Efficient method for detecting tool failures in high-speed machining process

Abstract

This research presents a method for detecting tool failures in high-speed face milling. This method detects tool failures from vibration signature maps. Tests were carried out at different tool failure levels, spindle speeds, feed rates, and workpiece mountings. Vibration signals were obtained with an accelerometer and processed using the continuous wavelet transform methodology. The vibration signature maps showed that healthy cutting tools produce a periodic insert passing frequency and its harmonics. In contrast, a damage tool generates additional nonlinear and transient frequencies at nonsynchronous frequencies. The experimental results agree with vibration signature maps obtained from a simulated cutting force model. The proposed method is effective as a tool failure detection method when transient and nonlinear behaviors are presented in face milling process. Moreover, the proposed method showed good results at different process parameters and for several types of tool failures. Finally, it is important to point out the use of accelerometers because they present several advantages against other types of sensors. Advantages such as low cost, wide bandwidth, and easy implementation are important characteristics for tool condition monitoring in high-speed machining.