Real-time tool condition monitoring in milling by means of control charts for auto-correlated data

Real time monitoring of tool conditions and machini ng processes has been extensively studied in the la st decades, but a wide gap is still present between re sea ch activities and commercial tools. One of the factors which currently limit the utilization of these syst ems is the low flexibility of off-the-shelf solutio ns: in most cases they need dedicated off-line training session t acquire the reference patterns and thresholds, and/or the need for several input data to be defined a priori by a human operator. Instead of exploiting off-line learning sessions and a priori defined thresholds, this pape r proposes an approach for automatic modelling of a cutting process and real-time monitoring of its stability t hat is based only on data acquired on-line during t he process itself. This approach avoids any a-priori assumptio n about expected signal patterns, and it is charact erized by an innovative implementation of well known Statistical Process Control techniques. In particular, with re ga d to milling processes, the paper proposes the utilizati on of cross-correlation coefficient between repeati ng signal profiles as the feature to be monitored, and an EWM A (Exponentially Weighted Moving Average) control c hart for auto-correlated data as monitoring tool.