Sensor Data Modeling and Model Frequency Analysis for Detecting Cutting Tool Anomalies in Machining

Abstract

Tool condition monitoring (TCM) in advanced manufacturing is concerned with cutting tool operational status monitoring and damage diagnosis. In the present study, an innovative TCM approach based on sensor data modeling and model frequency analysis is proposed. The new approach creates a paradigmatic shift to the conventional TCM techniques and can potentially realize autonomous cutting tool anomaly diagnosis satisfying the requirement of advanced manufacturing. When applying the proposed approach, the data from sensors are not directly utilized for monitoring cutting tool status. Instead, the data from sensors are utilized to build a dynamic process model. This allows the unique frequency-domain properties of the machining process to be extracted and used to reveal, in real time, cutting tool health conditions. Experimental studies are conducted to verify the effectiveness of the proposed approach and to demonstrate the superiority of the new approach over conventional TCM techniques.