Peningkatan efisiensi mesin wirecut melalui condition-based maintenance berbasis data multisensor

Abstract

This study aims to analyze the effect of machining parameter variations on the performance and stability of the Computer Numerical Control (CNC) Wire Electrical Discharge Machining (WEDM) process and to develop a multisensor-based Condition-Based Maintenance (CBM) approach. The research employs an experimental method by varying current, voltage, and wire speed, while monitoring machine conditions in real time using vibration and dielectric fluid temperature sensors. The collected data were analyzed using statistical and trend-based approaches to identify the relationship between machining parameters and machine condition indicators. The results show that increasing current and voltage combined with decreasing wire speed leads to higher discharge energy, resulting in increased vibration and temperature, as well as a significant reduction in wire break time from 60 minutes to 6 minutes. A critical transition is observed between the third and fourth parameter variations. Based on these findings, machine conditions are classified into three categories: normal, warning, and critical. The novelty of this study lies in the integration of machining parameters and multisensor data to establish a condition classification framework for early detection of wire break in WEDM processes. This study concludes that vibration and dielectric fluid temperature are reliable indicators for detecting machine degradation, and that the multisensor approach improves monitoring accuracy and supports the implementation of predictive maintenance to enhance reliability and operational efficiency in manufacturing processes.