A Fault Early Warning Method of Train BatteryBased on Real-time Network Data
Battery is a direct power source of the train under the condition of pantograph dropping or emergency, which plays an important role in the safety train operation. In order to prevent the occurrence of locomotive failure and related devices cannot startup caused by battery failure, combining with wo...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Control and Information Technology
2021-01-01
|
| Series: | Kongzhi Yu Xinxi Jishu |
| Subjects: | |
| Online Access: | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2021.02.100 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Battery is a direct power source of the train under the condition of pantograph dropping or emergency, which plays an important role in the safety train operation. In order to prevent the occurrence of locomotive failure and related devices cannot startup caused by battery failure, combining with work principle and power supply characteristics, an online fault early warning method of train battery based on real-time monitoring data and expert rule is proposed. Under the premise of not deploying additional sensors, the time evolution property of signals related to battery working states in the real-time MVB data is analyzed, based on which, the warning fault features are extracted and expert rule module is constructed. Consequently, the real-time state assessment and fault early warning results are given. The method has been widely applied in train batteries of certain metro line, and no missing or false positives were found during the application, the verification results show the proposed method can effectively pre-warn battery fault. |
|---|---|
| ISSN: | 2096-5427 |