Effective training data selection in tool condition monitoring system

Abstract

When neural networks (NNs) are used to identify tool conditions, the richness and size of training data are crucial. The training data set not only has to cover a wide range of cutting conditions, but also to capture the characteristics of the tool wear process. This data set imposes significant computing burdens, results in a complex identification model, and hampers the feasible application of NNs. In this paper, a training data selection method is proposed, and a systematic procedure is provided to perform this data selection. With this method, the generalization error surface is divided into three regions, and proper sampling factors are chosen for each region to prune the data points from the original training set. The quality of the training set is estimated by performance evaluation through decision making. In this work, SVM is used in the decision making method, and the generalization error is used as the performance evaluation criterion. The tradeoff between the generalization performance and the size of the training set is key to this selection. Experimental results have demonstrated that this selection strategy provides an effective and efficient training set, and the developed model based on this set is fast and reliable for tool condition identification. © 2005 Elsevier Ltd. All rights reserved.