Fractal analysis of vibration signals for monitoring the condition of milling tool wear

Tool wear depends on the common effect of many factors in the milling process and it is a very complicated random motion process in its evolution process. In order to reveal the inherent law of such a seemingly random evolution process, pattern recognition is described for the milling tool wear conditions by means of chaotic theory. Factors that influence the consistency of the calculated fractal dimension based on fractal dimension of vibration signals are analysed in this study. The angle domain tracing method is adopted during acquisition of vibration signals to minimize the effect from spindle speed. A new method for calculating the fractal unscale range is proposed for determining the fractal dimension. This method is based on multi-segments' average and threshold, which can extend the scope of the fractal unscale range. The experimental results show that the fractal theory can be applied in the monitoring field for milling tool wear to be practicable.