This paper presents a real-time tool wear performance monitoring system from data collection and data analysis to real-time tool wear fault classification. The lack of a monitoring system approach in tool wear fault detection for CNC machine applications leads to the effect on tool lifetime and production effectiveness. To overcome this issue, the tool wear fault is approached using a vibration sensor embedded in the spindle of the CNC machine. The state of the cutting edge is assessed based on wear observed on the flank surface during the milling processes. The experiment method in this research employed High-speed steel (HSS) end mills as the cutting tools. The tests were conducted with two different tools under combinations of the cutting speed (800 m/min) and the depth of cut varies at 0.5 mm and 1 mm. The vibrations due to the flank wear were measured using piezoelectric sensors embedded within a spindle of a CNC machine and the vibration data was recorded using a reliable data acquisition (DAQ) device during the milling process. Additionally, the tool wear image is captured using the microscope and the flank surface of tool wear is measured to analyze the tool wear lifetime. The method for signal analysis is carried on with the implementation of the time domain analysis and frequency domain analysis, Fast Fourier Transform (FFT) representation for vibration signal. Based on the result achieved, the amplitude of the vibrations increased with increasing the depth of cut and the flank wear value. The lifetime of the tool achieved accelerated wear during cycle 6 for Tool 1 (0.6425 mm) and Tool 2 (0.9615 mm) of the experiment.