A Novel Improved ELM Algorithm for a Real Industrial Application

Table 2

Simulation results of classification using R-ELM for bearing fault detection.

Operation conditions	Training accuracy (%)			Testing accuracy (%)			Training time	Testing Time
	Healthy bearing	Faulty bearing	Total	Healthy bearing	Faulty bearing	Total
Normal	96.15	96.15	96.15	97.50	94.83	96.17	0.0589	0.0312
Interferential	92.63	92.28	92.46	95.42	90.42	92.92	0.0612	0.0301