Tool wear monitoring plays an important role in the automatic machining processes. Therefore, a reliable method is necessary for practical application. In this paper, a new method based on cointegration theory was introduced to extract features from the cutting force signal in the milling process. Cointegration relationship between cutting forces of different directions could be found and the corresponding cointegration vector could also be calculated. In order to improve the reliability of pattern recognition, the cointegration vectors combined with the energy of the high-frequency components of the acoustic emission signals were used as features. Once all the features are extracted, they were trained and tested through a support vector machine model. Experiments were performed to verify this method and the results showed that it could efficiently recognize the tool wear status.