The objective of this work is to develop a tool condition monitoring system (TCMS) for machinery. The proposed TCMS is based on the analysis of the structure of the tool vibration signals with cutting force signals, sound signals and current of the spindle. A different drill wear conditions were artificially introduced to the neural network for prediction and classification. The experimental procedure for acquiring vibration and related data and extracting features to train and test the neural network models is detailed. The results demonstrate the effectiveness and robustness of using the vibration signals in proposed neural network for drilling and milling wear detection and classification. The used system is capable of accurate tool wear monitoring in around 97% accuracy.