Parameter prediction using machine learning in robot-assisted finishing process

Abstract

In finishing processes equipped with real-time process monitoring, analyzing real-time data acquired is vital to ensure product quality and safety compliance. The quality and dimensions of a finished product is often times dictated by the process parameter set initially. However, changes in parameter occurs whenever an unexpected event such as an equipment failure or voltage fluctuations occurs. This could result in a finished product with a below par quality and subsequently delays in production due to rework or machine downtime. With an indirect monitoring method to continually monitor these parameters such as spindle speed, these occurrences can be minimized. Here lies in the benefit of an integrated parameter prediction model, which is able to detect deviation from normal operation early, hence enabling the capability of delivering actionable insights in a real-time basis to shop-floor engineers. This paper presents a parameter prediction method tested successfully on data acquired from a robotassisted deburring process.