Tool Wear Health Monitoring with Limited Degradation Data

In advanced manufacturing industries, there is a need to monitor the health of tools with the aim of enhancing its lifetime. Often due to several reasons such as cost and time, many organizations are faced with the difficulty in collecting complete degradation data for monitoring the tool. As such, this makes tool wear prognostics a challenging problem in the real world. Although there have been a number of studies on tool wear prognosis, the monitoring of tool wear where the complete wear data is unavailable is still a challenge. This paper presents a framework for tool wear prognosis when the degradation data is limited. First, we present an analysis of tool wear diagnosis, in which the health of tool is classified into three categories of new tool, medium worn tool and high worn tool. Next, we present the analysis of tool wear prognosis by assuming linear and non-linear degradation curves of tool wear. Real data for tool wear is collected using five different tools used for cutting with three different degrees of flank wears, namely, new, medium and high worn. Results showed high classification and prediction accuracies in terms of the trends of prediction as well as the mean squared error.