Comparison of cutting tool wear classification performance with artificial intelligence techniques

Abstract. Optimal replacement of machining cutting tools is a major challenge in today's manufacturing industry. Due to the degradation tool during machining, late leads risk producing parts that do not meet technical specifications, while early increases machine downtime and costs. To replace at right time, it necessary monitor their degradation. Therefore, this paper compares classification performance different artificial intelligence approaches classify condition from signals. Different approaches, namely: Artificial Neural Network (ANN), Support Vector Classifier (SVC), Random Forest (RF) k-Nearest Neighbour (k-NN) are tested, compared. It highlighted ANN RF methods obtain better performances (88.8% 86.4%, respectively) than rest (80%). Nevertheless, all can satisfactory manner (i.e., 80% accuracy). A comparison training times highlights neural network takes longer other approaches. However, with computational power currently available, an obstacle for implementation real applications as still be achieved couple minutes.