Improving Machine Availability Through Sensor-Based Virtual Modeling in SIMIO: A Case Study of Smart Manufacturing Simulation

This study explores a simulation-based approach to improve machine availability in a manufacturing environment by integrating Smart Manufacturing principles and sensor-based modeling. Focusing on the case study of a paper envelope production line in a manufacturing plant in Peru, the study applies SIMIO software to simulate and compare two operational scenarios: the existing configuration without sensors and a proposed configuration with predictive sensors. In addition, the impact of unscheduled interruptions of the cutting machine on production was analyzed. Post-SIMIO simulation, real-world machine testing yielded a mean time between failures (MTBF) of 11.5 hours, a mean time to repair (MTTR) of 52 minutes, 78.5% operational availability, and an average daily output of 5400 envelopes. Simulating sensor detection of paper jams, blade breakage, and misalignment resulted in 92.3% availability in the enhanced scenario. This represents a notable improvement of 13.8% compared to the real-world scenario. These findings demonstrate that SIMIO's digital modelling and sensor-based predictive techniques can boost production capacity, decrease downtime, and increase machine availability without transforming the physical system. This study emphasizes the importance of simulation and smart manufacturing in optimizing industrial performance and reducing costs.