Tool breakage diagnosis in face milling by support vector machine

Abstract

This paper introduces a new diagnosis technique for tool breakage in face milling using a support vector machine (SVM). The features of spindle displacement signals are first fed into the kernel-based SVM decision function. After the SVM learning procedure, the SVM can respond in real-time to automatically diagnose tool fracture under varying cutting conditions. Experimental results show that this new approach can detect tool breakage in a wide range of face-milling operations.