Study on tool wear state monitoring based on EEMD information entropy and PSO-SVM

Abstract

Tool wear state is closely related to the workpiece surface, so tool wear monitoring has an important engineering significance. This paper proposes a tool for wear monitoring means based on EEMD information entropy and PSO-SVM. Firstly, the force signal of the cutting process collected force by the sensor is decomposed by EEMD, and information entropy of the decomposed signal was used as the tool wear feature quantity. Then the PSO-SVM model was used to classify and identify the extracted tool wear feature quantity, and the recognition accuracy of the method was 97.75%. Compared with BP neural network and SVM model without algorithm optimization, it can quickly and accurately identify three types of tool wear states meanwhile realizing monitoring of tool wear state.