Development of Machining Condition Monitoring System Using Piezoelectric Sensor Analyzed by I-Kaz Multilevel Method

Abstract

Cutting tool wear is found to be the major cause affecting the finished product in term of surface finish quality, dimensional precision and the cost of the defect. This paper proposes the development of a reliable machine condition monitoring system by using a low-cost piezoelectric sensor to monitor the flank wear progression on the cutting tool. The wear of the cutting insert was measured and recorded using Mitutoyo microscope under different operational conditions in turning process. A single channel piezoelectric sensor was mounted at the tool holder to measure the deflection on the cutting tool in the tangential direction during the machining process. The signal was transmitted to the piezoelectric amplifier device, then to data acquisition and finally to the computer system. I-kaz Multilevel method was used to identify and characterize the changes in the signals from the sensor. Under different experimental set up, new tool wear models were successfully formulated. Good agreements between the predicted and measured tool flank wear land width show that the developed machine condition monitoring system can accurately predict tool flank wear. This monitoring system is an efficient and low-cost method for flank wear level prediction which can be used in the real machining industry.