A new method of chatter prediction based on discrete hidden Markov models (DHMM) is proposed for dynamic patterns of chatter gestation in cutting process. At first FFT features are extracted from the vibration signal of 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 and classification. Finally the results of chatter gestation recognition and chatter prediction experiments are presented and show that the method proposed is effective.