The Study on Intelligent Tool Wear Monitoring Techniques

A novel method of tool wear monitoring based on variation features was proposed to increase recognized precision of monitoring system and solve the problem of feature selection under multi machining conditions. The trend of different signal features with the change of tool wear amounts were investigated through analyzing vibration signal, acoustic emission signal and cutting forces signal in time domain, frequency domain and time-frequency domain, the most sensitive features to tool wear were selected by means of synthesis coefficient, and the nonlinear relation between tool wear values and features was built by B-spline neural networks. The experimental results indicate that the proposed method can improve classifying accuracy and self-adjusting ability of tool wear monitoring system