EXPERIMENTAL STUDY AND LOGISTIC REGRESSION MODELING FOR MACHINE CONDITION MONITORING THROUGH MICROCONTROLLER-BASED DATA ACQUISITION SYSTEM

Abstract

Machine condition monitoring plays an important role in machining performance. A machine condition monitoring system will provide significant economic benefits when applied to machine tools and machining processes. By applying Taguchi design method, real-time pilot experimental study was conducted on a CNC machining center for monitoring the end mill cutting operations through the vibration data collection via a microcontroller-based data acquisition system. Featured machining signals were identified through data analyses and regression models were established that incorporates different combinations of featured machining signals and machining parameters in using logistic regression modeling approach. The onsite tests show that the developed logistic models including the featured machining signals can correctly distinguish worn and new cutting tools. Therefore, they can help construct decision-making mechanism for machine condition monitoring.