Investigation on early fault classification for rolling element bearing based on the optimal frequency band determination

Condition monitoring and fault diagnosis of working machine become increasingly important during the manufacturing process because they are closely related to the quality of product. In the meanwhile, they are crucial for early fault diagnosis of rolling element bearing (REB) as a machine always works in an off-design condition for machine tools. The key issue of REB early fault diagnosis is the optimal frequency band determination based on envelope analysis. In this research, a new method is proposed to determine the best frequency band for REB fault diagnosis by using a reference signal to determine the analyzed frequency band. The best frequency band is obtained according to the variance by comparing current condition with a normal one. To verify the effectiveness of this method, simulation signal and experimental signal in the test rig are applied for investigation. As well, practical monitored REB early fault diagnosis is also investigated to verify the effectiveness of this method. It can be concluded that this method can improve the accuracy for pattern recognition and benefit the development of REB fault diagnosis for manufacturing machines. This method assists us to develop an REB early fault diagnosis system, which is suitable for industrial application according to monitored REB condition investigation.