Tool Wear Monitoring and Failure Prediction Based on Hybrid SOM-DHMM Architecture

A method of pattern recognition of tool wear based on discrete hidden Markov models (DHMM) is proposed to monitor tool wear and to predict tool failure. At the first FFT features are extracted from the vibration signal and cutting force in cutting process, then FFT vectors are presorted and coded into code book of integer numbers by SOM, and these code books are introduced to DHMM for machine learning to build up 3-HMMs for different tool wear stage. And then, pattern of HMM is recognised by using maximum probability. Finally the results of tool wear recognition and failure prediction experiments are presented and show that the method proposed is effective.