in root cause diagnosis, fault localization and early anomaly detection. When the damage occurs, we can find out the root cause and location of fault; furthermore, the early anomaly can be detected by the cause-effect analysis between components, so the repair time will be reduced.
|Effective start/end date||2017/08/01 → 2018/07/31|
- rotary machine
- anomaly detection
- fault localization
- root cause diagnosis
- cause-effect analysis
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.