In the performance of a spindle CNC system, its bearings play an important role. Many problems arising in a spindle CNC operation are linked to bearing faults. In this project, the accuracy of the instruments and devices used to monitor and control the motor system is highly dependent on the dynamic performance of its bearings. Thus, fault diagnosis of a motor system is inseparably related to the diagnosis of the bearing assembly. In this paper, bearing vibration frequency features are discussed for spindle CNC of bearing fault diagnosis. This paper then presents an approach for life prediction of spindle CNC rolling bearing using nonlinear regression analysis. Vibration data are used to assist in the design for controlling and rolling bearing fault diagnosis strategies. Then our results obtained indicate that controlling and rolling bearing fault diagnosis can be effective agents in life prediction and diagnosis.