Abstract
The transmission system is a critical part of the rail vehicle bogie, mainly responsible for power drive and transmission. The performance of the transmission system directly affects the safe operation of trains. This paper proposes a multi-sensor data fusion method combined with deep belief nets (DBN) and fuzzy integral algorithm (FI) to improve the accuracy and reliability of fault diagnosis for rail vehicle transmission systems. First, multi DBN classifiers are established for the vibration signals collected from the key components of transmission systems to carry out preliminary fault diagnosis. Then, FI is applied to fuse the preliminary diagnosis results of DBNs to obtain comprehensive judgment. The effectiveness of the approach is verified by the bearing dataset collected in lab. This method is simple and practicable, and possesses certain applicability.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
