Tool condition monitoring in milling process using multifractal detrended fluctuation analysis and support vector machine

Tool wear will lead to the reduction of surface quality and machining accuracy. Therefore, tool condition monitoring is vital to the improvement of industrial production efficiency and quality. In this paper, first of all, the internal mechanism of the milling process and the performance characteristics of the milling signals were analyzed. It is found that there are different trends between the large and small fluctuations of milling signals in the process of tool wear increasing. This property can be characterized by various parameters of multifractal spectrum to establish the relationship between tool wear and multifractal parameters. By analyzing the changes of multifractal spectrum parameters, the tool wear monitoring can be realized. Then, the multifractal detrended fluctuation analysis (MFDFA) method is used to calculate the mean square error, generalized Hurst exponent, and multifractal spectrum parameters, which are the eigenvectors, and establish its relationship with tool wear. Finally, the tool condition diagnosis is conducted by a support vector machine (SVM). The results show that the tool condition monitoring method of MFDFA combined with SVM is proved to be effective and the multifractal parameters of MFDFA are very sensitive to tool wear.