An adaptive procedure for tool life prediction in face milling

Abstract

Accurate prediction of tool life is essential to guarantee surface quality and economics of cutting operations in face milling. This article presents a procedure for tool life prediction through in-process adaptation of tool wear rate based on indirect measures. The procedure effectively accounts for the uncertainty of tool wear progress owing to the complexity of the machining process. First, sensor fusion of spindle motor current AC and DC portions is taken to estimate the actual tool wear through relevance vector machine. Then, a tool life prediction model relating flank wear with cutting time is proposed for tracking the progress of tool wear under certain cutting settings. Further, a recursive least square algorithm is developed to update the parameters of the tool life prediction model by considering the error between the predicted tool wear and the estimated tool wear. Finally, the updated model capturing the uncertainty of tool wear progress is used to predict tool life in face milling. Tool life experiments validate that the adaptive procedure can quickly track the progress of tool wear, and make more accurate prediction of tool life compared with the procedure with constant model parameters.