A method for tool condition monitoring based on sensor fusion

This paper presents a multi-sensor information fusion method for tool condition monitoring (TCM) using acoustic emission and cutting sound as monitoring signals. In order to make the cutting state in experiments closer to that in actual production, the traditional data acquisition method was improved. Using time–frequency analysis methods and multi-fractal theories, each kind of signal was filtered and their features were extracted according to characteristics respectively. The decision level fusion method was used for realizing information fusion by the model of support vector machines (SVMs) ensemble. Its base layer composes of two models of SVMs for regression (SVRs). Before training, the two SVRs were optimized by multiple population genetic algorithm including input features selection and model parameters optimization. Its decision layer is a model of SVM for classification or SVR, which is used for the combined decision according to the sub-decisions of SVRs in the base layer. The test results of SVMs ensemble show that the method can be used effectively for classification of tool wear condition and prediction of tool wear quantity. It can make information of the two sensors complement each other and is better than methods using a single sensor for TCM.