Application of the character extraction with mutative scales on states recognition

The Numerical Control technology is applied to the high-accuracy mechanical working widely. So it is very important to monitor its states in time to ensure the maching accuracy. In the paper, a new states recognition method is proposed to improve the precision of state recognition. Firstly, the character extraction with mutative scales is applied to achieve the characteristic values. Secondly, the Hidden Semi-Markov model is built to identify the different runing states. Thirdly, the new method is compared with the traditional one by the example of abrasion of the headstock bearing in NC machines. According to the simulation and experiment researches, it indicates that the signal characters with more state information can be obtained pertinently by using the character extraction with mutative scales. And the accuracy of recognition is 98.44% in the 192 test samples, improved evidently than the traditional one. And the new character extraction method can be used in the technology domain widely.