Online tool wear prediction in drilling operations using selective artificial neural network ensemble model

Abstract

Online tool wear prediction plays a key role in industry automation for higher productivity and product quality. In recent past, several artificial neural network (ANN) models using multiple sensor signals as inputs for prediction as well as classification of tool wear have been proposed. However, a single ANN used in these models is often tries, which could limit their wide applications due to the complicated procedure of constructing a single ANN model. This study proposed a selective ANN ensemble approach DPSOEN, where several selected component ANNs are jointly used to online predict flank wear in drilling operation. DPSOEN provides more simple training and better generalization performance than using single ANN and hence is easier to be used by operators who often are not good at ANN techniques. Two benchmark cases were used to evaluate the performance of DPSOEN in predicting flank wear. It shows improved generalization performance that outperforms those of single ANN and Ensemble ALL approach. The investigation proposed a heuristic approach for applying the DPSOEN-based model as an effective and useful tool to predict tool wear online with potential applications for tool condition monitoring in general. Analysis from this study provides guidelines in developing ANN ensemble-based tool wear prediction systems.