EXPERIMENTAL EVALUATION OF A SMART MACHINING SYSTEM FOR FEEDRATE SELECTION AND TOOL CONDITION MONITORING

摘要

This research is focused on improving the efficiency of CNC machining by enabling automatic feedrate selection and tool condition monitoring (TCM). Sensor data, process models along with an Open Architecture Control (OAC) are integrated together as a test platform for a Smart Machining System (SMS). This SMS is used to investigate and develop the necessary algorithms required to calibrate, optimize, and monitor complex tool moves/geometries, as well as handle data collection/storage, and delays in sensing equipment. This paper focuses on evaluating the SMS with respect to online calibration, optimization, and TCM using a typical production part. The feedrate selection process allows the part to be cut 10% faster with a 20-40% lower peak cutting force when compared to the original "best practice" program provided by our industrial partner. TCM results show that the low cost power sensor can be effectively used to monitor tool wear if used in conjunction with a power model.