Detection of tool wear and breakage during machining operations is one of the major problems in control and optimization of the automatic machining process. In this study, the relationship between tool wear with vibration in the two directions, one in the machining direction and the other perpendicular to machining direction was investigated during face milling. For this purpose, a series of experiment were conducted in a vertical milling machine. An indexable sandvik insert and ck45 work piece were used in the experiments. Tool wear was measured by a microscope. It was observed that there was an increase in vibration amplitude with increasing tool wear. In this study adaptive neuro - fuzzy inference systems (ANFIS) and multi-layer perceptron neural network (MLPNN) were implemented for classification of tool wear. In this study for the first time, five different states of tool wear was used for accurate tool wear classification. Also to accuracy and speed of the network Principle Component Analysis (PCA) was implemented. Using PCA, the input matrix size was reduced to an acceptable order causing more efficient networks. ANFIS and MLP were trained using feature vectors extracted from the spectrum frequency and time signals. The results showed that for 86 final measurements, the ANFIS and MLP networks were successful in classifying different tool wear state correctly for 91 and 82 percent, respectively. ANFIS due to its high efficiency in diagnosing tool wear and breakage can be proposed as proper technique for intelligent fault classification.