Cutting Tool Wear Monitoring Based on Wavelet Denoising and Fractal Theory

Monitoring of metal cutting tool wear for turning is a very important economical consideration in automated manufacturing. In the process of turning, the vibration signals of cutting tool become more and more irregular with the increase of tool wear. The degree of tool wear can indirectly be determined according to the change of vibration signals of cutting tool. In order to quantitatively describe this change, the wavelet and fractal theory were introduced into the cutting tool wear monitoring area. To eliminate the effect of noise on fractal dimension, the wavelet denoising method was used to reduce the noise of original signals. Then, the fractal dimensions were got from the denoised signals, including box dimension, information dimension, and correlation dimension. The relationship between these fractal dimensions and tool wear was studied. Use these fractal dimensions as the status indicator of tool wear condition. The experiments result demonstrates that wavelet denoise method can efficiently eliminate the effect of noise, and the change of fractal dimensions can represent the condition of tool wear.