A novel Robot Joint Bearing fault diagnosis method based on VMD in BP neural network

摘要

Aiming at the problem that the bearing is difficult to diagnose under noise environment, a fault diagnosis method for rolling bearing based on Variation Mode Decomposition (VMD) and Back Propagation (BP) neural network is proposed. The method firstly uses VMD to decompose the time domain signal of bearing vibration into several intrinsic mode function, finds the energy of each component, and inputs the energy as a feature to the BP neural network for training. This method can well identify the fault type of the bearing.