Using Monte Carlo Simulations and Little's Law to Improve Process Planning

Production planning and scheduling are challenging with recent disruptions in the supply chain and increased demand for reduced lead times. With an increased demand for production and ever-changing delivery dates of raw materials, a dynamic production planning model with machine-operator-part-specific historical data is essential for small and medium-scale manufacturers. Based on the sales orders and inventory, machine production rates, and work-in-process information, Little's law estimates the initial lead time. To improve the accuracy of the lead time, a Monte Carlo simulation based on the historical data of the machine-operator-part production rate is used along with the queuing principles and theory of constraints. The theory of constraints is used to facilitate issues such as preventive maintenance, unscheduled machine breakdown, etc. The dynamic nature of the shop floor issues is used to update the Monte Carlo simulations to improve the process flow and the lead time estimation. This model was implemented as a case study at a cutting tool manufacturing plant to reduce lead time and increase customer satisfaction. Finally, the paper reports the case study's findings to estimate the lead time effectively and facilitate the production planning and scheduling process. Overall, the results showed that the model has assisted in reducing the lead times and backorders, proving the present study's hypothesis. Using Little's law and Monte Carlo simulation using realtime data has enabled an accurate estimate of the lead time and improved customer satisfaction.