Monitoring of tool condition is one of the most important techniques to be developed in the automatic cutting processes as it can help to prevent damages of machine tools and work pieces. Power monitoring technique is an effective method for identifying tool states. However, it is difficult to distinguish sources which led to the power signal drop. In order to solve the problem, wavelet transform algorithm was adopted to define inflexion of power signal, and wavelet threshold denoise technique was used to separate the characteristic inflexion of power signal. The simulation results show that the method is capable of detecting the cutting condition effectively.