The Spindle system is an important functional component of CNC machine tool, and its operating status directly affect the reliability of machine tool and the machining accuracy of parts. In order to achieve real-time monitoring, fault warning and maintenance strategy optimization, a status monitoring scheme was designed for machining center spindle system, and the hardware and software systems of status monitoring platform were developed and built. The wavelet de-noising method and empirical mode decomposition (EMD)-support vector machine (SVM) algorithms were used to process and analyze the signals, so as to achieve the status real-time monitoring and diagnosis of typical fault status for the machining center spindle system. Based on the spindle status monitoring system, the spindle belt looseness fault status monitoring test was carried out, and the accuracy of recognizing the typical fault status of the spindle system was verified.