• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.10a
• /
• pp.435-436
• /
• 2012

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2005.05a
• /
• pp.462-467
• /
• 2005

This paper presents virtual machining system in order to realize turning process in virtual space. A reliable virtual turning process simulation was developed based on the surface shaping system which is capable of considering geometric model, thermal error model, and vibration model. Accuracy of surface shape resulting from proposed machining simulator was verified experimentally. This paper also developed the watchdog agent that continuously assessed, diagnosed, and predicted performance of products and machines in machining. The Watchdog agent extracted feature signal using time-frequency analysis among various signals from multi-sensor and evaluated machining condition using performance confidence value.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.38 no.3
• /
• pp.100-107
• /
• 2015

Recently as the manufacturers want competitiveness in dynamically changing environment, they are trying a lot of efforts to be efficient with their production systems, which may be achieved by diminishing unplanned operation stops. The operation stops and maintenance cost are known to be significantly decreased by adopting proper maintenance strategy. Therefore, the manufacturers were more getting interested in scheduling of exact maintenance scheduling to keep smooth operation and prevent unexpected stops. In this paper, we proposedan integrated maintenance approach in injection molding manufacturing line. It consists of predictive and preventive maintenance approach. The predictive maintenance uses the statistical process control technique with the real-time data and the preventive maintenance is based on the checking period of machine components or equipment. For the predictive maintenance approach, firstly, we identified components or equipment that are required maintenance, and then machine parameters that are related with the identified components or equipment. Second, we performed regression analysis to select the machine parameters that affect the quality of the manufactured products and are significant to the quality of the products. By this analysis, we can exclude the insignificant parameters from monitoring parameters and focus on the significant parameters. Third, we developed the statistical prediction models for the selected machine parameters. Current models include regression, exponential smoothing and so on. We used these models to decide abnormal patternand to schedule maintenance. Finally, for other components or equipment which is not covered by predictive approach, we adoptedpreventive maintenance approach. To show feasibility we developed an integrated maintenance support system in LabView Watchdog Agent and SQL Server environment and validated our proposed methodology with experimental data.