[Show abstract][Hide abstract] ABSTRACT: According to acoustic emission signal of cutting tool wear states, this paper presents a method of cutting tool condition identifying based on empirical mode decomposition (EMD) and Support Vector Machine (SVM). AE signal was decomposed into a series of intrinsic mode functions (Intrinsic mode function, IMF) by EMD, extract the energy of IMF as feature vector, SVM-based tool wear identifying model was constructed by learning correlation between extracted features and actual tool wear state. In the experiment, the tool wear state was divided into: normal cutting, medium wear and severe wear. This paper compared the results of wavelet packet decomposition (WPD) method shows that EMD method was more accurate than wavelet packet decomposition to extract features of tool wear. Experimental results by cutting GH536 and GH4169 show that cutting a variety of materials tool in tool wear identification, the method based on EMD and SVM can be used.
[Show abstract][Hide abstract] ABSTRACT: Acoustic Emission signal reflecting the tool wear state is made by phase space reconstruction that uses mutual information method and Cao method to determine time delay and embedding dimension for constructing phase space matrix. After reconstruction, by calculating singular spectral of phase space matrix, based on which characteristic vector is constructed. These characteristic vectors are combined with the Support Vector Machine for training, which supports Support Vector Machine classifier model to predict new data. Compared with classifier model gotten by AE signal being directly put into Support Vector Machine after phase space reconstruction, the AE signals based on KC9125 tool cutting 40CrNiMoA can increase forecasting accuracy from 90% to raise 98%.